for Journals by Title or ISSN
for Articles by Keywords
Journal Cover
Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of
Journal Prestige (SJR): 1.547
Citation Impact (citeScore): 4
Number of Followers: 53  
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 1939-1404
Published by IEEE Homepage  [191 journals]
  • Frontcover
    • PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • IEEE Geoscience and Remote Sensing Societys
    • PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • IEEE Geoscience and Remote Sensing Societys
    • PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Institutional Listings
    • PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Foreword to the Special Issue on Analysis of Multitemporal Remote Sensing
    • Authors: L. Bruzzone;B. Deronde;E. Swinnen;
      Pages: 4548 - 4550
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Unsupervised Change Detection in Polarimetric SAR Data With the
           Hotelling-Lawley Trace Statistic and Minimum-Error Thresholding
    • Authors: Mohsen Ghanbari;Vahid Akbari;
      Pages: 4551 - 4562
      Abstract: Increased discrimination capability provided by polarimetric synthetic aperture radar (PolSAR) sensors compared to single and dual polarization synthetic aperture radar (SAR) sensors can improve land use monitoring and change detection. This necessitates reliable change detection methods in multitemporal PolSAR datasets. This paper proposes an unsupervised change detection algorithm for multilook PolSAR data. In the first step of the method, the Hotelling-Lawley trace (HLT) statistic is applied to measure the similarity of two multilook covariance matrices. As a result of this step, a scalar test statistic image is generated. Then, in the second step, a generalized Kittler and Illingworth (K&I) minimum-error thresholding algorithm is developed to perform on the test statistic image and discriminate between changed and unchanged areas. The K&I thresholding algorithm is based on the generalized Gamma distribution for statistical modeling of change and no-change classes. The proposed methodology is tested on a simulated PolSAR data and two C-band fully PolSAR datasets acquired by the uninhabited aerial vehicle SAR and RADARSAT-2 SAR satellites. The experiments show that the proposed algorithm accurately discriminates between change and no-change areas providing detection results with noticeably lower error rates and higher detection accuracy values compared to those of a CFAR-type thresholding of the HLT statistic. Also, the performance of the HLT statistic compared to the other statistics applied on the multilook polarimetric SAR data is assessed. Goodness-of-fit test results prove that the estimated generalized Gamma class conditional models adequately fit the corresponding change and no-change classes.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Machine Learning Regression Techniques for the Silage Maize Yield
           Prediction Using Time-Series Images of Landsat 8 OLI
    • Authors: Hossein Aghighi;Mohsen Azadbakht;Davoud Ashourloo;Hamid Salehi Shahrabi;Soheil Radiom;
      Pages: 4563 - 4577
      Abstract: Machine learning (ML) techniques have been utilized for the crop monitoring and yield estimation/prediction using remotely sensed data. However, these methods have been investigated less for yield prediction of some crops, such as silage maize, which can be cultivated at various times in different fields of an area. Inconsistency between fields for satellite-derived normalized difference vegetation index (NDVI) temporal profiles can lead to some difficulties in yield prediction methods using time series of remotely sensed data. Therefore, this research has investigated silage maize yield prediction based on time series of NDVI dataset derived from Landsat 8 OLI. This paper employed advanced ML techniques including boosted regression tree (BRT), random forest regression (RFR), support vector regression, and Gaussian process regression (GPR) approaches and compared their performance with some proposed conventional regression methods. For this purpose, the NDVI values of all silage maize fields were averaged and integrated to produce a two-dimensional dataset for each year. The ML techniques were employed 100 times and their evaluation metrics were used to evaluate their performances and also analyze their stability. Finally, all the results of each ML technique were averaged to produce silage maize yields. The comparisons between the results of these methods indicate that the BRT technique, with the average $R$ value higher than 0.87, outperforms other ones for all years. It was followed by RFR with almost same performance as GPR technique. This research demonstrated that some advanced ML approaches can predict the silage maize yield and they are less sensitive to inconsistency of NDVI time series. The results also showed that RFR was the most stable method to predict the maize yield in 2015, while it was trained using 2013–2014 dataset.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Spatial and Temporal Variability of Root-Zone Soil Moisture Acquired From
           Hydrologic Modeling and AirMOSS P-Band Radar
    • Authors: Wade T. Crow;Sushil Milak;Mahta Moghaddam;Alireza Tabatabaeenejad;Sermsak Jaruwatanadilok;Xuan Yu;Yuning Shi;Rolf H. Reichle;Yutaka Hagimoto;Richard H. Cuenca;
      Pages: 4578 - 4590
      Abstract: The accurate estimation of grid-scale fluxes of water, energy, and carbon requires consideration of subgrid spatial variability in root-zone soil moisture (RZSM). The NASA Airborne Microwave Observatory of Subcanopy and Subsurface (AirMOSS) mission represents the first systematic attempt to repeatedly map high-resolution RZSM fields using airborne remote sensing across a range of biomes. Here, we compare 3-arc-sec (∼100 m) spatial resolution AirMOSS RZSM retrievals from P-band radar acquisitions over nine separate North American study sites with analogous RZSM estimates generated by the Flux-Penn State Integrated Hydrologic Model (Flux-PIHM). The two products demonstrate comparable levels of accuracy when evaluated against ground-based soil moisture products and a significant level of temporal cross correlation. However, relative to the AirMOSS RZSM retrievals, Flux-PIHM RZSM estimates generally demonstrate much lower levels of spatial and temporal variability, and the spatial patterns captured by both products are poorly correlated. Nevertheless, based on a discussion of likely error sources affecting both products, it is argued that the spatial analysis of AirMOSS and Flux-PIHM RZSM fields provides meaningful upper and lower bounds on the potential range of RZSM spatial variability encountered across a range of natural biomes.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Optical Classifications of Poyang Lake Water and Long-Term Dynamics Based
           on MERIS Observations
    • Authors: Qi Guan;Lian Feng;Xingxing Kuang;
      Pages: 4591 - 4603
      Abstract: Using observations from the Medium Resolution Imaging Spectrometer (MERIS) and an unsupervised (Iterative Self-Organizing Data Analysis Technique) clustering method, the class centers for four different optical classes (i.e., moderate turbid or Class I; turbid or Class II; extremely turbid or Class III; and clear waters or Class IV) of Poyang Lake water were determined. A squared-Mahalanobis distance-based classification scheme was then used to classify 320 MERIS data between 2003 and 2012 (∼2.7 images/month on average). Significant dynamics of the probability of occurrence (POO) for different classes were observed through long-term analysis. The extremely turbid and clear water classes dominated Poyang Lake, accounting for ∼70% of the total surface area within the entire time series. Class III and IV waters showed out-of-phase fluctuation patterns, while a large POO was observed in dry seasons for the extremely turbid water class (Class III), and the clear water class (Class IV) represented most of the lake in the wet seasons. The northern narrow water channel of Poyang Lake was generally characterized by Class II and III waters. In contrast, the high POO of Class IV was demonstrated in the southern main lake and some eastern and southern isolated sublakes. The hydrological analysis shows that the south-to-north water level gradients were positively correlated with the combined POOs of Classes II and III (R2 = 0.4) and that the gradients were negatively correlated with the POO of Class IV (R2 = 0.36). Significant relationships existed between the POOs of different classes and-local precipitation. This study provides critical information for future environmental conservation planning.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Convolutional Neural Network-Based Land Cover Classification Using 2-D
           Spectral Reflectance Curve Graphs With Multitemporal Satellite Imagery
    • Authors: Miae Kim;Junghee Lee;Daehyeon Han;Minso Shin;Jungho Im;Junghye Lee;Lindi J. Quackenbush;Zhu Gu;
      Pages: 4604 - 4617
      Abstract: Researchers constantly seek more efficient detection techniques to better utilize enhanced image resolution in accurately detecting and monitoring land cover. Recently, convolutional neural networks (CNNs) have shown high performances comparable to or even better than widely used and adopted machine learning techniques. The aim of this study is to investigate the application of CNNs for land cover classification by using two-dimensional (2-D) spectral curve graphs from multispectral satellite images. The land cover classification was conducted in Concord, New Hampshire, USA, and South Korea by using multispectral images acquired from 30-m Landsat-8 and 500-m Geostationary Ocean Color Imager images. For the construction of input data specific to CNNs, two seasons (winter and summer) of multispectral bands were transformed into 2-D spectral curve graphs for each class. Land cover classification results of CNNs were compared with the results of support vector machines (SVMs) and random forest (RFs). The CNNs model showed higher performance than RFs and SVMs in both study sites. The examination of land cover classification maps demonstrates a good agreement with reference maps, Google Earth images, and existing global scale land cover map, especially for croplands. Using the spectral curve graph could incorporate the phenological cycles on classifying the land cover types. This study shows that the use of a new transformation of spectral bands into a 2-D form for application in CNNs can improve land cover classification performance.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Comparing the Effects of Temporal Features Derived From Synthetic
           Time-Series NDVI on Fine Land Cover Classification
    • Authors: Yinghuai Huang;Xiaoping Liu;Xia Li;Yuchao Yan;Jinpei Ou;
      Pages: 4618 - 4629
      Abstract: Landsat data are an ideal data source for deriving fine-resolution land cover maps, and integrating temporal features extracted from time-series normalized difference vegetation index (NDVI) data achieves better performance. This paper compares the different roles of NDVI statistic features and phenology features in land cover classification at a finer scale. Time-series NDVI with fine resolution is first obtained by fusing Landsat-8 Operational Land Imager and moderate resolution imaging spectrometer (MODIS) NDVI via spatiotemporal fusion algorithm. Statistic and phenology features are then extracted from the fused data and added into random forest (RF) classifier. Performance under different classifiers and importance of phenology features are further discussed. Results show that both NDVI statistic features and phenology features have great effects on improving the classification accuracy after adding them to Landsat spectral bands. The overall accuracy is improved approximately 3% and 5%. Phenology features contain majority information of statistic features, and better reflect the seasonal variations of time-series NDVI, especially for vegetation types. Additionally, neural network classifier achieved similar trends of results with RF but lower accuracy, while support vector machine classifier seems to be poor in dealing with high-dimension temporal features, especially in regions with abundant vegetation. Among phenology features, maximum value, large integrated value, and base value have the highest importance scores, while start, end, and middle times of season provide extra information for identifying grass and nongrass.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Detecting Changes of Wheat Vegetative Growth and Their Response to Climate
           Change Over the North China Plain
    • Authors: Zhengjia Liu;Sisi Wang;
      Pages: 4630 - 4636
      Abstract: Wheat vegetative growth, defined as the stage from green-up date to heading date (STAGE), is a crucial phrase, which largely affects crop yield. Previous some studies mainly focused on site-based changes of STAGE. However, there are few studies concerning large-scale changes of STAGE, which limits our understanding of regional changes of STAGE in response to climate change. Here, we introduced robust satellite-based phenological algorithms as well as third-generation global inventory modeling and mapping studies normalized difference vegetation index for the period of 1982–2015 to spatially derive winter wheat green-up date, heading date, and STAGE over croplands of the North China Plain (NCP). Changes of STAGE and their response to climate change were then investigated. Results showed that a strong predicted ability of introduced heading date algorithm was observed with r of 0.88 (p < 0.01), bias of −1.0 day and RMSE of 4.9 days. We found that unlike the patterns of winter wheat green-up and heading date, STAGE spatially decreased from southwestern to northeastern NCP with regional averaged stage of 41.2 ± 4.6 days. Advanced green-up date faster than advanced heading date induced lengthened stage of entire NCP with 1 day/decade (R2 = 0.11, p = 0.06). Stage of 23.4% cropland pixels performed significantly lengthened trends (p < 0.05), mainly locating in western NCP. The relationships between STAGE and climatic variables suggested that compared to precipitation, temperature was more responsible for changes of STAGE (r = 0.59, p < 0.01). This study highlights important roles of remote sensing data and satellite-based phenologic-l algorithms for regional crop growth monitoring and management.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Climate Control on Net Primary Productivity in the Complicated Mountainous
           Area: A Case Study of Yunnan, China
    • Authors: Xiaobin Guan;Huanfeng Shen;Xinghua Li;Wenxia Gan;Liangpei Zhang;
      Pages: 4637 - 4648
      Abstract: In this study, the influence of altitude on the relationship between vegetation and climate was investigated via net primary productivity (NPP) in the mountainous Yunnan province of China. In order to undertake a detailed spatial analysis at a long-term level, a monthly 1-km NPP time series from 1982 to 2014 was constructed from multisource remote sensing data sets. The altitudinal variation of the relationship between NPP and climatic factors was disclosed at annual, seasonal, and monthly scales, respectively. The results indicated that the correlation between NPP and precipitation gradually decreases from positive to negative with the ascending elevation at an annual scale, which is completely the opposite to temperature. The relationships at seasonal and monthly scales are also consistent, but significant seasonal heterogeneity was found due to the uneven climate. It was also concluded that downward run-off is responsible for the altitudinal heterogeneity, in that high-elevation areas cannot easily retain water, and only low-elevation areas benefit from the increased precipitation. What is more, we also found that the impact of climatic drought on NPP is related to topography. Large river valleys help to facilitate droughts, but the negative impacts on NPP can be mitigated in the rugged area with fluctuating slope.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Indicator-Kriging-Integrated Evidence Theory for Unsupervised Change
           Detection in Remotely Sensed Imagery
    • Authors: Pan Shao;Wenzhong Shi;Ming Hao;
      Pages: 4649 - 4663
      Abstract: This study proposes a novel approach based on indicator kriging and Dempster–Shafer (DS) theory for unsupervised change detection (CD) in remote sensing images (DSK). Indicator kriging is integrated to the standard DS theory. A feature set with four difference images (DIs) providing complementary change information is initially generated. Subsequently, the mass functions for each DI are determined automatically using fuzzy logic, the four pieces of DI evidence are combined by DS theory, and a preliminary CD map is achieved. The preliminary CD map is then divided into three parts adaptively—weakly conflicting part of no change, weakly conflicting part of change, and strongly conflicting part—by calculating the evidence conflict degree for each pixel. Finally, the pixels in the weakly conflicting parts, which have little or no conflict, are labeled as the current class, and the pixels in the strongly conflicting part that contains misclassified pixels are reclassified based on indicator kriging. DSK combines the advantages of different DI features and solves the conflicting situations to a large extent. The main contributions of this study include the following: 1) introducing indicator kriging into CD to manage conflict information during DS fusion and 2) presenting a scheme for producing DI set with complementary change information, developing a novel DSK fusion model for information fusion, and defining the proposed CD framework. Experimental results verify that the proposed DSK is robust and effective for CD.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • A Five-Year Evaluation of SMOS Level 2 Soil Moisture in the Corn Belt of
           the United States
    • Authors: Victoria A. Walker;Brian K. Hornbuckle;Michael H. Cosh;
      Pages: 4664 - 4675
      Abstract: We compare Soil Moisture Ocean Salinity Level 2 Soil Moisture (L2SM) retrievals to the five-year in situ soil moisture dataset available for the predominately agricultural South Fork Iowa River (SFIR) watershed in the U. S. Corn Belt. SMOS L2SM is 0.039 m$^3$ m$^{-3}$ drier than the SFIR network soil moisture and has an unbiased RMSE (ubRMSE) of 0.062 m$^3$ m$^{-3}$ for the period of April 2013 to November 2017 (excluding DJF). The bias is 11% of the range of in situ soil moisture. The largest monthly dry biases occur in April (0.052 m$^3$ m$^{-3}$), July (0.072 m$^3$ m$^{-3}$), and November (0.061 m$^3$ m$^{-3}$). Potential sources of the dry bias we discuss are: bias in auxiliary modeled temperatures; errors in soil texture maps; and nonrepresentative parameterizations of single scattering albedo and soil surface roughness. Auxiliary skin temperature was c-lder than expected and may explain why SMOS L2SM has a slightly drier bias for evening overpasses. Increasing the parameterized soil surface roughness produces wetter SMOS L2SM retrievals but also decreases the range of SMOS L2SM. Random error in auxiliary surface temperature, edge-of-field locations of in situ sensors, and differences in sensing volume between SMOS and in situ sensors contribute to the soil moisture ubRMSE. ubRMSE can be decreased by using a nonzero single scattering albedo more representative of a corn and soybean canopy at the cost of increasing the dry bias.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Unsupervised Scene Change Detection via Latent Dirichlet Allocation and
           Multivariate Alteration Detection
    • Authors: Bo Du;Yong Wang;Chen Wu;Liangpei Zhang;
      Pages: 4676 - 4689
      Abstract: Scene change detection is the process of identifying the differences between the multitemporal image scenes, which has significant potential in the application of urban development and land management at the semantic level. Traditional scene change detection methods are based on the supervised scene classification, and then directly compare the independent classification results without considering the temporal correlation between the unchanged regions. However, few studies have focused on detecting the semantic changes of multitemporal image scenes with unsupervised methods. In this paper, we propose a novel unsupervised scene change detection method by using latent Dirichlet allocation (LDA) and multivariate alteration detection (MAD). First, the scene is represented by the bag-of-visual-words model, and adopt the union dictionary to ensure the consistency of dictionary space. Then, LDA is used to achieve the middle-level feature dimension reduction, and generate the common topic space of the two multitemporal image scene datasets. And finally, the MAD method was applied to detect the semantic changes of corresponding multitemporal image scenes. Two experiments with high-resolution remote sensing image scene datasets demonstrated that our proposed approach can get a better performance in unsupervised scene change detection without prior knowledge.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Dynamic Monitoring of the Lake Area in the Middle and Lower Reaches of the
           Yangtze River Using MODIS Images Between 2000 and 2016
    • Authors: Yuyue Xu;Wei Liu;Jia Song;Ling Yao;Saihua Gu;
      Pages: 4690 - 4700
      Abstract: The middle and lower reaches of the Yangtze river are an important component of the Yangtze River Economic Zone that is a center of immense biological wealth, apart from its social and economic importance in China. As the main supply of water sources, a complete understanding of the change in the lake area is essential for the development of the Yangtze River Economic Zone. In this paper, we collected Moderate Resolution Imaging Spectroradiometer medium resolution (500 m) data from 2000 to 2016 to examine the long-term variation of the four largest lakes in this area, Poyang Lake, Dongting Lake, Taihu Lake, and Chaohu Lake. Taihu Lake and Chaohu Lake have a relatively stable lake area. Because they are clearly affected by human activities, the inflow and outflow of water from these two lakes are almost the same. In contrast, Poyang Lake and Dongting Lake experience rapid and large short-term fluctuations in the water area. These two lakes with large drainage areas have high amounts of water flowing into and out of them. The area of Poyang Lake and Dongting Lake showed a downward trend before 2010. However, we found the annual minimum area of the two lakes increased by 60.51 km2/year (Poyang Lake) and 51.64 km2/year (Dongting Lake) after 2010. The timely and proper monitoring in this study is of major significance for protecting these lakes.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • SAR Image Change Detection Using Saliency Extraction and Shearlet
    • Authors: Yan Zhang;Shigang Wang;Chao Wang;Jinxin Li;Hong Zhang;
      Pages: 4701 - 4710
      Abstract: Change detection has recently become a topic of great significance in the field of remote sensing. However, as one of the traditional effective detection methods, synthetic aperture radar (SAR) image change detection based on wavelet transform fusion remains limited because of the existence of speckle noise and because multidirectional information has been underutilized. Therefore, we propose an unsupervised change detection method using saliency extraction and the shearlet transform. Saliency extraction is first used to homogenize registered images to reduce speckle noise. Using a subtraction operation for preprocessed binary images, we then obtain a saliency-guided difference image (DI) that includes the main contour change information. Then, the Gauss-log-ratio DI includes the detailed change information at the edge of the image and acts as an auxiliary DI. Next, two DIs are fused with the shearlet transform. During this process, the DI is decomposed into one low-frequency and four high-frequency subimages. The low-frequency subimage contains image contour information and the high-frequency subimages contain the edge information of the images. Compared to wavelet fusion, in our method, no extra fusion noise occurs because the shearlet transform performs multiscale analysis. The final change map can be obtained through maximum entropy segmentation. Real SAR image pairs in areas of Bern, Switzerland, and Suzhou, China, are used to verify the proposed change detection method. The experimental results demonstrate the effectiveness of the proposed method when compared to the reference methods.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Atmospheric Fronts Using RISAT-1 SAR Data: Case Studies for Shear Lines
    • Authors: Jagdish;Bipasha Paul Shukla;Abhisek Chakraborty;Prashant Kumar;Raj Kumar;
      Pages: 4711 - 4717
      Abstract: Atmospheric fronts are an important feature of the marine atmospheric boundary layer. In this paper, India's first synthetic aperture radar (SAR) mission, RISAT-1, is used to detect the atmospheric fronts especially shear lines over the Indian Ocean by studying their imprints on the sea surface using backscatter radar echo. For this study, a multitude of SAR images were analyzed for detecting potential front structure over the Arabian Sea, Bay of Bengal, and South Indian Ocean. Frontal identification, analysis, and characterization are carried with the help of an ancillary satellite and atmospheric model data as provided by the sea-surface temperature, lower tropospheric stability, vertical wind shear, etc. The computation of the thermal front parameter and front points derived from them along with the associated wind speed exhibit a discernible demarcation at the frontal boundary, with the wind speed difference in the range of 2–4 m/s. The study is first of its kind over the Indian Ocean (IO), where separate zones of the IO are explored to emphasize different frontogenesis mechanisms, based on ocean–atmosphere coupling.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Sea Surface Wind Speed Retrieval and Validation of the Interferometric
           Imaging Radar Altimeter Aboard the Chinese Tiangong-2 Space Laboratory
    • Authors: Lin Ren;Jingsong Yang;Yongjun Jia;Xiao Dong;Juan Wang;Gang Zheng;
      Pages: 4718 - 4724
      Abstract: This study focuses on the retrieval and validation of sea-surface wind speeds using data from the interferometric imaging radar altimeter (InIRA) aboard the Chinese Tiangong-2 space laboratory. First, an empirical model, KuLMOD2, is proposed, which is a revised version of the former Ku-band low incidence model (KuLMOD) that directly relates the normalized radar cross section σ0 to both the wind speed and incidence angle. The revised model extends the ranges of the incidence angle and wind speed and is thus applicable to the new InIRA data. The model coefficients are estimated by fitting precipitation radar data from the Tropical Rainfall Measuring Mission and collocated wind data from the European Centre for Medium-Range Weather Forecasts. The wind speeds are then retrieved from the InIRA data using KuLMOD2. For more efficient retrieval, a lookup table method is used to find the wind speed solution. Finally, the InIRA wind speeds are validated using collocated Advanced Scatterometer (ASCAT) wind speeds. The validation of the InIRA wind speed data shows that InIRA can capture regional changes and that the data have a bias of 0.02 m/s and a root-mean-square error of 1.58 m/s. This suggests that the InIRA data alone can provide valid wind speeds for future sea state bias correction of InIRA-derived sea-surface heights and that the InIRA data can act as a complement to data from other spaceborne wind sensors.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Real-Time Imaging Flow for High-Resolution Ice-Sounding Radar
    • Authors: Shinan Lang;Xiangbin Cui;Xiaojun Liu;Qiang Wu;Lin Li;Wenbo Zhang;Xin Zheng;
      Pages: 4725 - 4736
      Abstract: In order to determine a great capacity of ice thickness assessments in a short time on-site, we have designed a real-time processor by using the modern commercial DSP chip named TMS320C6678. It is essential to develop an appropriate real-time imaging algorithm adapted to this real-time processor. In this paper, we propose a novel real-time imaging algorithm named the range-Doppler algorithm (RDA) integrated with the shift-and-correlate (SAC) algorithm. The proposed method extends the standard RDA to be appropriate for numerous media while adding the SAC algorithm to realize azimuth FM rate estimation to obtain accurate echograms of interior reflecting horizons (IRHs) and bedrock of the ice sheets at different depths. Initially, theoretical study is performed to the introduced method. Next, the hardware architecture of the designed real-time embedded system is presented, as well as the implementation of the proposed method on this processor. As a final point, the method is applied to the replication point targets and high-resolution ice-sounding radar information in order to verify its correctness of ice layers picturing. Through the presented echograms of ice sheets and the comparisons with both preceding methods in both main features, we can establish that the designed real-time processor accompany with the proposed RDA integrated with the SAC algorithm is quite reliable to generate the high-resolution ice-sounding images deprived of lowering the capability to reduce the azimuth clutter.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • An Improved Automated Method to Detect Landfast Ice Edge off Zhongshan
           Station Using SAR Imagery
    • Authors: Xinqing Li;Lunxi Ouyang;Fengming Hui;Xiao Cheng;Mohammed Shokr;Petra Heil;
      Pages: 4737 - 4746
      Abstract: Landfast ice is an important component of the Antarctic sea ice. Its edge generally advances offshore to its annual maximum extent by mid-winter before retreating later in spring. This study presents an automated method to detect the seaward landfast ice edge (SLIE) at its maximum extent in the beginning in the austral spring (October) for a region northeast of the Amery Ice Shelf, East Antarctic. Here, the net gradient difference algorithm developed by Mahoney [1] has been extended to include the medium edge detection method to automatically delineate the SLIE using the sequential SAR data. The underlying method is to use a spatial gradient operation to identify potential edge pixels, before applying the noise removal using a baseline (2000–2008) SLIE, and a pixel connection technique to generate a contiguous edge. We show that in 2016, the SLIE extended 20 km (25%) further equatorward than in 2008. Good agreement has been achieved between the SLIE derived from our automated method and the manual SLIE extraction using the original SAR as well as a near-coincident Landsat-8 OLI image. The error in the automated approach is minimized when using three to four calibrated SAR images, all with the same incident angle and the maximum separation between them is less than 20 days. Our results confirm the potential of the method for operational application, and we expect it to promote the study of Antarctic landfast ice.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Estimation of Corn Yield by Assimilating SAR and Optical Time Series Into
           a Simplified Agro-Meteorological Model: From Diagnostic to Forecast
    • Authors: Maël Ameline;Rémy Fieuzal;Julie Betbeder;Jean-François Berthoumieu;Frédéric Baup;
      Pages: 4747 - 4760
      Abstract: The estimation of crop yield plays a major role in decision making and management of food supply. This paper aims to estimate corn dry masses and grain yield at field scale using an agro-meteorological model. The SAFY-WB model (simple algorithm for yield model combined with a water balance) is controlled by green area index (GAI) derived from optical satellite images (GAIopt), and the GAI derived from synthetic aperture radar (SAR) satellite images (GAIsar) acquired over two crop seasons (2015 and 2016) in the south-west of France. Landsat-8 mission provides the optical data. SAR information ($sigma _{{rm{VV}}}^circ $, $sigma _{{rm{VH}}}^circ $, and $sigma _{{rm{VH/VV}}}^circ $) is provided by Sentinel-1A mission through two angular normalized orbits (30 and 132) allowing a repetitiveness from 12 to 6 days. $sigma _{{rm{VH}}/{rm{VV}}}^circ $ is successfully used to derive GAIsar (R2 = 0.72, relative root mean square error (rRMSE) = 10.4%) over the leaf development stages of the crop cycle from a nonlinear function. Others SAR signal ($sigma _{{rm{VV}}}^circ $ and $sigma _{{rm{VH}}}^circ $) are too much related to soil moisture changes. At the opposite of GAIopt, GAIsar cannot be used alone in the model to accurately estimate vegetation parameters. Finally, the robustness of the results comes from the combination of GAI derived from SAR and optical data. In this condition, the model is able, thanks to the inc-usion of a new “production module,” to simulate dry masses and yield (R2> 0.75 and rRMSE < 12.75%) with good performances in the diagnostic approach. In the context of forecast, results offer lower performances but stay acceptable, with relative errors inferior to 13.95% (R2> 0.69).
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Fusion of Urban TanDEM-X Raw DEMs Using Variational Models
    • Authors: Hossein Bagheri;Michael Schmitt;Xiao Xiang Zhu;
      Pages: 4761 - 4774
      Abstract: Recently, a new global digital elevation model (DEM) with pixel spacing of 0.4 arcsec and relative height accuracy finer than 2 m for flat areas (slopes $ < $ 20%) and better than 4 m for rugged terrain (slopes $>$ 20%) was created through the TanDEM-X mission. One important step of the chain of global DEM generation is to mosaic and fuse multiple raw DEM tiles to reach the target height accuracy. Currently, weighted averaging (WA) is applied as a fast and simple method for TanDEM-X raw DEM fusion, in which the weights are computed from height error maps delivered from the Integrated TanDEM-X Processor (ITP). However, evaluations show that WA is not the perfect DEM fusion method for urban areas, especially in confrontation with edges such as building outlines. The main focus of this paper is to investigate more advanced variational approaches such as TV-$ L_{1}$ and Huber models. Furthermore, we also assess the performance of variational models for fusing raw DEMs produced from data takes with different baseline configurations and height of ambiguities. The results illustrate the high efficiency of variational models for TanDEM-X raw DEM fusion in comparison to WA. Using variational models could improve the DEM quality by up to 2 m, particularly in inner city subsets.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Impervious Surface Extraction From Multispectral Images via Morphological
           Attribute Profiles Based on Spectral Analysis
    • Authors: Changyu Zhu;Jun Li;Shaoquan Zhang;Changshan Wu;Bing Zhang;Lianru Gao;Antonio Plaza;
      Pages: 4775 - 4790
      Abstract: Impervious surfaces exhibit unique spatial characteristics in urban environments. The estimation of impervious surfaces is critical for the analysis of these environments. In this paper, we propose a new technique based on morphological attribute profiles for mapping impervious surfaces under a spectral mixture analysis model. A main feature of our newly developed method is that it can model different kinds of structural information, which represents an important competitive advantage over existing techniques. As a result, considering the special characteristics of urban environments, our new method for impervious surface extraction exhibits the potential to model complex urban backgrounds. Four kinds of remotely sensed data, including Landsat ETM+, GF-1, IKONOS and sentinel-2 collected over Guangzhou, China, are used in this work to test the performance of our approach in the task of extracting imperviousness from images with different spatial resolution. Our experimental results illustrate that the proposed method exhibits very good performance in the task of estimating the impervious surface distribution, with relatively high precision. Root-mean-square error (RMSE) was 10.89%, mean absolute error (MAE) was 8.37% and Bias was 1.4% for the ETM+ data. RMSE was 11.49%, MAE was 6.25% and Bias was 2.34% for the GF-1 data. The RMSE was 7.72%, MAE was 7.67% and Bias was 3.91% for the IKONOS data, respectively. These results are superior to those provided by other state-of-the-art methods. Furthermore, our results also show the effectiveness of the method in distinguishing bright impervious surface from the dark impervious surface, especially in high resolution remotely sensed images.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Integrated Approach for Lithological Classification Using ASTER Imagery in
           a Shallowly Covered Region—The Eastern Yanshan Mountain of China
    • Authors: Ran Wang;Jingyu Lin;Bo Zhao;Lu Li;Zhouxuan Xiao;Jürgen Pilz;
      Pages: 4791 - 4807
      Abstract: This paper studied the applicability of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data for lithological classification in the shallowly covered Eastern Yanshan Mountain of Eastern China. The interpreted objects include quartz sandstone, carbonate rock, gneiss, and andesite. An integrated approach was employed to process the remote sensing data: First, the matched filtering method, accompanied by the ASTER library and imagery spectra as reference, was used to enhance the targeted information, namely the remotely visible (typical) rock outcrops. As the andesite is frequently weathered to iron-rich minerals in the field, so the high-resolution SPOT6 3/1 image, instead of the ASTER image, was used to locate the outcrops. Second, the fractal digital number-frequency algorithm was developed to preliminarily extract the lithology anomaly patches; and the obtained geological anomalies were generalized into three types: anomalies related to outcrops, anomalies caused by different forms of the same lithology, and random noise. Third, digital elevation model derived slope masks, in combination with the spatial intersection operation, was used to eliminate the pseudo-outcrop anomalies and noise. Finally, the accuracy assessment was conducted by referencing the local rock-outcrop database, and the misclassification rates for quartz sandstone, carbonate rock, gneiss, and andesite are 8.9%, 12.5%, 23%, and 48.3%, respectively. This study has contributed a useful case study for remote-sensing lithology mapping in shallowly covered areas, and the proposed method should have a great potential to be applied to many similar cases.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Building Detection in Very High Resolution SAR Images Via Sparse
           Representation Over Learned Dictionaries
    • Authors: Sadjad Adelipour;Hassan Ghassemian;
      Pages: 4808 - 4817
      Abstract: The spatial resolution of synthetic aperture radar (SAR) images has significantly increased in the past few years. As a result, very high resolution images are available for interpretation of the urban area. Buildings are one of the most important parts of the urban area. In this paper, we propose a novel method for building detection from SAR images. First, a set of primary detections, using double bounce, layover, and shadow features, are made. These features are extracted using the order statistics constant false alarm rate method and power ratio detector. The detectors parameters are adjusted in such a way that all bright and dark areas are well extracted. Second, the K-singular value decomposition method is used to learn two dictionaries for discrimination of buildings from clutters. The main idea is to utilize recognition techniques in detection algorithms in order to reduce the number of the false alarms. Gray level statistical, textural, and shape features are used to form the dictionaries. In this step, a secondary set of detections are available, and the final detections are made by the fusion of these two sets. The effectiveness of the algorithm is evaluated by two different TerraSAR-X images from a densely built-up area. The results show that the proposed method is an effective way to detect building through single SAR images.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Complex Scene Classification of PoLSAR Imagery Based on a Self-Paced
           Learning Approach
    • Authors: Wenshuai Chen;Shuiping Gou;Xinlin Wang;Licheng Jiao;Changzhe Jiao;Alina Zare;
      Pages: 4818 - 4825
      Abstract: Existing polarimetric synthetic aperture radar (PolSAR) image classification methods cannot achieve satisfactory performance on complex scenes characterized by several types of land cover with significant levels of noise or similar scattering properties across land cover types. Hence, we propose a supervised classification method aimed at constructing a classifier based on self-paced learning (SPL). SPL has been demonstrated to be effective at dealing with complex data while providing classifier performance improvement. In this paper, a novel support vector machine (SVM) algorithm based on SPL with neighborhood constraints (SVM_SPLNC) is proposed. The proposed method leverages the easiest samples first to obtain an initial parameter vector. Then, more complex samples are gradually incorporated to update the parameter vector iteratively. Moreover, neighborhood constraints are introduced during the training process to further improve performance. Experimental results on three real PolSAR images show that the proposed method performs well on complex scenes.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Efficient Chirp Parameters Estimation Based on the Ringing Effect With
           Application to the Velocity Estimation of Ground Moving Targets
    • Authors: Amir Hosein Oveis;Mohammad Ali Sebt;Ali Noroozi;Reza Saleh;
      Pages: 4826 - 4834
      Abstract: This paper presents an efficient algorithm for the estimation of the chirp parameters, including the chirp rate and centroid frequency. The estimation mechanism is based on the ringing effect, which undesirably occurs in multipath scenarios. However, the deliberate ringing effect can be exploited for the estimation of the chirp parameters. The salient feature of the proposed method is the low computational burden, which makes its realization feasible for real-time applications. Furthermore, the proposed chirp rate estimator can be employed in low signal-to-noise ratio scenarios. The application of the proposed method is for the synthetic aperture radar in which the Doppler rate and the Doppler centroid frequency of a moving target are efficiently estimated and its radial and along-track velocities are correspondingly calculated.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Radio Frequency Interference Suppression for SAR via Block Sparse Bayesian
    • Authors: Xingyu Lu;Weimin Su;Jianchao Yang;Hong Gu;Hailong Zhang;Wenchao Yu;Tat Soon Yeo;
      Pages: 4835 - 4847
      Abstract: Radio frequency interference (RFI) can severely degrade the image quality for synthetic aperture radar (SAR). Traditional sparse recovery-based RFI suppression methods construct a joint dictionary to represent both the time-domain RFI and the useful target echo (UTE), thus, transforming the task of RFI suppression into a signal recovery problem. However, these methods generally have poor performance when the one-dimensional (1-D) range profiles are nonsparse. To overcome this problem, two RFI suppression algorithms are proposed based on a modified block sparse Bayesian learning (BSBL). In the first algorithm, the vector to be recovered is divided into several blocks of identical size. The Bayesian hyper-parameters corresponding to the RFI and UTE are learned separately by exploiting the temporal intrablock correlation, and then the nonsparse vector can be successfully recovered. In the second algorithm, the dictionary is adaptively tuned during the iteration process of BSBL, thus reducing the computational load. After recovering the UTE, a well-focused 2-D image can be obtained by traditional SAR imaging algorithms. With the use of properties of both the RFI and UTE, and by exploiting the intrablock correlation, the proposed RFI suppression methods outperform other sparse recovery methods, especially when the range profile is nonsparse. Simulation results demonstrate the superior performance of the proposed algorithms.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Triplet Hybrid Discriminative Fields Model Based on Bayesian Fusion for
           Unsupervised Nonstationary SAR Image Multiclass Segmentation
    • Authors: Peng Zhang;Ming Li;Wanying Song;Yan Wu;Lin An;
      Pages: 4848 - 4861
      Abstract: The discriminative random fields (DRF) model is suitable for analyzing images with complex textural structures and has achieved promising results in image segmentation. However, the DRF model does not consider the nonstationarity of synthetic aperture radar (SAR) images and lacks the ability to model SAR scattering statistics in nonstationary SAR image segmentation. In this paper, we propose a triplet hybrid discriminative random fields (THDF) model based on Bayesian fusion. According to its semantic structure, the THDF model belongs to hybrid discriminative models, and it provides the following promising contributions to nonstationary SAR image segmentation while inheriting the advantages of the discriminative models: first, it takes the nonstationarity of SAR images into account from the perspective of their texton appearances, and thus regulates the local label interaction patterns and considers the distribution differences of the congeneric image features in different stationary parts; and second, for nonstationary SAR images, it performs a fusion-type treatment of the nonstationary textural features and the SAR scattering statistics based on Bayesian fusion and, thus, captures the nonstationary information from SAR data in a more complete manner. The effectiveness of the proposed model is demonstrated through applications to both synthetic images and real SAR image segmentations.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Ionospheric Scintillation Impacts on L-band Geosynchronous D-InSAR System:
           Models and Analysis
    • Authors: Yuanhao Li;Cheng Hu;Dongyang Ao;Xichao Dong;Weiming Tian;Siwei Li;Jiaqi Hu;
      Pages: 4862 - 4873
      Abstract: The upcoming L-band geosynchronous differential interferometric synthetic aperture radar (GEO D-InSAR) system has the capability to monitor rapid deformations due to its excellent revisit capability. However, because of its low working frequency, the random ionospheric scintillation signal will degrade the deformation retrieval accuracy by giving rise to extra interferometric phase errors and obvious decorrelations in GEO D-InSAR interferograms. In this paper, aiming at impacts of ionospheric scintillations on GEO D-InSAR system, we theoretically establish its interferometric phase error and decorrelation models by using the scintillation statistical parameters directly. Simulations based on the scintillation sampling model, the Cornell university scintillation model, the phase screen mode, and the ionospheric scintillation signal acquired by the ground-based global positioning system receiver are carried out to verify the proposed model. Moreover, quantitative analyses of the ionospheric scintillation interferometric phase error and decorrelation impacts under different scintillation cases are obtained. The results verify that the proposed models and the analyses are effective. Meanwhile, they also suggest that the generated defocusing decorrelation dominates the ionospheric scintillation impacts on GEO D-InSAR, which can induce a coherence loss of more than 0.1 in the interferogram when only one image of the interferometric pair suffers the weak ionospheric scintillation.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Two-Level W-ESMD Denoising for Dynamic Deflection Measurement of Railway
           Bridges by Microwave Interferometry
    • Authors: Xianglei Liu;Sinan Li;Xiaohua Tong;
      Pages: 4874 - 4883
      Abstract: Aiming to reduce the influences of noise for dynamic deflection measurements of railway bridges by microwave interferometry, this paper proposes a two-level wavelet-based extreme-point symmetric mode decomposition (ESMD) denoising algorithm on the basis of the characteristics of different noise frequency scales. First, the ESMD method is adopted to decompose the obtained dynamic deflection signal into a series of intrinsic mode functions (IMFs) from high to low frequency. Second, the first-level denoising is performed to eliminate the influences of high frequency noise by integrating the heursure threshold rule, soft thresholding, and different decomposition scales for high or low frequency IMFs, respectively. Third, the reconstructed first-level denoised signal is further decomposed into a series of IMFs, from high to low frequency, by the ESMD method. Last, the second-level denoising is performed to eliminate the influences of low frequency noise and some residual high frequency noise. For the low frequency noise, by using the heursure threshold rule, soft thresholding and a lower decomposition scale, and for some residual high frequency noise by using minimax threshold rule, hard thresholding and a moderate decomposition scale, the results on both simulated and real dynamic deflection signals show that the proposed two-level denoising algorithm is superior to wavelet threshold denoising and conventional empirical mode decomposition-based denoising techniques.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • SAR Target CFAR Detection Via GPU Parallel Operation
    • Authors: Zongyong Cui;Hongbin Quan;Zongjie Cao;Shengping Xu;Chunmei Ding;Junjie Wu;
      Pages: 4884 - 4894
      Abstract: The constant false alarm rate with convolution and pooling (CP-CFAR) method, which can improve the detection efficiency via GPU parallel acceleration in the airborne synthetic aperture radar (SAR) images, is proposed in this paper. The constant false alarm rate (CFAR) method is one of the most widely used methods for target detection in airborne SAR images. However, since the CFAR is performed on a pixel-by-pixel basis, the time consumption will increase rapidly with the expansion of image scene. Even if the GPU is used for acceleration, the efficiency improvement is still limited, which cannot meet the real-time processing requirements. Therefore, the CP-CFAR method for the target detection of SAR images is proposed in this paper. The convolution layer uses the horizontal and vertical Sobel operators to improve the contrast between targets and background, and the pooling layer can reduce the processing dimension of the images. The convolution and pooling layers are added before the two-parameter CFAR, which can reduce the computational elements but without losing the main feature of the original image. More importantly, compared to the traditional CFAR, the proposed CP-CFAR is more suitable for GPU acceleration, which can improve the detection efficiency significantly. Experiments on the moving and stationary target acquisition and recognition SAR images with a size of 1478 × 1784 show that, compared with the traditional cell-averaging CFAR, two-parameter CFAR and their CPU, multithread CPU, and GPU acceleration modes, the proposed CP-CFAR with GPU acceleration can obtain the best detection performance with the highest acceleration ratio, and the operation time is less than 192 ms.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • CFAR-Based Adaptive PolSAR Speckle Filter
    • Authors: Rakesh Sharma;Rajib Kumar Panigrahi;
      Pages: 4895 - 4905
      Abstract: The patch-based polarimetric synthetic aperture radar (PolSAR) nonlocal means (NLM) speckle filters are efficacious in noise suppression and detail preservation, but are computationally inefficient. The objective of this paper is to develop a filter that provides better noise suppression and edge preservation along with reduced computational complexity for PolSAR applications. In this paper, the patch-based NLM adaptive speckle filter based on constant false alarm rate (CFAR) edge detector is proposed. The CFAR-based edge detector is used to generate a map that classifies the data into three regions: homogeneous, heterogeneous, and strong edge dominant regions. The proposed speckle filter adapts itself suitably based on the heterogeneity of the region using classified regions as a mask. The performance of proposed filtering technique is evaluated on 1-look simulated (generated by Monte Carlo simulation), 1-look RADARSAT-2, and 4-look AIRSAR data. The performance evaluation is done based on the extent of noise reduction measured by equivalent number of looks, edge preservation degree, bias in estimation, polarimetric structure preservation, and visual appearance. The performance of the proposed filtering technique is found to be better than the state-of-the-art speckle filtering techniques like refined Lee, NLM pretest, and NL-SAR. The order of computational complexity of the proposed filter is found to be better than the pretest or NL-SAR filters.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Pauli Phase Calibration in Compact Polarimetry
    • Authors: Shane R. Cloude;David G. Goodenough;Hao Chen;Yalamanchili S. Rao;Wen Hong;
      Pages: 4906 - 4917
      Abstract: In this paper, we consider the problem of true transmitter polarization state estimation for circular compact SAR modes. We employ two methods—the first using point targets such as trihedral reflectors, and the second, a new method, based on the Pauli phase observed over distributed targets like forest canopy. We first show how compact modes allow estimation of the Pauli phase for reflection symmetric scatterers. We show that this phase remains remarkably constant over forest canopies, depending primarily on the dielectric constant of constituent volume particles. We show that small imperfections in the transmit polarization state then lead to large errors in this phase estimate. These errors can then be used as the basis for a calibration strategy that allows estimation of a set of candidate true transmitter states. These can then be compared with the trihedral estimates for validation. We illustrate using L-band compact data from the JAXA ALOS-2 satellite and C-band data from the ISRO RISAT-1 satellite.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Emulation as an Accurate Alternative to Interpolation in Sampling
           Radiative Transfer Codes
    • Authors: Jorge Vicent;Jochem Verrelst;Juan Pablo Rivera-Caicedo;Neus Sabater;Jordi Muñoz-Marí;Gustau Camps-Valls;José Moreno;
      Pages: 4918 - 4931
      Abstract: Computationally expensive radiative transfer models (RTMs) are widely used to realistically reproduce the light interaction with the earth surface and atmosphere. Because these models take long processing time, the common practice is to first generate a sparse look-up table (LUT) and then make use of interpolation methods to sample the multidimensional LUT input variable space. However, the question arise whether common interpolation methodsperform most accurate. As an alternative to interpolation, this paper proposes to use emulation, i.e., approximating the RTM output by means of the statistical learning. Two experiments were conducted to assess the accuracy in delivering spectral outputs using interpolation and emulation: at canopy level, using PROSAIL; and at top-of-atmosphere level, using MODTRAN. Various interpolation (nearest-neighbor, inverse distance weighting, and piece-wice linear) and emulation [Gaussian process regression (GPR), kernel ridge regression, and neural networks] methods were evaluated against a dense reference LUT. In all experiments, the emulation methods clearly produced more accurate output spectra than classical interpolation methods. The GPR emulation performed up to ten times more accurately than the best performing interpolation method, and this with a speed that is competitive with the faster interpolation methods. It is concluded that emulation can function as a fast and more accurate alternative to commonly used interpolation methods for reconstructing RTM spectral data.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Remote Sensing Image Compression in Visible/Near-Infrared Range Using
           Heterogeneous Compressive Sensing
    • Authors: Jin Li;Yao Fu;Guoning Li;Zilong Liu;
      Pages: 4932 - 4938
      Abstract: Compressive sensing (CS) framework is very suitable for onboard image compression of high-resolution remote sensing cameras in the visible/near-infrared range (VI/NI-RSC) because it has the low-complexity in the sampling measurement stage. In this paper, we propose a new heterogeneous CS method for VI/NI-RSCs. Different from conventional CS methods evenly allocating sensing resources, the proposed method fully employs texture-feature information of remote sensing images to guide the allocation of sensing resources. More sensing resources are allocated to high-frequency regions, but fewer to low-frequency regions. The heterogeneous distribution of sensing resources obtains high reconstruction quality at the same compression performance, as well as high compression performance at the same level reconstructed quality. The shift of sensing resources is consistent with artificial image interpretations, i.e., human visual characteristics, where high-frequency regions, such as edges and textures, are the principal proof of the ground target identification. Experimental results indicate that the proposed method has better reconstruction quality than conventional CS method where texture-features are not utilized.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • $M^3text{Fusion}$ :+A+Deep+Learning+Architecture+for+Multiscale+Multimodal+Multitemporal+Satellite+Data+Fusion&rft.title=Selected+Topics+in+Applied+Earth+Observations+and+Remote+Sensing,+IEEE+Journal+of&rft.issn=1939-1404&;&rft.aufirst=Paola&;Dino+Ienco;Raffaele+Gaetano;Kenji+Ose;Ruggero+G.+Pensa;Stephane+Dupuy;">$M^3text{Fusion}$ : A Deep Learning Architecture for Multiscale Multimodal
           Multitemporal Satellite Data Fusion
    • Authors: Paola Benedetti;Dino Ienco;Raffaele Gaetano;Kenji Ose;Ruggero G. Pensa;Stephane Dupuy;
      Pages: 4939 - 4949
      Abstract: Modern Earth Observation systems provide remote sensing data at different temporal and spatial resolutions. Among all the available spatial mission, today the Sentinel-2 program supplies high temporal (every five days) and high spatial resolution (HSR) (10 m) images that can be useful to monitor land cover dynamics. On the other hand, very HSR (VHSR) imagery is still essential to figure out land cover mapping characterized by fine spatial patterns. Understanding how to jointly leverage these complementary sources in an efficient way when dealing with land cover mapping is a current challenge in remote sensing. With the aim of providing land cover mapping through the fusion of multitemporal HSR and VHSR satellite images, we propose a suitable end-to-end deep learning framework, namely $M^3text{Fusion}$, which is able to simultaneously leverage the temporal knowledge contained in time series data as well as the fine spatial information available in VHSR images. Experiments carried out on the Reunion Island study area confirm the quality of our proposal considering both quantitative and qualitative aspects.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Destriping of Multispectral Remote Sensing Image Using Low-Rank Tensor
    • Authors: Yong Chen;Ting-Zhu Huang;Xi-Le Zhao;
      Pages: 4950 - 4967
      Abstract: Multispectral image (MSI) destriping is a challenging topic and has been attracting much research attention in remote sensing area due to its importance in improving the image qualities and subsequent applications. The existing destriping methods mainly focus on matrix-based modeling representation, which fails to fully discover the correlation of the stripe component in both spatial dimensions. In this paper, we propose a novel low-rank tensor decomposition framework based MSI destriping method by decomposing the striped image into the image component and stripe component. Specifically, for the image component, we use the anisotropic spatial unidirectional total variation (TV) and spectral TV regularization to enhance the piecewise smoothness in both spatial and spectral domains. Moreover, for the stripe component, we adopt tensor Tucker decomposition and $ell _{2,1}$-norm regularization to model the spatial correlation and group sparsity characteristic among all bands, respectively. An efficient algorithm using the augmented Lagrange multiplier method is designed to solve the proposed optimization model. Experiments under various cases of simulated data and real-world data demonstrate the effectiveness of the proposed model over the existing single-band and MSI destriping methods in terms of the qualitative and quantitative.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Urban Traffic Density Estimation Based on Ultrahigh-Resolution UAV Video
           and Deep Neural Network
    • Authors: Jiasong Zhu;Ke Sun;Sen Jia;Qingquan Li;Xianxu Hou;Weidong Lin;Bozhi Liu;Guoping Qiu;
      Pages: 4968 - 4981
      Abstract: This paper presents an advanced urban traffic density estimation solution using the latest deep learning techniques to intelligently process ultrahigh-resolution traffic videos taken from an unmanned aerial vehicle (UAV). We first capture nearly an hour-long ultrahigh-resolution traffic video at five busy road intersections of a modern megacity by flying a UAV during the rush hours. We then randomly sampled over 17 K 512×512 pixel image patches from the video frames and manually annotated over 64 K vehicles to form a dataset for this paper, which will also be made available to the research community for research purposes. Our innovative urban traffics analysis solution consists of an advanced deep neural network (DNN) based vehicle detection and localization, type (car, bus, and truck) recognition, tracking, and vehicle counting over time. We will present extensive experimental results to demonstrate the effectiveness of our solution. We will show that our enhanced single shot multibox detector (Enhanced-SSD) outperforms other DNN-based techniques and that deep learning techniques are more effective than traditional computer vision techniques in traffic video analysis. We will also show that ultrahigh-resolution video provides more information that enables more accurate vehicle detection and recognition than lower resolution contents. This paper not only demonstrates the advantages of using the latest technological advancements (ultrahigh-resolution video and UAV), but also provides an advanced DNN-based solution for exploiting these technological advancements for urban traffic density estimation.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Remote Sensing Image Fusion Using Hierarchical Multimodal Probabilistic
           Latent Semantic Analysis
    • Authors: Ruben Fernandez-Beltran;Juan M. Haut;Mercedes E. Paoletti;Javier Plaza;Antonio Plaza;Filiberto Pla;
      Pages: 4982 - 4993
      Abstract: The generative semantic nature of probabilistic topic models has recently shown encouraging results within the remote sensing image fusion field when conducting land cover categorization. However, standard topic models have not yet been adapted to the inherent complexity of remotely sensed data, which eventually may limit their resulting performance. In this scenario, this paper presents a new topic-based image fusion framework, specially designed to fuse synthetic aperture radar (SAR) and multispectral imaging (MSI) data for unsupervised land cover categorization tasks. Specifically, we initially propose a hierarchical multi-modal probabilistic latent semantic analysis (HMpLSA) model that takes advantage of two different vocabulary modalities, as well as two different levels of topics, in order to effectively uncover intersensor semantic patterns. Then, we define an SAR and MSI data fusion framework based on HMpLSA in order to perform unsupervised land cover categorization. Our experiments, conducted using three different SAR and MSI data sets, reveal that the proposed approach is able to provide competitive advantages with respect to standard clustering methods and topic models, as well as several multimodal topic model variants available in the literature.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Band Dependent Spatial Details Injection Based on Collaborative
           Representation for Pansharpening
    • Authors: Maryam Imani;
      Pages: 4994 - 5004
      Abstract: This paper proposes an improved version of the generalized band dependent spatial detail pansharpening method. The proposed method called collaborative representation based band dependent spatial detail (CR-BDSD) benefits the advantages of collaborative representation (CR) to increase the difference between the panchromatic image and the approximation image. Therefore, the highlighted detail image is provided. Then, by adding it to the upsampled multispectral image, the pansharpened image is generated. The use of local spectral-spatial information and also removing noise and redundant spatial features are other benefits of CR in the pansharpening product. According to the experimental results, the CR-BDSD method provides superior fusion results in terms of both quantative and qualitative measures.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Hyperspectral Image Classification With Global–Local Discriminant
           Analysis and Spatial–Spectral Context
    • Authors: Shan Zeng;Zhiyong Wang;Chongjun Gao;Zhen Kang;Dagan Feng;
      Pages: 5005 - 5018
      Abstract: Hyperspectral images (HSIs) obtained from remote sensing contain abundant information of ground objects, and precise analysis of landcover depends on effective and efficient classification of HSIs into homogeneous ground regions. While many advanced algorithms have been developed for HSI classification, it is a challenge for an algorithm to achieve a good balance between its effectiveness and efficiency due to the high dimensionality of HSIs and insufficient labeled training samples. By taking both the rich spectral features and the spatially homogeneous property of land cover distributions, in this paper, we propose a simple and efficient yet effective method for HSI classification. First, features are extracted by using a weighted spatial–spectral and global–local discriminant analysis algorithm, which is proposed to reduce the feature dimension. Then, combining the discriminant information of neighboring pixels, we propose a spatial collaboration nearest neighbor (SC-NN) classifier to make reliable class judgment for the central one. In the SC-NN classifier, the spatially homogeneous property of landcover distribution of HSIs is utilized to effectively reduce the probability of misclassification when only a small number of training samples are available. To further address the issue of a small number of training samples, we adopt an incremental learning strategy by adding the samples with high classification confidence to the training set. Experimental results on four public datasets show that our proposed method outperforms several state-of-the-art methods with high classification accuracy.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image
    • Authors: Vanika Singhal;Angshul Majumdar;
      Pages: 5019 - 5028
      Abstract: In recent studies in hyperspectral imaging, biometrics, and energy analytics, the framework of deep dictionary learning has shown promise. Deep dictionary learning outperforms other traditional deep learning tools when training data are limited; therefore, hyperspectral imaging is one such example that benefits from this framework. Most of the prior studies were based on the unsupervised formulation; and in all cases, the training algorithm was greedy and hence suboptimal. This is the first work that shows how to learn the deep dictionary learning problem in a joint fashion. Moreover, we propose a new discriminative penalty to the said framework. The third contribution of this work is showing how to incorporate stochastic regularization techniques into the deep dictionary learning framework. Experimental results on hyperspectral image classification shows that the proposed technique excels over all state-of-the-art deep and shallow (traditional) learning based methods published in recent times.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Hyperspectral Anomaly Detection Using Collaborative Representation With
           Outlier Removal
    • Authors: Hongjun Su;Zhaoyue Wu;Qian Du;Peijun Du;
      Pages: 5029 - 5038
      Abstract: Recently, collaborative representation detector (CRD) has been popularly used for hyperspectral anomaly detection. For the original CRD, the least squares solution becomes more unstable when more classes, i.e., samples for anomaly detection are involved, and the detection error is likely to happen if the test pixel is an anomalous pixel and several samples from background are similar anomalous. In this paper, we propose a hyperspectral anomaly detection method that uses CRD with principal component analysis (PCA) for removing outlier (PCAroCRD). According to the different background modeling methods, global and local versions are proposed. In the proposed algorithm, the spatial-domain PCA is adopted to extract main pixel information of global/local background that will be used as samples for collaborative representation, and simultaneously the information of abnormal pixels in global/local background can be removed. Fewer useful samples can also keep the detection result stable. Experimental results indicate that the PCAroCRD outperforms the original CRD, kernel version of CRD, advanced CRD (CRDBORAD), morphology-based CRD, Global Reed–Xiaoli (RX) algorithm, and the Local RX.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Robust Infrared Small Target Detection Using Multiscale Gray and Variance
           Difference Measures
    • Authors: Jinyan Gao;Yulan Guo;Zaiping Lin;Wei An;Jonathan Li;
      Pages: 5039 - 5052
      Abstract: As a long-standing problem, infrared small target detection is challenging due to the dimness of targets and the complexity of background. Considering the limitation of traditional approaches, we propose an accurate and robust method for infrared small target detection using multiscale gray and variance difference measures. A multiscale adaptive gray difference measure is first used to enhance small targets and improve detection accuracy. Then, a multiscale variance difference measure is proposed to alleviate the impact of background fluctuation and improve the robustness of our method. By integrating these two approaches, targets can be extracted accurately using a threshold-adaptive segmentation. Extensive experiments have been conducted on datasets with various scenes. Results have demonstrated the effectiveness and outperformance of our method as compared to the state-of-the-art methods.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Qualifying the LIDAR-Derived Intensity Image as an Infrared Band in
           NDWI-Based Shoreline Extraction
    • Authors: Abdullah Harun Incekara;Dursun Zafer Seker;Bulent Bayram;
      Pages: 5053 - 5062
      Abstract: Obtaining the shoreline of a water body and spatial changes on it provide valuable information regarding the fact that freshwater resources constitute a small fraction of available water resources in the world. Nowadays, various types of image are used to extract shoreline details with the contribution of near infrared response (NIR) band. In this study, the potential utility of light-detection-and-ranging LIDAR-derived intensity image (LDII) as an infrared band in shoreline extraction was investigated. Study area was Kestel Dam operated in Izmir province of Turkey. Orthophoto, multispectral Pléiades image (PI), and LDII were processed and evaluated to obtain the shoreline of the dam lake. Mean-shift segmentation was applied on the LDII as smoothing to maintain the edge details while eliminating noise. Noise-free LDII was then added to red, green and blue (RGB) bands of PI instead of NIR band to obtain layer stacked image. Two shorelines were extracted from these two imageries by means of rule-based object-oriented classification. Implemented rules were directly based on threshold values of normalized difference water indexes derived from imageries. Areal-based change detection analysis was carried out with reference to the occupancy rates at the minimum and maximum operating volumes of the dam lake. Also, change detection analysis based on minimum distance differences between extracted and digitized shorelines was performed to examine the subpixel values. Both analyses proved that LDII created from point cloud produced by a beam of 1064 nm can be used as an infrared band in object-based shoreline extraction and may provide better distinction between water and nonwater objects.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Feasibility of Wind Direction Observation Using Low-Altitude Global
           Navigation Satellite System-Reflectometry
    • Authors: Feng Wang;Dongkai Yang;Lei Yang;
      Pages: 5063 - 5075
      Abstract: A study investigating the feasibility of retrieving wind direction using low-altitude backward geometry of Global Navigation Satellite System-Reflectometry (GNSS-R) is implemented in this paper. This paper first focuses on analyzing the influence of wind direction on the roughness of sea surface and scattering strength. The results show that backward scattered GNSS signals obviously change over wind direction despite of the weaker power level than the forward signals. Then, the power link of backward scattered GNSS signal and the visible number of the satellites composing the bistatic backward observation geometry with the receiver are analyzed. Backward scattered GNSS signals are lower about $10text{--}20$ dB than forward ones; hence, a higher gain left-hand circularly polarization antenna should be used to receive them. In the same antenna view, theoretically the backward scattered signals from about three satellites could be received. Finally, a retrieving algorithm of wind direction based on matching theory is proposed. The retrieving results using simulated data show that, first, multibeam observation (at least three-beam observation) should be utilized to remove the uncertainty of retrieving wind direction, second, the accuracy of wind speed and the signal-to-noise ratio (SNR) of the delay waveform importantly impact on the retrieving performance of wind direction, therefore, it is needed to improve the measuring accuracy of wind speed and the SNR. In one word, all results mentioned above give the guide information to observe wind direction using low-altitude GNSS-R.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Experimental Results About Traffic Flow Detection by Using GPS Reflected
    • Authors: Chaoqun Gao;Dongkai Yang;Xuebao Hong;Yao Xu;Bo Wang;Yunlong Zhu;
      Pages: 5076 - 5087
      Abstract: Traffic flow detection using global positioning system (GPS) reflected signals is presented in this paper for the first time, which is a new application in this field. The phase difference information of the reflected signal, which is the output of the phase-locked loop in the tracking process, has been extracted to determine the traffic flow density. In order to verify the reliability of the technology, the inversion model of traffic flow density based on the phase difference information has been established; an experiment has been conducted in a suburban area of Beijing, which is designed to provide auxiliary validation. A metal box is placed in the coverage area of a left-handed circular polarization antenna at two time-periods, i.e., 20–30 and 40–55 s; and a traffic flow experiment in an urban area of Beijing has been carried out. Besides that, a camera is employed to record the traffic flow during the data acquisition time-period. According to the experimental results, the conclusions that can be obtained are that after the time synchronization, the two time-periods of placing the metal box can be clearly observed from the phase difference information of the GPS reflected signal and that by comparing with the real-time traffic flow, the calculation result retrieved from GPS reflected signals is closer to the real situation, which proves the feasibility of traffic flow detection using the global navigation satellite system reflectometry technique.
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
  • Become a published author in 4 to 6 weeks
    • Pages: 5088 - 5088
      PubDate: Dec. 2018
      Issue No: Vol. 11, No. 12 (2018)
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-