Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Xuemin Xing;Li Huang;Zhongming He;Tengfei Zhang;Yikai Zhu;
Pages: 232 - 241 Abstract: Objectives: The Airport South Expressway in China is built in a soft soil area, which may induce great hidden danger to airport traffic safety operations. Technology or Method: A new method to improve multitemporal interferometric synthetic aperture radar (MT-InSAR) technology, based on a novel time-series InSAR deformation model and an improved parameter estimation algorithm, is proposed for soft soil expressways monitoring. The functional relationship between the deformation and the creep parameters (viscosity and elastic modulus) based on the Maxwell model in 1-D linear rheology replaces the traditional InSAR linear model, and the creep physical parameters can be solved simultaneously in the solution process. The least squares method with inequality constraints (LSICs) is induced to solve the unknown parameters. In total, 19 TerraSAR-X radar satellite images covering the South Expressway were utilized to validate the proposed method. The creep parameters for each pixel along the expressways and the time-series deformation sequences from January 2012 to July 2014 were obtained. Results: As the results showed, the maximum settlement along the expressway was up to 125 mm, and the accuracy verification results showed that the modeling accuracy was 1.6 mm, with an improvement of 36.0% compared to the traditional linear model; the internal accuracy of the deformation results was ±1.9 mm, accounting for 1.5% of the maximum deformation. Clinical or Biological Impact: Our method can provide data support and a reference for long-term health monitoring and early warning of infrastructure and traffic operation management in poor soil regions. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Jianlai Chen;Xiaoqing Xu;Junchao Zhang;Gang Xu;Yucan Zhu;Buge Liang;Degui Yang;
Pages: 242 - 249 Abstract: Aiming at the problem of target detection for multiple source information fusion, in this article, a decision-level fusion algorithm for visible and SAR images is proposed. First, using the Faster-RCNN network detects visible and SAR images to retain the detection results, respectively. Second, the semantic segmentation of visible images based on U-Net is realized. Finally, based on the detection results of single source and semantic segmentation results of land and sea, a fusion strategy based on decision level is proposed to achieve accurate target detection under multisource information. Through experimental verification, the detection performance of the proposed algorithm is an advantage over that of single-source image detection. The detection accuracy is 2.87% and 4.73% higher, and the recall rate is 3.02% and 0.19% higher than that of visible and SAR images separately. Compared with other target detection algorithms based on traditional image fusion, the proposed method has fewer false detections and missed detections. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Ivan V. Saetchnikov;Victor V. Skakun;Elina A. Tcherniavskaia;
Pages: 250 - 256 Abstract: Computer vision-based systems seem highly perspective for semantic analysis of the dynamical objects. However, considering dynamical object recognition and tracking from the unmanned aerial vehicle (UAV) the task to design a robust model for data association is highly challenging due to additional issues, e.g., image degradation, nonfixed object camera distance and shooting focus, and real-time issues. Thus, we propose an accurate deep neural network-based dynamical object recognition and robust multiobject tracking technique based on bidirectional LSTM with the optimized motion and appearance gates as a multiobject tracking backbone, supported by an advanced single-shot detector network improved with residual prediction model and implemented a DenseNet network as well as a YOLOv4eff network as feature extraction. The technique has been trained on VisDrone 2022 and UAVDT datasets with the side-shoot dynamical objects at a height of up to 50 m. The performance analysis on the test stage performed on seven metrics demonstrate that the proposed technique surpasses, by accuracy and robustness ability, other state-of-the-art techniques based on two cumulative MOTA and MOTP, as well as MT and IDsw. In particular, we have dramatically decreased the number of IDsw which implies a better capability to handle several occlusions, which is a desirable property in real-time multiple object tracking. We have pointed out the sensitivity of the tracking performance of our technique on the number of utilizing different sequence lengths and have defined an optimum. Finally, the applicability and reliability of the proposed technique for onboard UAV computer-based systems have been discussed. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Fei Liu;Shuang Li;Yaoquan Jing;Jia Liu;Han Hu;Quan Gan;Tingting Zhao;Yuling Ding;Xing Pan;Shuo Deng;Qing Zhu;
Pages: 257 - 266 Abstract: A high-precision digital elevation model (DEM) is useful for disaster investigation and evaluation in cloudy, rainy, and complex mountainous areas. However, clouds and rain make the optical images and laser point-cloud data acquisition difficult, while noise prohibits obtaining accurate surface information. Additionally, the complex elevation difference in mountainous areas increases the data processing difficulty, such as phase unwrapping (PU) and filtering. To overcome these problems, first, we introduce a new airborne multibaseline Ka-interferometric synthetic aperture radar (InSAR) system developed by the Beijing Institute of Radio Measurement. The system affords high resolution and small volume, is lightweight, has a good top-view angle, and is flexible. Thus, it reduces the flight platform’s dependence and improves the aircraft’s adaptability and universality. Moreover, a multibaseline PU method of a two-stage programming approach (TSPA) is selected to overcome the influence of severe noise and the phase continuity assumption limitation. Additionally, an adaptive filtering method for InSAR point clouds considering coherence and optimal bending energy is proposed. This method’s validity is verified using stereo satellite images, ground observation point precision checks, and geomorphic texture analysis against existing DEM results. The experimental results demonstrate that the proposed scheme has a good filtering effect on noise, vegetation, residential building areas, and bridges, significantly reducing manual intervention. Moreover, the results highlight that our method is well integrated with stereo images and has more texture details than conventional stereo mapping results, with a mean square error of elevation of 1.938 m. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Xiangwei Bu;Zongcheng Liu;
Pages: 267 - 273 Abstract: Most of the existing prescribed performance control (PPC) methodologies are developed in the continuous-time domain. In this article, a discrete-time PPC (DPPC) strategy is investigated for an air-vehicle’s seeker stabilized platform. Unlike the existing DPPC whose convergence time drifts with the sampling time, the proposed controller is able to guarantee tracking errors with fixed convergence time via devising a new discrete-time performance function, which improves the engineering practicability. Moreover, a new disturbance observer is constructed to estimate both system uncertainties and external disturbances. In addition, the backstepping procedure is used to design a DPPC approach for the sake of stabilizing transformed errors. This endows tracking errors with desired fixed-time prescribed performance. Finally, the efficiency of design is verified via compared simulations. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Meijie Liu;Ping Luo;Changhua Hu;Rui Guo;Xiaoxiang Hu;
Pages: 274 - 282 Abstract: A T–S fuzzy-based $Hinfty $ sliding mode observer (SMO)-based fault detection scheme is conducted to realize the actuator fault detection issue, including stuck fault detection and partial loss of effectiveness (PLOE) fault detection in our work. First, a T–S fuzzy attitude control model with an uncertainty term is derived from the original nonlinear hypersonic flight vehicle (HSV) model by combining local linear models at four equilibrium points. Second, the actuator fault model is introduced to further establish a T–S fuzzy HSV model with actuator faults. Then, a T–S fuzzy-based $Hinfty $ SMO is designed for fault detection based on matrix coordinate transformation. Finally, the SMO observer simulation is conducted to the T–S fuzzy HSV model for single-input single-style actuator fault detection. The simulation results show that stuck faults can be timely and accurately detected at the fault time and the state change amplitude is approximately in direct-ratio relation with the amplitude of stuck faults, which is caused by the implicit relationship between the states and the flap. Unfortunately, the detection of PLOE faults encounters some difficulties for acceptable reasons and needs further attention and investigation. PubDate:
TUE, 22 AUG 2023 14:17:42 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Ravi Teja Nallapu;Yinan Xu;Tristan Schuler;Jekan Thangavelautham;
Pages: 283 - 304 Abstract: The next frontier in space exploration involves visiting some of the 2 million small bodies scattered throughout the solar system. However, these missions are expected to be challenging due to the surface irregularities of these bodies and the very low gravity, which makes steps like getting into orbit very complex. For these reasons, reconnaissance is crucial for small-body exploration before taking on ambitious orbital, surface, and sample-return missions. Our previous work developed IDEAS, an automated design software for small-body reconnaissance mission development using spacecraft swarms. A critical challenge to furthering such designs is the lack of hardware demonstration platforms for interplanetary spacecraft operations. In this article, we present multiagent photogrammetry of small bodies (MAPS), a hardware platform to demonstrate critical reconnaissance operations of multispacecraft missions identified by the IDEAS framework. MAPS uses unmanned air vehicles (UAVs) as the autonomous agents that perform reconnaissance operations. The UAVs use their visual feed to generate a 3-D surface map of a small-body mockup, which is encountered along their flight path. In this article, we examine the various design elements of a small-body surface reconstruction mission inside the MAPS testbed. These elements are used for designing reference trajectories of the participating UAVs, which is enforced using a tracking feedback control law. We then formulate the small-body mapping problem as a mixed-integer nonlinear programming problem, which is handled by the Automated Swarm Designer module of the IDEAS framework. The solutions are implemented inside the MAPS, and shape models generated from the UAV feeds are compared. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Xinsheng He;Ming Deng;Bingjie Chai;Wenlong Dong;Zhaohui Zhang;Chunmin Wu;Yuqi Wang;
Pages: 305 - 310 Abstract: The synthetic aperture passive localization system generally compensates for the second-order phase term of the received signal with the Taylor series of the range history and then uses the focusing result of the compensated signal to obtain the position of the emitter. However, the existence of a higher-order residual phase causes the mismatch of reference function, leading to the bias of localization results. To solve the problem, this article proposes a slant range expansion method based on an orthogonal basis. The optimal expansion of the range history is obtained by constructing a set of orthogonal bases in the space composed of quadratic polynomials so that the residual phase after integration is minimized. The proposed method can effectively mitigate the localization bias caused by the model approximation of a synthetic aperture localization system. Simulations and Monte Carlo tests show that the proposed method outperforms the traditional synthetic aperture localization method. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Pakezhamu Nuradili;Ji Zhou;Xiangbing Zhou;Jin Ma;Ziwei Wang;Lingxuan Meng;Wenbin Tang;Yizhen Meng;
Pages: 311 - 319 Abstract: The availability of high-resolution imagery resources for semantic segmentation research has expanded significantly due to the rapid development of remote-sensing technology utilizing unmanned aerial vehicles (UAVs). These images provide researchers with a more accurate view of the region of interest and allow for more detailed analysis and interpretation of the images. However, semantic segmentation based on UAV remote-sensing imagery still faces new challenges in deriving ground objects. In contrast to the commonly used multispectral (MS) imagery, thermal infrared (TIR) imagery can record the emission of ground objects, making the temperature characteristics of TIR imagery and the color characteristics of MS imagery complementary. These two approaches can be used synergistically to provide more comprehensive image information. On this basis, we propose a strategy for semantic segmentation of UAV images by utilizing both TIR and MS image features. The approach combines principal component analysis (PCA) transformation with a deep learning semantic segmentation network, namely, Deeplv3. The effectiveness of the proposed strategy is evaluated by comparing it with both traditional supervised classification algorithms and deep learning algorithms. According to the results, the proposed strategy exhibits greater robustness, achieving a mean pixel accuracy (MPA) of 92.8% and a mean intersection over union (MIOU) of 73.5%. These results outperform several classical deep learning semantic segmentation algorithms that were also evaluated. The proposed strategy would be beneficial to promote the development of semantic segmentation technology for UAV remote-sensing images. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:
Xindi Wang;Hao Liu;Qing Gao;
Pages: 320 - 328 Abstract: In this article, the optimal real-time decision making and near-optimal path planning problem for multiagent systems subject to bounded state, collision avoidance, external disturbance, and partially unknown nonlinear dynamics of the multiagent system in complex games, is addressed and applied to the unmanned aerial vehicle. A mean-field decision-making model based on the neighbor information is established to transform the decision-making problem into a Bellman equation solving problem. A data-driven dynamic programming algorithm is proposed to solve the Bellman equation and generate an optimal strategy using the data from the historical database and expert knowledge. The near-optimal path planning problem is formulated with an optimal coordination control problem, and an online integral reinforcement learning algorithm is proposed to iteratively interact with the environment to obtain a near-optimal path. Simulation results are provided to verify the effectiveness of the proposed methods. PubDate:
TUE, 22 AUG 2023 14:18:43 -04 Issue No:Vol. 4, No. 3 (2023)
Hybrid journal (It can contain Open Access articles)
