Shadow-Background-Noise 3D Spatial Decomposition Using Sparse Low-Rank Gaussian Properties for Video-SAR Moving Target Shadow Enhancement

• Published in: IEEE geoscience and remote sensing letters Vol. 19; pp. 1 - 5
• Main Authors: Xu, Xiaowo, Zhang, Xiaoling, Zhang, Tianwen, Yang, Zhenyu, Shi, Jun, Zhan, Xu
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Attenuation; Background noise; Convex functions; Decomposition; Detection; Detection-tracking; Image enhancement; moving target; Moving targets; Qualitative analysis; Radar imaging; Radar tracking; SAR (radar); shadow enhancement; Shadows; Sparse matrices; Synthetic aperture radar; Target tracking; Three dimensional models; Three-dimensional displays; Tracking; video synthetic aperture radar (video-SAR)
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2022.3223514

Moving target shadows among video synthetic aperture radar (Video-SAR) images are always interfered with by low scattering backgrounds and cluttered noises, causing poor detection-tracking accuracy. Thus, a shadow-background-noise 3D spatial decomposition (SBN-3D-SD) model is proposed to enhance shadows for higher detection-tracking accuracy. It leverages the sparse property of shadows, the low-rank property of backgrounds, and the Gaussian property of noises to perform 3-D spatial three-decomposition. It separates shadows from backgrounds and noises by the alternating direction method of multipliers (ADMM). Results on the Sandia National Laboratories (SNL) data verify its effectiveness. It boosts the shadow saliency from the qualitative and quantitative evaluation. It boosts the shadow detection accuracy of Faster R-CNN, RetinaNet, and YOLOv3. It also boosts the shadow tracking accuracy of TransTrack, FairMOT, and ByteTrack.