Suppressing False Alarm in VideoSAR viaGradient-Weighted Edge Information

Abstract

VideoSAR (Video Synthetic Aperture Radar) technology provides an important mean for real-time and continuous earth observation, whereas the ever-changing scattering characteristics may destroy the accuracy of target motion perception and bring in massive false alarms subsequently. False alarms emerge easily in the edge region for its sharper variations of the scattering characteristics. Utilizing the gradient difference between the target shadow edge and other edge regions in the image, this letter proposes a VideoSAR false alarm reduction method based on gradient-weighted edge information. By considering the reasonable gradient and area of the overlapping edge region between changing region and background, this method could reduce the amount of false alarms ( P f a = 18 . 4 % ) and retain the correct shadow of moving target ( P d = 74 . 8 % ). Experiments on a real footage verify the excellent effect of the proposed method.

Detecting Moving Target on Ground Based on Its Shadow by Using VideoSAR

“…The methods proposed in [24] were used to register the image sequence and suppress speckle noise. The method to reduce the number of false alarms proposed in [21] was applied after fusion.…”

“…The shadow of a moving target appears as a low grayscale area in the SAR image, and its grayscale range is related to the total time for which the shadow of the ground object is detected. The intensity of the shadow region of the moving target can be written as (detailed deduction has been provided in [21]):…”

“…However, shadow detection by using VideoSAR has some inherent defects, especially in the case of a slowly moving target. According to the mechanism of shadow formation in VideoSAR, the main causes of false alarm include temporal variations in scattering, variations in the shadow with changes in the viewing angle, energy displacement and shifting of the target, and SAR speckle noise [21]. A clear and stable shadow is thus challenging to obtain in VideoSAR data.…”

Mobile multimedia computing in cyber-physical surveillance services through UAV-borne Video-SAR: A taxonomy of intelligent data processing for IoMT-enabled radar sensor networks

“…Object detection and tracking 2D/3D Yes Yes Deep learning for moving target (shadow) tracking considering abnormal playback speed (it looks without a general tracking filter) Damini et al [46] 2013 Change detection 3D No No Practical tests have been done Li et al [47] 2019 Object detection 3D Yes No Suppressing false alarm in Video-SAR Ding et al [48] 2020 Object detection 2D Yes Yes Moving target indication using deep learning Huang et al [49] 2021…”

“…8), however some other aspects related to intelligent computing can be found in Refs. [46] and [47]. Similar to other SAR modes, the moving objects in Video-SAR should be detected through their shadows, in other words, automatic target tracking for the radar surveillance is more complicated and needs more attention in future studies.…”