Abstract
Video synthetic aperture radar (ViSAR) has been found very useful for the surveillance of ground moving targets. The target energy can be utilized for ground moving target tracking, while the dynamic shadows of moving targets enable an alternative tracking approach. However, neither of these two approaches can stand alone to provide reliable target tracking. The smeared shadow and energy both degrade the tracking performance when the target is maneuvering. A moving target tracking framework based on the joint kernelized correlation filter (JKCF) has been developed. Based on the feature training of JKCF, the target is tracked by combining its shadow in the sequential SAR imagery and the corresponding energy in the range-Doppler (RD) spectra. Aiming at the problems of tracking drift and collapse, interactive processing is adopted to enhance the target positioning and feature update based on the confidence assessment. By cooperating with the initialization and feature update strategy, the tracking success rate and precision can be improved significantly.
Highlights
V IDEO synthetic aperture radar (ViSAR) presents dynamic imagery of illuminated scenes at a high frame rate and has been found very useful in the surveillance of ground maneuvering targets [1]–[8]
The moving target tracking framework based on the joint kernelized correlation filter (JKCF) has been developed for ViSAR
The initialization is proposed by adopting the inter-frame data association and track matching
Summary
V IDEO synthetic aperture radar (ViSAR) presents dynamic imagery of illuminated scenes at a high frame rate and has been found very useful in the surveillance of ground maneuvering targets [1]–[8]. Moving target energy is often position-shifted and defocused in SAR imagery due to the mismatch with the imaging algorithms designed for the stationary scene, which difficulties the tracking. Many techniques, such as time-frequency analysis methods [9], [10] and along-track interferometry (ATI) [11], [12], can be used to locate and track targets, these methods largely depend on the signal to noise ratio (SNR) of radar echo. The dynamic shadows between adjacent frames provide the real track of the moving target and are independent of the target radar cross-section (RCS). A few approaches have been proposed for shadow detection and tracking in ViSAR
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
