A New Framework for Tracking Aerial Moving Targets using AFFINE - SIFT Algorithm

Moving target tracking is a process in which an object is tracked and its location is determined in each frame. The goal of this process is facilitating the subsequent process in order to analyze the behavior or detect moving objects. In this paper, a new approach has been proposed for aerial moving targets detection and tracking based on feature matching algorithms. By this way, we propose spectral density for target detection and ASIFT feature matching algorithm for tracking. The challenge is selecting features that are robust against the changes of brightness, noise, rotation, scaling and viewing angle. To solve this problem, key points and their correspondence on the patterns extracted from consecutive frames, are calculated by the ASIFT algorithm. Also, to reduce false matches in consecutive frames, the RANSAC algorithm is used. In addition to strengthening the proposed algorithm against the scale change of target, the object history scale in the 10 previous frames is used. The proposed algorithm was performed on an AIRCRAFT TRACKING standard database. Experimental results demonstrate the robustness and accuracy of our proposed technique.