A Hierarchical Anti-occlusion Target Tracking Algorithm Based On Particle Filter And Corner Matching

Video target tracking plays an important role in the traffic video monitoring field by providing real-time location information of tracked target. Although it has been investigated intensively, there are still many challenges, such as occlusions, appearance changes, nonrigid motions, background clutter, etc.. Among many challenges in tracking problem, occlusion is one of the most critical issues since it is not straightforward to generalize and model occlusions. Occlusion, especially serious and total occlusion, may result in the deterioration of location accuracy, or even failing to track. Therefore, tracking target robustly and precisely under occlusion is still a challenging problem in this field.This thesis studied around the continuously and precisely target tracking under different occlusion status, as well as reliable occlusion judgment scheme. Main contributions are summarized as follows:1. A hierarchical anti-occlusion tracking algorithm based on Dual Mode Particle Filter (DMPF) and Oriented FAST and Rotated BRIEF (ORB) is proposed to improve the location accuracy under different occlusion conditions in video target tracking. In the first layer, DMPF is used to track target and preliminarily locate its position under various occlusion status. By using corner matching in the second layer, the target is precisely located according to ORB similarity and corner coordinate, thus a more accurate position of target is obtained. A modularized occlusion judgment scheme is also presented to switch tracking mode timely and accurately in DMPF and a Quantified Matrix based on Weighted RGB color space (WQM) is introduced for both color feature creation and corner detection to save operation time. Simulation results show that the proposed algorithm could provide high tracking accuracy in a real-time manner for different occlusion status.2. Proposed an occlusion judgment scheme with joint parameters for target tracking method based on particle filter. In traffic surveillance system, it is still a challenging issue to track an occluded vehicle continuously and accurately, especially under total occlusion situations. Occlusion judgment is critical in occluded target tracking. A corner matching method is utilized to improve the accuracy of target position and velocity estimation due to structure information, thus obtain a more accurate weight value which can reflect the real target’s status. By analyzing the internal relation between the weight value and the particles distribution region based on resample function of particle filter, a new parameter with good performance is proposed to improve the occlusion detection efficiency. Simulation results show that the proposed occlusion judgment scheme improves the performance of the PF-based tracking algorithm by detecting occlusion happening or fading robustly and timely.