Abstract
Aiming to address dense small object tracking, we propose an image-to-trajectory framework including tracking and detection, where Track-Oriented Multiple Hypothesis Tracking(TOMHT) is revised for tracking. Unlike common cases of multi-object tracking, merged detections and the greater number of objects make dense small object tracking a more challenging problem. Firstly, we handle frequent merged detections through the aspects of detection and hypothesis selection. To tackle merged detection, we revise Local Contrast Method(LCM) and propose a multi-appearance variant, which exploits tree-like topological information and realizes one threshold for one object. Meanwhile, one-to-many constraint is employed via the proposed extended 0-1 programming, which enables hypothesis selection to handle track exclusions caused by merged detections. Secondly, to alleviate the high complexity caused by dense objects, we consider batch optimization and more rigorous and precise pruning technologies. Specifically, we propose autocorrelation based motion score test and two-stage hypotheses pruning. Experimental results are presented to verify the strength of our methods, which indicates speed and performance advantages of our tracker.
Highlights
We approach the problem of complexity from two aspects: (1)batch optimization: we find that in Multi-Hypothesis Tracking (MHT) a considerable part of the computation is spent on compatibility processing, which accounts for the compatibility between hypotheses and is performed at every time step
Our tracking method achieves better performance with near 20% decreasing in OSPA-T compared with the second method, i.e greedy randomized adaptive search procedure (GRASP)-MHT
We utilize two-stage hypothesis pruning and modified motion score for hypothesis management and generation, which could improve the quality of hypothesis
Summary
Results from some studies [12, 13] show that the precision of JPDA may be inferior to MHT when handling an excessive amount of objects. We approach the problem of complexity from two aspects: (1)batch optimization: we find that in MHT a considerable part of the computation is spent on compatibility processing, which accounts for the compatibility between hypotheses and is performed at every time step Such frequent processing may not be totally necessary, because the compatibility relations won’t change for every time step. We make the following contributions: (1)We employ an one-to-many association based constraint for dense small object tracking, and implement it by the proposed extended 0-1 programming; (2)We introduce a two-stage pruning technology and a short-term motion score for hypothesis generation and management, which help to reduce the hypothesis quantity and improve its quality. It utilizes a topological tree structure to count for the relationship among local thresholds for different objects. (4)Owing to the efforts of pruning hypotheses and reducing complexity, the implementation of our tracker has an advantage in speed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
