Visual Multi-Object Tracking with Re-Identification and Occlusion Handling using Labeled Random Finite Sets
This work provides an incremental improvement for researchers and practitioners in computer vision by enhancing tracking accuracy and efficiency in scenarios with occlusions and reappearances.
The paper tackles the problem of visual multi-object tracking by addressing object reappearance and occlusion, achieving a method with linear complexity in the number of detections and improved occlusion handling through a fuzzy detection model.
This paper proposes an online visual multi-object tracking (MOT) algorithm that resolves object appearance-reappearance and occlusion. Our solution is based on the labeled random finite set (LRFS) filtering approach, which in principle, addresses disappearance, appearance, reappearance, and occlusion via a single Bayesian recursion. However, in practice, existing numerical approximations cause reappearing objects to be initialized as new tracks, especially after long periods of being undetected. In occlusion handling, the filter's efficacy is dictated by trade-offs between the sophistication of the occlusion model and computational demand. Our contribution is a novel modeling method that exploits object features to address reappearing objects whilst maintaining a linear complexity in the number of detections. Moreover, to improve the filter's occlusion handling, we propose a fuzzy detection model that takes into consideration the overlapping areas between tracks and their sizes. We also develop a fast version of the filter to further reduce the computational time. The source code is publicly available at https://github.com/linh-gist/mv-glmb-ab.