Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking
This work addresses the problem of robust video object tracking for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles video object tracking by integrating a deep object detector with a particle filter tracker under a regularization framework, resulting in improved robustness to occlusion, pose, and scale changes. It reports an 11% and 9% improvement in success rate on VOT2016 and VOT2018 datasets, respectively.
We introduce a tracking-by-detection method that integrates a deep object detector with a particle filter tracker under the regularization framework where the tracked object is represented by a sparse dictionary. A novel observation model which establishes consensus between the detector and tracker is formulated that enables us to update the dictionary with the guidance of the deep detector. This yields an efficient representation of the object appearance through the video sequence hence improves robustness to occlusion and pose changes. Moreover we propose a new state vector consisting of translation, rotation, scaling and shearing parameters that allows tracking the deformed object bounding boxes hence significantly increases robustness to scale changes. Numerical results reported on challenging VOT2016 and VOT2018 benchmarking data sets demonstrate that the introduced tracker, L1DPF-M, achieves comparable robustness on both data sets while it outperforms state-of-the-art trackers on both data sets where the improvement achieved in success rate at IoU-th=0.5 is 11% and 9%, respectively.