Effective Occlusion Handling for Fast Correlation Filter-based Trackers ( Vol-5,Issue-6,November - December 2020 )
Author: Zheng Zhang, T.T. Wong
Keyword: Correlation filter, Log Polar, Quality measurement, Visual object tracking.
Abstract: Correlation filter-based trackers heavily suffer from the problem of multiple peaks in their response maps incurred by occlusions. Moreover, the whole tracking pipeline may break down due to the uncertainties brought by shifting among peaks, which will further lead to the degraded correlation filter model. To alleviate the drift problem caused by occlusions, we propose a novel scheme to choose the specific filter model according to different scenarios. Specifically, an effective measurement function is designed to evaluate the quality of filter response. A sophisticated strategy is employed to judge whether occlusions occur, and then decide how to update the filter models. In addition, we take advantage of both log-polar method and pyramid-like approach to estimate the best scale of the target. We evaluate our proposed approach on VOT2018 challenge and OTB100 dataset, whose experimental result shows that the proposed tracker achieves the promising performance compared against the state-of-the-art trackers.
Article Info: Received: 12 Nov 2020; Received in revised form: 15 Dec 2020; Accepted: 22 Dec 2020; Available online: 29 Dec 2020
Cite this Article: Show All (MLA | APA | Chicago | Harvard | IEEE | Bibtex)
|Total View: 159||Downloads: 0||Page No: 24-31|