Particle filter re-detection for visual tracking via correlation filters
This work addresses a specific problem in visual tracking for applications like surveillance or robotics, but it is incremental as it builds on existing correlation filter methods.
The paper tackles inaccurate object localization in correlation filter-based visual tracking by proposing a particle filter re-detection approach, which improves performance on OTB2013 and OTB2015 datasets compared to state-of-the-art methods.
Most of the correlation filter based tracking algorithms can achieve good performance and maintain fast computational speed. However, in some complicated tracking scenes, there is a fatal defect that causes the object to be located inaccurately. In order to address this problem, we propose a particle filter redetection based tracking approach for accurate object localization. During the tracking process, the kernelized correlation filter (KCF) based tracker locates the object by relying on the maximum response value of the response map; when the response map becomes ambiguous, the KCF tracking result becomes unreliable. Our method can provide more candidates by particle resampling to detect the object accordingly. Additionally, we give a new object scale evaluation mechanism, which merely considers the differences between the maximum response values in consecutive frames. Extensive experiments on OTB2013 and OTB2015 datasets demonstrate that the proposed tracker performs favorably in relation to the state-of-the-art methods.