An Efficient Method for Tracking Failure Detection Using Parallel Correlation Filtering and Siamese Network

In recent years, object tracking based on Siamese network has attracted the attention by taking advantage of both speed and accuracy. However, when similar object interference, severe occlusion and other factors cause temporary tracking failure, a restricted search window makes Siamese network difficult to retrieve the object again, and results in unrecoverable tracking failures. In this paper, a general and efficient two-way verification tracking failure detection method using parallel correlation filtering and Siamese network is proposed, which can detect the tracking failure and retrieve the object again. Firstly, we construct parallel Siamese network and correlation filter tracking network, and get tracking results respectively. Secondly, we make a preliminary judgment on the reliability of the tracking results based on the overlap ratio of the tracking results. Finally, based on two-way verification, which tracker failed to track is finally determined, and the search window of Siamese network is optimized to retrieve the object again. We comparisons with state-of-the art trackers on benchmark datasets: OTB100, VOT2016, VOT2018, VOT2019 and NFS. The results show that the method we proposed can detect the tracking failure and retrieve the object again, thus improving the accuracy of object tracking.