Paf-tracker: a novel pre-frame auxiliary and fusion visual tracker

Wei Liang, Derui Ding, Hui Yu

Abstract: Siamese-like trackers expose considerable shortcomings in the case of brief occlusion due mainly to the inadequate consideration of the correlation information between adjacent frames. The precision of predicted bounding boxes still has much room for further improvement because the traditional regression loss cannot effectively handle the case where one box contains the other. To address these shortages, the paper proposes a novel pre-frame auxiliary and fusion tracking framework. Within this framework, a retained variable is first introduced to avoid some additional twin branches while retaining the previously obtained deep features of the search frames. Based on such a variable, a pre-frame auxiliary module is constructed to establish the relationship between encoding features and the retained pre-frame information. Furthermore, a decoding fusion module is designed to fuse the generated similarity relationship between the template patch and the search patch and the one between the search frame and previous frames. Moreover, the Efficient IoU (EIoU) loss is employed to increase the precision of predicted bounding boxes by adding three penalty terms for the differences in the center point, length, and width of the two bounding boxes. Finally, the superiority over state-of-the-art methods is verified by numerous tests on visual tracking benchmarks.