Structural Pixel-Wise Target Attention For Robust Object Tracking

Some Siamese-based trackers use temporal context prior as structural constraint to suppress background distractors. However, due to the lack of contour recognition, it is difficult to obtain a better performance. In order to address this issue, we propose a structural pixel-wise target attention strategy for robust object tracking with memory model. Firstly, a pixel-wise target attention model is constructed for evaluating the probability that the pixel belongs to the target, which can effectively discriminate the target boundary so as to highlight the target area. Meanwhile, structural information is used to solve pixel-wise distractors, which is combined with complementary pixel-wise label constraints to obtain a structural pixel-wise target attention model. This attention mechanism can improve the confidence of the final response map and achieve more reliable target location. Secondly, a memory model is learned using the highly reliable memory pattern for providing high-quality training samples for updating pixel-wise target attention model. Benefiting from this method, our method realizes the pixel-wise target attention model to adapt to the variation of the target while preventing the background noise, thus improving the discriminability of the model. Finally, the structural pixel-wise target attention mechanism and memory model are integrated into the Siamese-based tracking framework, which shows better merit for robust object tracking. Extensive experiments on multiple tracking benchmarks show that our approach achieves excellent performance in various challenging target tracking tasks. (C) 2021 Published by Elsevier Inc.