SiamCAM: A Real-Time Siamese Network for Object Tracking with Compensating Attention Mechanism

Abstract

The Siamese-based object tracking algorithm regards tracking as a similarity matching problem. It determines the object location according to the response value of the object template to the search template. When there is similar object interference in complex scenes, it is easy to cause tracking drift. We propose a real-time Siamese network object tracking algorithm combined with a compensating attention mechanism to solve this problem. Firstly, the attention mechanism is introduced in the feature extraction module of the template branch and search branch of the Siamese network to improve the feature representation of the network to the object. The attention mechanism of the search branch enhances the feature representation of both the target and the similar backgrounds simultaneously. Therefore, based on the above two-branch attention, we propose a compensated attention model, which introduces the attention selected by the template branch into the search branch, and improves the discriminative ability of the search branch to the object by using the feature attention weighting of the template branch to the object. Experimental results on three popular benchmarks, including OTB2015, VOT2018, and LaSOT, show that the accuracy and robustness of the algorithm in this paper are adequate. It improved occlusion cases, similar object interference, and high-speed motion. The processing speed on GPU reaches 47 fps, which can achieve real-time object tracking.

An anti-occlusion optimization algorithm for multiple pedestrian tracking

“…They used an adaptive threshold to determine whether to use the Siamese network for re-detection, effectively addressing occlusion and background clutter issues in object tracking and achieving state-of-the-art performance. Similar object interference in object tracking often leads to tracking drift, Huang et al [ 18 ] introduced a compensated attention model, which incorporated attention mechanisms in the feature extraction modules of both the template branch and search branch of the Siamese network. This model enhances the feature representation of both the target and the similar backgrounds simultaneously and improves the discriminative ability of the search branch towards the object.…”