Siamese Network Object Tracking Algorithm Combined with Attention Mechanism

Abstract

Object tracking is one of the important research topics in the direction of computer vision. And occlusion, deformation and scale change are the most challenging issues in the realm of tracking. In an effort to address the issue that the Siamese network-based object tracking algorithm's resilience and success rate are both low and weak in complicated circumstances such as similar object interference and object occlusion, a Siamese network Object tracking algorithm combined with attention mechanism based on the existing Siamese network algorithm is proposed. Firstly, in order to extract the features of the template picture and the sample picture, the modified AlexNet convolutional neural network ^[1] is utilized as the feature extraction network. Secondly, in order to increase the model's precision and increase tracking's rate of success, the module for the attention mechanism, which consists of the channel attention mechanism and the spatial attention mechanism, is introduced. The channel attention mechanism can focus on the information useful for tracking the Object, suppress unimportant background information, and the spatial attention mechanism is capable of picking up on the object's abundant spatial information. Experiments show that the proposed Siamese network target tracking algorithm combined with attention mechanism achieves contestable results on the OTB100 test dataset, and the enhanced method outperforms the original approach in terms of performance.