Object-Aware Adaptive Convolution Kernel Attention Mechanism in Siamese Network for Visual Tracking

Applied Sciences

Mingyue Zhang¹  Qingdang Li¹  Dongliang Yuan²  Zhen Sun³  Xiaohui Yang⁴ 

[1] Chinesisch-Deutsche Technische Fakultat, Qingdao University of Science and Technology, Qingdao 266061, China;College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, China;College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China;Faculty of Electrical Engineering and Computer Science, University of Kassel, 34001 Kassel, Germany;

关键词: visual object tracking;    convolution kernel attention;    Siamese convolutional neural network;    convolutional neural network;   

DOI  :  10.3390/app12020716

来源: DOAJ

【 摘 要 】

As a classic framework for visual object tracking, the Siamese convolutional neural network has received widespread attention from the research community. This method uses a convolutional neural network to obtain the object features and to match them with the search area features to achieve object tracking. In this work, we observe that the contribution of each convolution kernel in the convolutional neural network for object tracking tasks is different. We propose an object-aware convolution kernel attention mechanism. Based on the characteristics of each object, the convolution kernel features are dynamically weighted to improve the expression ability of object features. The experiments performed using OTB and VOT benchmark datasets show that the performance of the tracking method fused with the convolution kernel attention mechanism is significantly better compared with the original method. Moreover, the attention mechanism can also be integrated with other tracking frameworks as an independent module to improve the performance.

【 授权许可】

Unknown