Vol.132, No.3, 2022, pp.909-927, doi:10.32604/cmes.2022.020471
OPEN ACCESS
ARTICLE
Visual Object Tracking via Cascaded RPN Fusion and Coordinate Attention
  • Jianming Zhang1,2,*, Kai Wang1,2, Yaoqi He1,2, Lidan Kuang1,2
1 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China
2 Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha, 410114, China
* Corresponding Author: Jianming Zhang. Email:
(This article belongs to this Special Issue: Enabled and Human-centric Computational Intelligence Solutions for Visual Understanding and Application)
Received 26 November 2021; Accepted 20 January 2022; Issue published 27 June 2022
Abstract
Recently, Siamese-based trackers have achieved excellent performance in object tracking. However, the high speed and deformation of objects in the movement process make tracking difficult. Therefore, we have incorporated cascaded region-proposal-network (RPN) fusion and coordinate attention into Siamese trackers. The proposed network framework consists of three parts: a feature-extraction sub-network, coordinate attention block, and cascaded RPN block.We exploit the coordinate attention block, which can embed location information into channel attention, to establish long-term spatial location dependence while maintaining channel associations. Thus, the features of different layers are enhanced by the coordinate attention block. We then send these features separately into the cascaded RPN for classification and regression. According to the two classification and regression results, the final position of the target is obtained. To verify the effectiveness of the proposed method, we conducted comprehensive experiments on the OTB100, VOT2016, UAV123, and GOT-10k datasets. Compared with other state-of-the-art trackers, the proposed tracker achieved good performance and can run at real-time speed.
Keywords
Object tracking; deep learning; coordinate attention; cascaded RPN
Cite This Article
Zhang, J., Wang, K., He, Y., Kuang, L. (2022). Visual Object Tracking via Cascaded RPN Fusion and Coordinate Attention. CMES-Computer Modeling in Engineering & Sciences, 132(3), 909–927.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.