Graph Attention Networks and Track Management for Multiple Object Tracking
-
Published:2023-09-28
Issue:19
Volume:12
Page:4079
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Zhang Yajuan1, Liang Yongquan1, Elazab Ahmed2ORCID, Wang Zhihui1ORCID, Wang Changmiao3
Affiliation:
1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266510, China 2. School of Biomedical Engineering, Shenzhen University, Shenzhen 518060, China 3. Shenzhen Research Institute of Big Data, Shenzhen 518172, China
Abstract
Multiple object tracking (MOT) constitutes a critical research area within the field of computer vision. The creation of robust and efficient systems, which can approximate the mechanisms of human vision, is essential to enhance the efficacy of multiple object-tracking techniques. However, obstacles such as repetitive target appearances and frequent occlusions cause considerable inaccuracies or omissions in detection. Following the updating of these inaccurate observations into the tracklet, the effectiveness of the tracking model, employing appearance features, declines significantly. This paper introduces a novel method of multiple object tracking, employing graph attention networks and track management (GATM). Utilizing a graph attention network, an attention mechanism is employed to capture the relationships of nodes within the graph as well as node-to-node correlations across graphs. This mechanism allows selective focus on the features of advantageous nodes and enhances discriminability between node features, subsequently improving the performance and robustness of multiple object tracking. Simultaneously, we categorize distinct tracklet states and introduce an efficient track management method, which employs varying processing techniques for tracklets in diverse states. This method can manage occluded tracks in crowded scenes and improves tracking accuracy. Experiments conducted on three challenging public datasets (MOT16, MOT17, and MOT20) demonstrate that our method could deliver competitive performance.
Funder
GuangDong Basic and Applied Basic Research Foundation Elite Plan of Shandong University of Science and Technology Innovation Teams of Youth Innovation in Science and Technology of High Education Institutions of Shandong province
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference49 articles.
1. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada. 2. Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., and Hu, H. (2023, January 17–24). Detrs with hybrid matching. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada. 3. Effective multiple pedestrian tracking system in video surveillance with monocular stationary camera;Wang;Expert Syst. Appl.,2021 4. Cao, J., Pang, J., Weng, X., Khirodkar, R., and Kitani, K. (2023, January 17–24). Observation-centric sort: Rethinking sort for robust multi-object tracking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada. 5. Chen, J., Wang, F., Li, C., Zhang, Y., Ai, Y., and Zhang, W. (2021). Online multiple object tracking using a novel discriminative module for autonomous driving. Electronics, 10.
|
|