Multiple Moving Vehicles Tracking Algorithm with Attention Mechanism and Motion Model
-
Published:2024-01-04
Issue:1
Volume:13
Page:242
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Gao Jiajun1, Han Guangjie12ORCID, Zhu Hongbo3, Liao Lyuchao1ORCID
Affiliation:
1. School of Transportation, Fujian University of Technology, Fuzhou 350118, China 2. Department of Information and Communication System, Hohai University, Changzhou 213022, China 3. School of Information Science and Engineering, Shenyang Ligong University, Shenyang 110159, China
Abstract
With the acceleration of urbanization and the increasing demand for travel, current road traffic is experiencing rapid growth and more complex spatio-temporal logic. Vehicle tracking on roads presents several challenges, including complex scenes with frequent foreground–background transitions, fast and nonlinear vehicle movements, and the presence of numerous unavoidable low-score detection boxes. In this paper, we propose AM-Vehicle-Track, following the proven-effective paradigm of tracking by detection (TBD). At the detection stage, we introduce the lightweight channel block attention mechanism (LCBAM), facilitating the detector to concentrate more on foreground features with limited computational resources. At the tracking stage, we innovatively propose the noise-adaptive extended Kalman filter (NSA-EKF) module to extract vehicles’ motion information while considering the impact of detection confidence on observation noise when dealing with nonlinear motion. Additionally, we borrow the Byte data association method to address unavoidable low-score detection boxes, enabling secondary association to reduce ID switches. We achieve 42.2 MOTA, 51.2 IDF1, and 364 IDs on the test set of VisDrone-MOT with 72 FPS. The experimental results showcase our approach’s highly competitive performance, attaining SOTA tracking performance with a fast speed.
Funder
Fujian Key Lab for Automotive Electronics and Electric Drive, Fujian University of Technology Fujian University of Technology
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference57 articles.
1. Bashar, M., Islam, S., Hussain, K.K., Hasan, M.B., Rahman, A., and Kabir, M.H. (2022). Multiple object tracking in recent times: A literature review. arXiv. 2. Multiple object tracking: A literature review;Luo;Artif. Intell.,2021 3. Simsek, F.E., Cigla, C., and Kayabol, K. (2022, January 23–27). SOMPT22: A Surveillance Oriented Multi-pedestrian Tracking Dataset. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel. 4. Fabbri, M., Brasó, G., Maugeri, G., Cetintas, O., Gasparini, R., Ošep, A., Calderara, S., Leal-Taixé, L., and Cucchiara, R. (2021, January 11–17). Motsynth: How can synthetic data help pedestrian detection and tracking?. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada. 5. Creß, C., Bing, Z., and Knoll, A.C. (2021). Intelligent transportation systems using external infrastructure: A literature survey. arXiv.
|
|