Education, Science, Technology, Innovation and Life
Open Access
Sign In

Tracking algorithm based on spatial progressive matching strategy and optimized correlation

Download as PDF

DOI: 10.23977/acss.2024.080210 | Downloads: 8 | Views: 92

Author(s)

Yunhua Jia 1, Siyue Cha 1, Chengjiang Zhou 1

Affiliation(s)

1 Information Institute, Yunnan Normal University, 768 Juxian Street, Kunming, China

Corresponding Author

Chengjiang Zhou

ABSTRACT

The task of multi-target tracking is to correctly associate the identity of the same target in the two scene scenes. How to improve the accuracy of target tracking is still full of challenges. In this article, we propose a tracking algorithm based on spatial progressive matching strategy and optimized correlation. In it, we divide the targets in the scene according to the area of the target detection frame in the scene. By Prioritizing matching of target groups with a larger target frame area, and then matching target groups with a smaller target frame area is the spatial progressive matching strategy we propose. We noticed that in certain scenes where the target moves too quickly, the traditional intersection-to-union method becomes limited to some extent. Therefore, we substituted it with a circular intersection-to-union ratio method, which is more effective in accurately associating the targets in those scenes.

KEYWORDS

Target tracking, Computer vision, Correlation optimization

CITE THIS PAPER

Yunhua Jia, Siyue Cha, Chengjiang Zhou, Tracking algorithm based on spatial progressive matching strategy and optimized correlation. Advances in Computer, Signals and Systems (2024) Vol. 8: 63-68. DOI: http://dx.doi.org/10.23977/acss.2024.080210.

REFERENCES

[1] Kuru A. Exploring experience of runners with sports tracking technology [J]. International Journal of Human–Computer Interaction, 2016, 32(11): 847-860. 
[2] Huang Y C, Liao I N, Chen C H, et al. Tracknet: A deep learning network for tracking high-speed and tiny objects in sports applications[C]//2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 2019: 1-8.
[3] Senanayake M, Senthooran I, Barca J C, et al. Search and tracking algorithms for swarms of robots: A survey[J]. Robotics and Autonomous Systems, 2016, 75: 422-434.
[4] Bewley A, Ge Z, Ott L, et al. Simple online and realtime tracking[C]//2016 IEEE international conference on image processing (ICIP). IEEE, 2016: 3464-3468.
[5] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788. 
[6] Terven J, Córdova-Esparza D M, Romero-González J A. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas[J]. Machine Learning and Knowledge Extraction, 2023, 5(4): 1680-1716.

Downloads: 13628
Visits: 260011

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.