Implementation of multiple object tracking for tracking pedestrians

Jinning Liang; Xinming Yu; Yingying Zou

doi:10.1117/12.2653361

27 September 2022 Implementation of multiple object tracking for tracking pedestrians

Jinning Liang, Xinming Yu, Yingying Zou

Proceedings Volume 12346, 2nd International Conference on Information Technology and Intelligent Control (CITIC 2022); 123460C (2022) https://doi.org/10.1117/12.2653361
Event: 2nd International Conference on Information Technology and Intelligent Control (CITIC 2022), 2022, Kunming, China

Abstract

Multiple object tracking is complex and this essay will analyse a method to build flexible tracking system, contributing to people detection. The system can perform automatic detection using Kalman filter’s prediction and update function, and bboxOverlapRatio calculates the cost of matching detection and track. Then, referring to the cost calculated, Munkres’ version of the Hungarian algorithm matches detection and track. Also, the method uses customized non-maximum suppression and approach to discover and eliminate false alarm tracks. The simulation tracks people from a moving car, and finally, under common circumstances, the method can help detect people successfully and rapidly. Although, there are still some problems existing, like that it can’t recognize the static people and the distance between pedestrians and car will influence the result. The method still provides new ideas of detection and is useful to solve the problems of shelter among objects from one another, the effect of motion, including vagueness and capture.

Citation Download Citation

Jinning Liang, Xinming Yu, and Yingying Zou "Implementation of multiple object tracking for tracking pedestrians", Proc. SPIE 12346, 2nd International Conference on Information Technology and Intelligent Control (CITIC 2022), 123460C (27 September 2022); https://doi.org/10.1117/12.2653361

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available