Improved YOLO-based algorithm for urban traffic object detection

Liguo Zhang; Xu Yan; Mei Jin

doi:10.1117/12.3034992

7 August 2024 Improved YOLO-based algorithm for urban traffic object detection

Liguo Zhang, Xu Yan, Mei Jin

Proceedings Volume 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024); 1322432 (2024) https://doi.org/10.1117/12.3034992
Event: 4th International Conference on Internet of Things and Smart City, 2024, Hangzhou, China

Abstract

Urban traffic vehicle detection is a key component of smart city transportation systems, aimed at improving traffic management and safety through modern technologies and information methods. In response to the characteristics and challenges of vehicle detection in smart cities, this paper proposes a vehicle detection method based on drone aerial images, employing an object detection algorithm based on YOLOv4, namely the Adaptive Cropping YOLO algorithm. Through training and optimization on a large-scale dataset, this method can accurately detect and identify different types of urban vehicles. Experimental results show that this algorithm can effectively detect large-sized image targets that traditional YOLO algorithms may miss, providing reliable technical support for traffic safety monitoring and management.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Liguo Zhang, Xu Yan, and Mei Jin "Improved YOLO-based algorithm for urban traffic object detection", Proc. SPIE 13224, 4th International Conference on Internet of Things and Smart City (IoTSC 2024), 1322432 (7 August 2024); https://doi.org/10.1117/12.3034992

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