Traffic sign detection based on improved YOLOv5

Mingkui Zhang; Quanyu Wang

doi:10.1117/12.2659125

23 November 2022 Traffic sign detection based on improved YOLOv5

Mingkui Zhang, Quanyu Wang

Proceedings Volume 12454, International Symposium on Robotics, Artificial Intelligence, and Information Engineering (RAIIE 2022); 124540Y (2022) https://doi.org/10.1117/12.2659125
Event: International Symposium on Robotics, Artificial Intelligence, and Information Engineering (RAIIE 2022), 2022, Hohhot, China

Abstract

Aiming at the problems of locating and identifying impediment for minor targets as well as unpromising detection accuracy, a traffic sign detection algorithm based on improved YOLOv5 is propounded in this paper. First, the Addition of the Coordinate Attention Mechanism module behind the backbone network enables the model to effectively capture the relationship between location information and channels, thereby more accurately locates the area of interest. Then a detection layer is introduced into the network structure, and the feature map is continued to be upsampled after the 17th layer of the original algorithm network structure, so that the feature map continues to expand, and a feature map of 160 *160 size is obtained at the 19th layer and the feature map of the second layer of the backbone network is spliced and integrated. This results in a larger feature map for the detection of small targets. Finally, α -CIoU loss is used to replace the original CIoU positioning loss function in the model training stage to obtain higher quality anchor frame. Experiments are performed on the TT100K dataset, compared to the original YOLOv5 algorithm, the proposed algorithm improves accuracy by 3.9%, recall rate by 5.5% and mAP by 4.6% under the premise of less speed reduction, which still meets the requirements of real-time detection.

Citation Download Citation

Mingkui Zhang and Quanyu Wang "Traffic sign detection based on improved YOLOv5", Proc. SPIE 12454, International Symposium on Robotics, Artificial Intelligence, and Information Engineering (RAIIE 2022), 124540Y (23 November 2022); https://doi.org/10.1117/12.2659125

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