Research on YOLOv4 object detection algorithm based on lightweight

Bo Liu; Yanwu Li

doi:10.1117/12.2684979

19 October 2023 Research on YOLOv4 object detection algorithm based on lightweight

Bo Liu, Yanwu Li

Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 1270941 (2023) https://doi.org/10.1117/12.2684979
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China

Abstract

Aiming at the problem that the existing target detection algorithm has too many network parameters to be applied to embedded or mobile devices, a lightweight YOLOv4 target detection algorithm is proposed. Firstly, the lightweight feature extraction network GhostNet and the deep separable convolution are introduced to reduce the computational load of the model; secondly, the Efficient Channel Attention (ECA) module is introduced into the feature fusion network to strengthen the learning of target features; then use the idea of deep separable convolution to improve the ASPP module and replace the SPP module. The Pascal VOC dataset is used to evaluate the optimization algorithm. The results show that the introduction of GhostNet network and deep separable convolution can reduce the network parameters by 75%, and the mAP value of the algorithm is reduced by 7.73%. After the introduction of the ECA module and the improved ASPP module, the network computing capacity has only slightly improved, and the mAP value has increased by 2.12% to 65.92%.

Citation Download Citation

Bo Liu and Yanwu Li "Research on YOLOv4 object detection algorithm based on lightweight", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 1270941 (19 October 2023); https://doi.org/10.1117/12.2684979

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