Automatic detection method of scrap material of scrap automobile based on improved YOLO V4-tiny

Wen Zhou; Feng Chen; Meng Chen; Ruoyu Zuo

doi:10.1117/12.2674569

23 May 2023 Automatic detection method of scrap material of scrap automobile based on improved YOLO V4-tiny

Wen Zhou, Feng Chen, Meng Chen, Ruoyu Zuo

Proceedings Volume 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022); 126044E (2023) https://doi.org/10.1117/12.2674569
Event: 2nd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 2022, Guangzhou, China

Abstract

Aiming at the problem of low visual recognition accuracy of waste materials (copper, brass, aluminum and plastic) in the scrap automobile industry, a novel YOLO V4-tiny algorithm was proposed by adding Mosaic data enhancement and improving the Efficient Channel Attention (ECA) mechanism to the original feature extraction network, which strengthened the learning ability of the target detection algorithm and made the network focus on effective features. Suppress interference features, enhance the model's attention to useful information, improve the detection ability of the algorithm. The improved network model was trained, verified and tested on the self-made data set. The results show that the algorithm can effectively improve the identification accuracy of scrap materials of scrapped vehicles, and finally improve the mAP (mean Average Precision) of the existing YOLOV4-tiny algorithm from 91.33% to 95.17%.

Citation Download Citation

Wen Zhou, Feng Chen, Meng Chen, and Ruoyu Zuo "Automatic detection method of scrap material of scrap automobile based on improved YOLO V4-tiny", Proc. SPIE 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 126044E (23 May 2023); https://doi.org/10.1117/12.2674569

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