Automatic detection of safety helmet with improved YoloV3

Shiqian Li; Ning Ji; Jun Wu; Xiawei Zhang; Lvyi Sun; Minzhe Wu

doi:10.1117/12.2645445

30 August 2022 Automatic detection of safety helmet with improved YoloV3

Shiqian Li, Ning Ji, Jun Wu, Xiawei Zhang, Lvyi Sun, Minzhe Wu

Author Affiliations +

Proceedings Volume 12309, International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2022); 123092I (2022) https://doi.org/10.1117/12.2645445
Event: International Conference on Advanced Manufacturing Technology and Manufacturing System (ICAMTMS 2022), 2022, Shijiazhuang, China

Abstract

Wearing safety helmets is important for the safety of power operators, and using computer vision technology to automatically identify whether operators wear safety helmets can improve the efficiency of safety management. However, due to complex background, illumination condition, this task is non-trivial. We propose in this a method based on YoloV3 network which can effectively solves the problem. We added bi-directional adaptive feature fusion module which is able to better exploit the discriminative power of the low-level features and high-level features. Experimental results have demonstrated the effectiveness of the proposed method.

Citation Download Citation

Shiqian Li, Ning Ji, Jun Wu, Xiawei Zhang, Lvyi Sun, and Minzhe Wu "Automatic detection of safety helmet with improved YoloV3", Proc. SPIE 12309, International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2022), 123092I (30 August 2022); https://doi.org/10.1117/12.2645445

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