Vehicle detection in dark weather based on YOLO and MSRCR method

Haiyun Hu; Xiangwu Gong

doi:10.1117/12.2644207

9 September 2022 Vehicle detection in dark weather based on YOLO and MSRCR method

Haiyun Hu, Xiangwu Gong

Proceedings Volume 12328, Second International Conference on Optics and Image Processing (ICOIP 2022); 123280Y (2022) https://doi.org/10.1117/12.2644207
Event: Second International Conference on Optics and Image Processing (ICOIP 2022), 2022, Taian, China

Abstract

With the continuous growth of car ownership, intelligent transportation has penetrated into our daily life. As an important part of intelligent transportation, car detection has also been developed rapidly. It plays a vital role on the planning of urban public transportation and brings great convenience for citizens to commute. Due to the extremely complex urban conditions, car detection encounters many difficulties. By analyzing a large amount of vehicle color difference data, it draws the conclusion that illumination is the main factor of affecting detection and recognition. Based on the convolutional neural network framework, this paper focuses on low-light enhancement and car recognition, aiming to realize the task of car recognition in more complex low-light situations. Notably, in those scenarios, the YOLOv4 model with a basic training set can recognize automobiles well.

Citation Download Citation

Haiyun Hu and Xiangwu Gong "Vehicle detection in dark weather based on YOLO and MSRCR method", Proc. SPIE 12328, Second International Conference on Optics and Image Processing (ICOIP 2022), 123280Y (9 September 2022); https://doi.org/10.1117/12.2644207

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