Sensor fusion-based obstacle detection method for hazy environment

Yan Li; Wei Dong; Jindai Qu; Tianyu Gong; Yan Ji; Miao Gu; Tianqiang Zhang; Yong Liu; Guangsheng Han

doi:10.1117/12.2678832

15 May 2023 Sensor fusion-based obstacle detection method for hazy environment

Yan Li, Wei Dong, Jindai Qu, Tianyu Gong, Yan Ji, Miao Gu, Tianqiang Zhang, Yong Liu, Guangsheng Han

Author Affiliations +

Proceedings Volume 12699, Third International Conference on Sensors and Information Technology (ICSI 2023); 1269902 (2023) https://doi.org/10.1117/12.2678832
Event: International Conference on Sensors and Information Technology (ICSI 2023), 2023, Xiamen, China

Abstract

Based on camera and millimeter wave radar data fusion, an intelligent vehicle obstacle detection method suitable for hazy environment is proposed. Firstly, by taking the effectiveness of obstacle detection after image dehazing as the evaluation standard, a series of typical dehazing networks are compared and the best one was selected for image preprocessing. An obstacle detection model based on YOLOv5s depth network was established; Then, the camera data and radar data are fused in time and space, and the sensor data is associated based on the global nearest neighbor data association algorithm. Finally, the effectiveness of the proposed method is verified by open source data sets and real vehicle experiments.

Citation Download Citation

Yan Li, Wei Dong, Jindai Qu, Tianyu Gong, Yan Ji, Miao Gu, Tianqiang Zhang, Yong Liu, and Guangsheng Han "Sensor fusion-based obstacle detection method for hazy environment", Proc. SPIE 12699, Third International Conference on Sensors and Information Technology (ICSI 2023), 1269902 (15 May 2023); https://doi.org/10.1117/12.2678832

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