Affiliation:
1. State Key Laboratory of Automotive Simulation and Control (ASCL), Changchun 130025, China
2. College of Transportation, Shandong University of Science and Technology, Qingdao 266590, China
Abstract
The issues of the degradation of the visual sensor’s image quality in foggy weather and the loss of information after defogging have brought great challenges to obstacle detection during autonomous driving. Therefore, this paper proposes a method for detecting driving obstacles in foggy weather. The driving obstacle detection in foggy weather was realized by combining the GCANet defogging algorithm with the detection algorithm-based edge and convolution feature fusion training, with a full consideration of the reasonable matching between the defogging algorithm and the detection algorithm on the basis of the characteristics of obvious target edge features after GCANet defogging. Based on the YOLOv5 network, the obstacle detection model is trained using clear day images and corresponding edge feature images to realize the fusion of edge features and convolution features, and to detect driving obstacles in a foggy traffic environment. Compared with the conventional training method, the method improves the mAP by 12% and recall by 9%. In contrast to conventional detection methods, this method can better identify the image edge information after defogging, which significantly enhances detection accuracy while ensuring time efficiency. This is of great practical significance for improving the safe perception of driving obstacles under adverse weather conditions, ensuring the safety of autonomous driving.
Funder
foundation of State Key Laboratory of Automotive Simulation and Control
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference35 articles.
1. Liu, Z., He, Y., Wang, C., and Song, R. (2020). Analysis of the influence of foggy weather environment on the detection effect of machine vision obstacles. Sensors, 20.
2. An advanced contrast enhancement using partially overlapped sub-block histogram equalization;Kim;IEEE Trans. Circuits Syst. Video Technol.,2001
3. Adaptive image contrast enhancement using generalizations of histogram equalization;Stark;IEEE Trans. Image Process.,2000
4. Wen, H., Dai, F., and Wang, D. (2020, January 18–20). A survey of image dehazing algorithm based on retinex theory. Proceedings of the 2020 5th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), Okinawa, Japan.
5. Single image haze removal using dark channel prior;He;IEEE Trans. Pattern Anal. Mach. Intell.,2010
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献