A COMPUTER VISION-BASED STUDY ON ROAD SAFETY USING YOLO AND INFRARED THERMAL INFORMATION

Abstract

The purpose of this paper is to explore the monitoring method of road condition environment and driving safety based on YOLO and thermal property information. By integrating visual and thermal imaging data, it can make up for the deficiency of a single sensing method, improve the detection accuracy and robustness of various targets in the road scene, and provide all-round and multi-level protection for driving safety. The research content covers the front information recognition, vehicle side safety recognition and driver status recognition based on YOLOv8 algorithm. The effectiveness and superiority of the thermo physical information compensation method in different scenarios are verified by experiments. The safe driving detection method provides theoretical basis and technical support