Design of MSPRN Target Recognition Algorithm for Vehicle Automatic Driving

Abstract

Vehicle automatic driving technology can effectively improve the safety performance of vehicle driving. This research is to meet the needs of vehicle automatic driving, and propose a target recognition algorithm with better performance. According to the existing research, the algorithm is optimized and improved based on the traditional Faster R-CNN algorithm, and a network target recognition algorithm based on Multi Strategy Regional candidate box is proposed to optimize the anchor box. Through the comparative analysis of recognition and recall rate between traditional R-CNN algorithm and MSPRN algorithm, it can be seen that MSPRN algorithm has better algorithm performance and is suitable for target detection and recognition in vehicle automatic driving.