Vehicle identification method and device, electronic device and storage medium

Abstract

The embodiment of the invention discloses a vehicle identification method and device, electronic equipment and a storage medium. Among them, the method includes: acquiring the image in front of the vehicle; extracting the edge contour features of the vehicle from the image, and identifying the position of the vehicle in the same direction closest to the front of the vehicle; extracting highlighted connected areas from the image, and obtaining highlights whose features are obviously independent of each other Connected area; count the proportion of red pixels in the halo area outside the highlighted connected area in the image, obtain the highlighted connected area belonging to the tail light area, and mark the corresponding tail light position; compare the position of the tail light with the nearest vehicle in the same direction in front of the vehicle The position is matched to obtain the taillight area of ​​the other vehicles in the same direction except the nearest vehicle in the same direction in front of the vehicle; according to the geometric characteristics of the taillight area of ​​the vehicle in the same direction in front of the vehicle, identify the other vehicles in the same direction in front of the vehicle except the nearest vehicle in the same direction the location of the vehicle. The embodiments of the present invention can improve the accuracy of vehicle recognition at night.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a vehicle recognition method and device, electronic equipment and a storage medium. Background technique [0002] In recent years, with the increasing popularity of automobiles, people have paid more and more attention to the safety performance of automobiles. An effective measure to improve automobile safety performance is to use automobile safety driving assistance systems, in which computer vision-based vehicle recognition Technology is an important part of the car's safety assisted driving system. [0003] At present, for automobile safety driving assistance systems, the vehicle recognition technology based on monocular vision in the daytime environment has been relatively perfect, while the vehicle recognition technology based on monocular vision in the night environment mostly adopts a feature-based method, based on The characteristic vehicle recognition method m...

AI Technical Summary

Problems solved by technology

[0003] At present, for automobile safety driving assistance systems, the vehicle recognition technology based on monocular vision in the daytime environment has been relatively perfect, while the vehicle recognition technology based on monocular vision in the night environment mostly adopts a feature-based method, based on The characteristic vehicle recognition method mainly extracts the taillights of the vehicle and uses taillight matching to identify vehicles. During the vehicle recognition process, it is often interfered by ground reflections, roadside marker reflections, and vehicle body reflections, and many non-taillight areas are extracted, resulting in matching. Errors that affect the accuracy of vehicle recognition

Images