Front vehicle detection method based on monocular vision

Abstract

The invention belongs to the technical field of intelligent transportation, and relates to a front vehicle detection method based on monocular vision, which comprises the steps of: acquiring a vehicle front road condition original image, capturing a subimage, carrying out histogram equalization on the subimage, extracting a vehicle front road surface average gray threshold; obtaining a gray threshold by adopting an improved OTSU method; calculating a binarization threshold; estimating a binarization result, segmenting and reinforcing a target according to an estimation result; filtering; obtaining a key position line expressing a bottommost line in a vehicle bottom shadow, carrying out line fusion on the key position line, then extracting target information of an image to be used as a target result of a current frame; and matching the target result of the current frame with a target result of the last frame and information of a tracking target result, and carrying out classifying decision on the target result of the current frame according to a matching result, and determining a final detection result of a front vehicle of the current frame. The front vehicle detection method has the characteristics of good instantaneity, high detection accuracy rate and good robustness.

Description

technical field [0001] The invention belongs to the field of image processing, and specifically relates to a detection method capable of real-time identification of vehicles driving in front of a car in the scene of a highway or expressway, which is mainly applicable to an intelligent vehicle auxiliary driving system in the field of intelligent transportation, and belongs to the active safety technology of automobiles field. Background technique [0002] Statistical analysis of traffic accidents shows that rear-end collisions account for 30%-40% of traffic accidents, and property losses and casualties caused by rear-end collisions account for 60% of the total losses. The main danger to the driver is the vehicle in front of the road. According to the results of a study in the United States, as long as the driver's reaction time is increased by 0.555 seconds, 60% of intersection car collision accidents and 30% of car rear-end collision accidents can be reduced. Another study...

AI Technical Summary

Problems solved by technology

This method has been proven to be effective, but its shortcomings are also obvious

First of all, due to the diversity of car models, the shape features and aspect ratio information vary widely, and it is difficult to build a vehicle model that takes into account all models; second, due to the viewing angle, the outline of the vehicle will be distorted, and some features of the vehicle will be distorted. is destroyed, the calculation of the model matching algorithm is often very large, which greatly reduces the real-time performance of the detection method, so there are still many limitations in practical applications

Images