Vehicle detection and tracking method based on monocular vision

Abstract

The invention requests to protect a vehicle detection and tracking method based on monocular vision, and belongs to the field of machine vision. The method comprises the steps that in a vehicle detection stage, a rod driving region is determined by combining interest region extracting, self-adaptive Canny edge detection and lane line detection, then a vehicle bottom shadow is obtained by means of local tonal value statistics and a thresholding method in which a maximum between-class variance method is used twice in an integrated manner, furthermore, a supposed vehicle is proposed, and then the supposed vehicle is verified through a texture description co-occurrence matrix method; and in a vehicle tracking stage, an improved algorithm combining Kalman filtering with Cam shift is adopted to carry out multi-target tracking, then new target judging, whether searching is successful, and whether a vehicle is out of an edge are used as three standards, and if a new target is detected twice, the new target is processed as a new tracking target, and the tracking target is updated continuously. By adopting the method, vehicle detection and multi-target tracking under a dynamic background are realized, and the instantaneity, the accuracy and the reliability are relatively high.

Description

technical field [0001] The invention relates to a method for real-time vehicle detection and tracking in an assisted driving system, belonging to the field of machine vision, in particular to a method for vehicle detection and tracking based on monocular vision. Background technique [0002] When the vehicle is driving on the road, the losses caused by rear-end collision with the vehicle in front or improper avoidance are huge. Using the safety assistance driving system can not only reduce the pressure on the driver, but also give early warning and corresponding measures before the accident occurs , thereby effectively reducing the occurrence of traffic accidents. The vehicle anti-collision warning system in the safety assisted driving system is the most important part of the system. The vehicle anti-collision warning system judges whether there is a vehicle in front by searching the area in front of the road, and locates the vehicle in front if there is a vehicle. The spee...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of poor real-time performance, anti-interference performance and high false detection rate in the vehicle detection process in the prior art, the present invention provides a method to improve the real-time performance, anti-interference performance and reduce false detection rate of vehicle detection. Vehicle detection and tracking method, the technical solution of the present invention is as follows: a vehicle detection and tracking method based on monocular vision, which includes the following steps: in the detection stage of moving vehicles, 101, the road driving area extraction step: specifically, A1 1. Obtain the image information around the car, remove the region of the image part that does not contain road information, and extract the region of interest; A2, use the adaptive canny edge detection method to detect the entire region of interest extracted in step A1 The edge of the image; A3, then use the Hough transform to detect all straight lines in the image area, and vote for each straight line, and get the straight line with the largest number of votes in this area; A4, set the threshold for the angle of the left and right lane lines, and establish In the polar angle constraint area, the positions of the left and right lane lines are delineated in the polar angle constraint area, and the straight line with the largest number of votes in the polar angle constraint area is selected as the lane line, thereby locating the road driving area;

Images