A slant vehicle detection and tracking system and method based on machine vision

Abstract

The invention provides a slant vehicle detection and tracking system and method based on machine vision. The system comprises a CCD camera, a USB data transmission port and a computer terminal. The method comprises the following steps of: in vehicle detection phase, firstly, image preprocessing is performed, region-of-interest extraction and improved lane line detection are combined, an inclined vehicle detection area is divided; an adaptive threshold value and a maximum between-class variance method are adopted; a shadow area is extracted, further a shadow line is extracted at the bottom of the vehicle, left and right boundaries of the vehicle are determined in combination with Sobel vertical edge extraction to obtain a suspected rectangular frame of a vehicle target, then features in the rectangular frame are extracted, dimensionality reduction is performed on the features by adopting kernel principal component analysis, and detection confirmation is performed by utilizing an Adaboost cascade classifier; in the vehicle tracking stage, mean shift and Kalman filtering are combined, a vehicle detection result is used as an initial tracking target, and the tracking target is screened by using rectangular frame coincidence. The system and the method can realize real-time vehicle detection and tracking, and have high accuracy.

Description

technical field [0001] The invention relates to the fields of machine vision and automobile active safety, and specifically designs a machine vision-based oblique vehicle detection and tracking method. Background technique [0002] Mixed flow of people and vehicles and traffic congestion are typical characteristics of my country's traffic conditions. In the environment of mixed flow of people and vehicles, drivers often ignore the peripheral vision area and blind spot obstacles, which is an important cause of accidents. Therefore, it is particularly important to detect and track oblique vehicles in the peripheral field of view for the intelligent design of vehicles in China's traffic conditions. Target detection and tracking based on machine vision is a widely used sensor, and its advantages lie in the continuous development of machine vision technology and the low cost of cameras. However, the driving environment is complex and changeable, and the delay problem of image p...

AI Technical Summary

Problems solved by technology

[0003] At present, for forward vehicle detection and tracking, the patent publication number [CN 104866823A] first uses the shadow feature to obtain the hypothetical vehicle, and then uses the co-occurrence matrix method described by the texture to verify the hypothetical vehicle and improve the detection accuracy, but the detection process is affected by the light It is very large, and the detection accuracy is low; the patent publication number [CN 107704833A] uses two different features, and performs two classifier detections, which improves the detection accuracy of the forward vehicle, but also produces a large Due to the amount of calculation, the real-time performance cannot meet the requirements

Images