Vehicle pedestrian-avoiding detection method based on video analysis

Abstract

The invention belongs to the field of intelligent transportation, and especially relates to a vehicle pedestrian-avoiding detection method based on video analysis. The method comprises the following steps: (1) sample acquisition: intercepting and acquiring positive and negative samples of vehicles and pedestrians from an actual scene; (2) sample preprocessing: graying the acquired samples, and performing scaling; (3) feature extraction: calculating the image gradient, performing gradient voting, calculating and optimizing gradient voting, normalizing a histogram, and collecting feature vectors; (4) classifier training; (5) quick target detection: detecting all vehicle and pedestrian targets in a calibrated area, and returning the center coordinates of the targets; and (6) making illegality judgment. Through the method, the potential conflict between vehicles and pedestrians at an intersection without traffic signal lights can be detected actively, and drivers can be reminded to avoid pedestrians so as to reduce the occurrence of traffic accidents; and drivers can be urged to develop a civilized and safe driving habit, and thus, the civilization of cities is improved.

Description

technical field [0001] The invention belongs to the field of intelligent transportation, in particular to a video analysis-based vehicle avoidance pedestrian detection method. Background technique [0002] In recent years, with the advancement of my country's urbanization process and the increase of road traffic pressure, the traffic safety situation has become increasingly severe. At urban road intersections, especially at intersections without traffic lights, there has been an obvious conflict between the right of way of vehicles and pedestrians for a long time. The law of our country clearly stipulates that when a motor vehicle is driving on a road without traffic signals, it should give way to pedestrians crossing the road. However, due to the lack of effective supervision and detection means, some motor vehicles still go their own way when passing through intersections without traffic lights, and do not pay attention to avoiding pedestrians, often causing serious accide...

AI Technical Summary

Problems solved by technology

However, due to the lack of effective supervision and detection methods, some motor vehicles still go their own way when passing through intersections without traffic lights, and do not pay attention to avoiding pedestrians, often causing serious accidents inadvertently

Images