Vehicle and pedestrian anti-collision warning system and method based on visual perception

Abstract

The invention discloses a visual perception car front-view vehicle and pedestrian anti-collision warning system and method, which reads the video acquired by the car front-view camera frame by frame, and uses the training cascade classifier to realize the detection of the video in the video frame Vehicles and pedestrians are identified, and at the same time combined with line detection, the recognition results are filtered to remove non-vehicle and non-pedestrian parts, and the deep DBN network is used to complete the judgment of the vehicle and pedestrian information in front of the vehicle. After confirming the position of the vehicle in front and pedestrians, convert the image coordinates into vehicle body coordinates, so as to obtain the relative distance and relative angle between the vehicle in front, the vehicle in front and the pedestrian in front, calculate the safe time distance, and then use the Kalman filter to predict If the position of vehicles and pedestrians is less than the safe time distance, an alarm will be issued. The invention can realize more effective and accurate identification of vehicles and pedestrians, so as to perform anti-collision warning more accurately.

Description

technical field [0001] The invention relates to the technical field of image processing, and in particular to a visual perception vehicle and pedestrian anti-collision warning system and method. Background technique [0002] It is particularly important for a car to recognize cars and pedestrians in its front-sight area in a complex traffic environment. Through the recognition of forward-looking vehicles and pedestrians, it can effectively make up for the lack of the driver's sensory ability, thereby reducing traffic accidents. Therefore, the recognition of forward-looking vehicles and pedestrians when the car is driving has important theoretical and practical significance. [0003] With the advancement of science and technology, vehicle and pedestrian recognition technology has also been developed, but in the actual implementation process, as the scene and shape change, the recognition effect is not satisfactory, and various recognition algorithms only judge and recognize ...

AI Technical Summary

Problems solved by technology

[0003] With the advancement of science and technology, vehicle and pedestrian recognition technology has also been developed, but in the actual implementation process, as the scene and shape change, the recognition effect is not satisfactory, and various recognition algorithms only judge and recognize based on image features , thus limiting the use of various algorithms

Images