Work method of identification and early-warning system based on pedestrians and bicycle riders in front of vehicle

Abstract

The invention discloses a work method of an identification and early-warning system based on pedestrians and bicycle riders in front of a vehicle. An offline training module selects positive and negative samples of the upper half of the body from a video shot by the practical vehicle, an Adboost algorithm is used for training to obtain a cascaded classifier for identifying the upper half of the body, the cascaded classifier is provided for an online detection module, the online detection module uses a CCD camera to collect images, a video collection card is used for conversion, and an improved multi-scale scanning method is used for preprocessed images to obtain a subwindow; and the online detection module selects an identified target frame, and transmits the target frame to a collision early-warning module, and the collision early-warning module uses a monocular visual range-finding geometric model to calculate the horizontal distance X and the vertical distance D between a target and the vehicle, the vertical speed Vy of the target and the vertical collision time TTC; and such information and the speed of the vehicle u are integrated to determine the danger degree of the target, a driver is prompted timely, and accidents can be reduced o protect the pedestrians and bicycle riders.

Description

technical field [0001] The invention belongs to the technical field of automobile active safety, relates to image processing and pedestrian and cyclist safety protection knowledge, and specifically relates to a working method of an early warning system based on the identification and early warning of pedestrians and cyclists in front of a vehicle. Background technique [0002] In a typical mixed traffic system like China, pedestrians, bicycles, electric vehicles, cars, etc. are the main participants in the traffic system. With the increase of car ownership in our country, traffic accidents are also increasing year by year. Pedestrians, bicycles, and electric vehicles are exposed to the outside and have no protective measures, so they are vulnerable to greater injuries in traffic accidents. Therefore, research on mixed The identification and early warning method of pedestrians and cyclists under traffic conditions is conducive to reminding drivers before traffic accidents occ...

AI Technical Summary

Problems solved by technology

[0004] Related patents: Chinese patent CN103279741A discloses a pedestrian warning system based on vehicle-mounted infrared images and its working method, which uses K-means clustering analysis algorithm and template matching to identify pedestrians, and then establishes a warning unit based on pedestrian information and vehicle speed information; This method can only be applied to pedestrians, ignoring the protection of cyclists, and there is less information to construct the early warning unit, which is prone to false and missed reports

Chinese patent CN103204123A discloses a vehicle pedestrian detection and tracking early warning device and its early warning method, which detects and tracks other vehicles and pedestrians other than the vehicle and measures the distance, and performs early warning by calculating the distance from other vehicles and pedestrians; The distance of other vehicles and pedestrians is used as the only indicator for early warning discrimination, and the reliability of the early warning system is poor

Images