Linear regression-based pedestrian recognition method

Abstract

The invention provides a linear regression-based pedestrian recognition method. The method comprises the following steps: selecting two types of training image sets; processing the two types of selected training images; modeling for the two types of processed training images; performing multi-scale zooming on an image to be tested; selecting a candidate region through sliding window processing; processing the candidate region; next estimating a least square parameter in the processed data; then calculating a most approximate vector of the estimated numerical value; calculating the distance between an observation vector and the approximate vector; judging the type of the candidate region; filtering off a duplicate detection part by using a non-maximum suppression algorithm; finally outputting a recognition result. According to the method, no complex characteristic extraction and classifier training process is required, a simple structure is realized, and the real-time property of the recognition method is effectively improved.

Description

technical field [0001] The invention relates to a pedestrian recognition method, in particular to a linear regression-based pedestrian recognition method, and belongs to the technical field of intelligent transportation. Background technique [0002] With the increasing popularity of automobiles, road traffic accidents have become an important cause of accidental death and disability, and the development of vehicle-mounted pedestrian detection systems has become an important research topic in the field of automotive active safety. Pedestrian detection is a difficult task from the perspective of machine vision, mainly because the appearance of pedestrians is highly variable, such as people can wear different clothes, carry different objects, have different body shapes, etc. The requirements for real-time and robustness are very strict, and the probability of false alarm and false alarm is very low. [0003] Existing pedestrian detection systems can use different sensors, suc...

AI Technical Summary

Problems solved by technology

The key to these methods is some kind of optimal separable feature representation, and a lot of computing time is spent on the extraction of pedestrian features and the training of classifier models.

Vehicle-mounted pedestrian detection systems have high requirements for real-time performance, and the computational complexity of existing methods is generally high, and the detection time of each frame is difficult to meet the needs of real-vehicle applications

Images