A pedestrian re-identification method, device, electronic equipment, and computer-readable storage medium

Abstract

The invention discloses a pedestrian re-identification method, device, electronic equipment, and computer-readable storage medium, wherein the method includes: acquiring an image of a pedestrian to be detected; Global feature information; extract multiple intermediate feature information of the pedestrian image to be detected through multiple convolutional layers of the convolutional neural network, and combine the multiple intermediate feature information as local feature information; The global feature information and the local feature information are used as classification features of the pedestrian image to be detected, and a classification result of the pedestrian image to be detected is determined according to the classification feature. By implementing the embodiments of the present invention, the multi-level and multi-scale features of pedestrian images are fused with each other, and the global features and local features of pedestrian images are combined to obtain a more discriminative feature and improve the accuracy of pedestrian re-identification.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a pedestrian re-identification method, device electronic equipment, and a computer-readable storage medium. Background technique [0002] In recent years, as people pay more and more attention to the public safety of the society, video surveillance systems have become popular. Public places such as airports, railway stations, campuses and office buildings are in urgent need of monitoring to protect security. In the face of massive surveillance video data, a large amount of manpower needs to be invested in the monitoring and retrieval of video information. This method is not only inefficient, but also causes additional waste of resources. If computer vision analysis technology and automated monitoring can be used to analyze video information, the construction of a "safe city" will definitely be greatly accelerated. [0003] With the rapid development of deep lea...

AI Technical Summary

Problems solved by technology

Different from face recognition, pedestrian re-identification faces more problems, and the problems to be solved are more difficult, so the challenges faced are also greater, such as: the angle of the pedestrian image, the clarity of the image, and the inability to obtain the frontal image. Discriminative feature declassification, so the current recognition accuracy of pedestrian re-identification based on convolutional neural network is low

Images