Unsupervised pedestrian re-identification method, device and equipment and readable storage medium

Abstract

The invention provides an unsupervised pedestrian re-identification method, device and equipment and a readable storage medium. The method comprises the following steps: clustering pedestrian image samples, and distributing a false label for each pedestrian image sample based on a clustering result; constructing a category feature memory and a feature memory; obtaining K * P pedestrian image samples according to the false labels; inputting the preprocessed K * P pedestrian image samples into a deep learning model to obtain second pedestrian features; optimizing a deep learning model based on the category feature memory, the feature memory and the second pedestrian feature; and when the number of optimization times reaches a preset number of times, obtaining pedestrian features corresponding to the target pedestrian image by using a finally obtained deep learning model, and matching the pedestrian features corresponding to the target pedestrian image with pedestrian features in a database to obtain a pedestrian recognition result. According to the invention, the technical problem of low recognition result accuracy of pedestrian re-recognition in the prior art is solved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, and in particular, to an unsupervised pedestrian re-identification method, device, device and readable storage medium. Background technique [0002] Pedestrian re-identification is to search for the same pedestrian in different surveillance cameras, but due to the diversity of camera shooting angles, light intensity and human posture, the images of the same pedestrian captured by the camera are quite different, so that the pedestrian images are used for the identification of pedestrians. Pedestrian re-identification is more difficult. [0003] At present, in the process of pedestrian re-identification through pedestrian images, it is considered that the importance of each image is equivalent, and there is no distinction between the difficulty of pedestrian feature recognition in pedestrian images, and the attention to all pedestrian images is the same. Pedestrian images that are ea...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide an unsupervised pedestrian re-identification method, device, equipment and readable storage medium, aiming to solve the technical problem of low accuracy of the recognition result of pedestrian re-identification in the prior art

Images