Image re-identification method and device, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence, and provides an image re-identification method and device, electronic equipment and a storage medium. The image re-identification method comprises the steps of: obtaining a to-be-identified image; based on a preset feature extraction model, extracting global re-identification features and local re-identification features of the to-be-identified image; performing fusion processing on the global re-identification features and the local re-identification features of the to-be-identified image to obtain fusion features; and carrying out classification processing on the fusion features to generate re-identification features, used for image re-identification, of the to-be-identified image. According to the image re-identification method and device, the electronic equipment and the storage medium, the features of multiple scales can be extracted from the to-be-identified image based on the preset feature extraction model to perform image re-identification, the robustness of image re-identification is enhanced, and the identification performance of image re-identification is improved.

Description

technical field [0001] The present application relates to the technical field of intelligent decision-making, and in particular to an image re-identification method, device, electronic equipment and storage medium. Background technique [0002] Pedestrian re-identification technology (hereinafter referred to as reID) refers to the technology of automatically retrieving target pedestrians in camera videos from multiple perspectives without overlapping and overlapping, and is mainly used in scenarios such as intelligent video surveillance and retrieval. However, due to the differences in the installation of the cameras during the installation process, the changes in the posture of pedestrians and the angle of view of the cameras when shooting with different cameras, the differences in picture quality when taking pictures with different cameras, and the occlusion of the cameras, the pedestrian re-identification is difficult. It is difficult to improve the recognition performanc...

AI Technical Summary

Problems solved by technology

However, due to the differences in the installation of the cameras during the installation process, the changes in the posture of pedestrians and the angle of view of the cameras when shooting with different cameras, the differences in picture quality when taking pictures with different cameras, and the occlusion of the cameras, the pedestrian re-identification is difficult. Recognition performance is difficult to improve

Most of the existing reID methods use the last layer of features of the image to perform pedestrian re-identification by extracting the coarse-grained features of the image. Such methods are prone to information loss, and it is difficult to learn robust feature representations. The recognition of pedestrian re-identification poor performance

Moreover, the reID method used in a specific intelligent video surveillance scene is often combined with the online pedestrian tracking method. If the overall reID feature is directly applied to the tracking problem, the tracking effect is poor

Images