Pedestrian re-identification method and device based on pedestrian re-identification model, and storage medium

Abstract

The invention discloses a pedestrian re-identification method based on a pedestrian re-identification model, computer equipment and a computer readable storage medium. The method comprises the following steps: through randomly selecting a to-be-trained pedestrian image, a preset feature extraction module, a preset local correlation attention module and a preset overall correlation attention module, obtaining an optimized pedestrian feature of the to-be-trained pedestrian image and an optimized pedestrian feature optimization preset depth model with overall correlation; and generating a pedestrian re-identification model to obtain a pedestrian identification result of the to-be-tested pedestrian image, thereby realizing learning of dependency between the pedestrian images and dependency in the images through a deep model, fusing the dependency between the images and the dependency in the images into a network structure, learning robustness features of the pedestrian images, and improving the robustness of the to-be-tested pedestrian image. The problem of uncertainty caused by variability of environments, pedestrians and the like is solved, and the accuracy of pedestrian re-identification search is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a pedestrian re-identification method based on a pedestrian re-identification model, computer equipment, and a computer-readable storage medium. Background technique [0002] Security is closely related to the stability and development of society, and is closely related to people's life. It is an important strategic goal of the country. In order to maintain social stability and discover potential safety hazards in a timely manner, it is a timely and effective means to install surveillance cameras for all-weather monitoring. However, in the face of a large amount of monitoring data, realizing all-weather detection requires a lot of manpower and financial resources, which is costly and difficult to achieve. The purpose of person re-identification (Person Re-Identification) is to use computer technology to quickly and efficiently retrieve target pedest...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of this application is to provide a pedestrian re-identification method based on the pedestrian re-identification model, computer equipment and computer-readable storage medium, aiming to solve the existing method of restricting the relationship between features only restricting the feature distribution between the same pedestrian images , without calculating the dependencies between the same pedestrian images, only a small amount of feature information can be obtained, while the method of learning local features does not pay attention to the foreground information of pedestrians, and it is easy to lose important features.

Images