Pedestrian re-identification method of twin generative adversarial network based on attitude guidance pedestrian image generation

Abstract

The invention discloses a pedestrian re-identification method of a twin generative adversarial network based on attitude guidance pedestrian image generation. According to the implementation scheme, the method includes: carrying out target detection on pedestrian images according to a pedestrian image data set to obtain training samples; constructing a twin generative adversarial network model based on diversity sample generation, and exchanging attitude attribute information of two groups of pedestrian images input after target detection by the model to realize generation of diversity samples; constructing a twin generative adversarial network model based on identity feature maintenance, wherein identity information of a generated pedestrian image is reserved by the model through an identity discriminator, so that the robustness of pedestrian re-identification on the identity of the generated pedestrian image is improved; aiming at the problem that the generative adversarial network is difficult to optimize, constructing a twin generative adversarial network parameter learning method based on multi-objective optimization; in order to verify the effectiveness of the pedestrian re-identification method, carrying out pedestrian re-identification method verification on a data set formed by generated pedestrian images.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a pedestrian re-identification method based on a gesture-guided twin generation confrontation network for pedestrian image generation. Background technique [0002] With the rapid development of artificial intelligence technology and its wide application in the field of urban security, it is of great significance to study the basic theory and key technologies of deep learning and image recognition. Pedestrian re-identification can realize the function of retrieving specific target pedestrians in the field of view of multiple cameras in the monitoring network. It is a technology that uses computer vision methods to judge whether a specific pedestrian exists in an image or video sequence, and provides technical support for cross-camera pedestrian search. . At present, the key to pedestrian re-identification lies in the two steps of pedestrian feature representatio...

AI Technical Summary

Problems solved by technology

[0005] Studying the pedestrian re-identification method based on data generation can solve the main difficulty of the pedestrian re-identification problem, that is, the problem of too little data for individual pedestrians, which is not conducive to the model learning efficient and robust feature representation and measurement criteria

Images