A cross-domain person re-identification method and system integrating multiple source domains

Abstract

The invention discloses a cross-domain pedestrian re-identification method and system that integrates multiple source domains. The method includes: when training the cross-domain pedestrian re-identification model, obtaining multiple sets of source domain data sets, using a set of source domain data sets to train a representation learning network and a metric learning network to perform cross-domain pedestrian re-identification model Training to obtain a trained cross-domain pedestrian re-identification model. When performing pedestrian re-identification, input pedestrian sample pairs to be identified into the trained cross-domain pedestrian re-identification model to obtain pedestrian re-identification results. By adopting the method and system of the present invention, the data of multiple source domains are fused during the training process, and the feature representation of pedestrians can be better learned. Compared with a single training model, the accuracy of pedestrian re-identification can be improved, which effectively solves the problem of The problem of model performance degradation caused by inter-domain differences.

Description

technical field [0001] The present invention relates to the technical field of pedestrian re-identification, in particular to a cross-domain pedestrian re-identification method and system that integrates multiple source domains. Background technique [0002] Person re-identification (Person re-identification), also known as pedestrian re-identification, is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence. In recent years, due to the rapid development of deep learning, the performance of pedestrian re-identification algorithms has also been improved unprecedentedly. When implementing a person re-identification system based on deep learning, when the model trained by a single training set is applied to the actual scene, the performance decline is very obvious, because when the trained model is directly used in the real scene, often Because of the inter-domain differences between the pedestrians i...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a cross-domain pedestrian re-identification method and system that integrates multiple source domains, which can effectively solve the problem of model performance degradation caused by inter-domain differences and improve the accuracy of pedestrian re-identification

Images