Pedestrian re-identification method and device based on unsupervised learning and medium

Abstract

The invention discloses a pedestrian re-identification method and device based on unsupervised learning and a medium, and the method comprises the steps: obtaining a target image and a comparison image, and identifying whether a pedestrian exists in the target image in the comparison image through a pedestrian re-identification model based on unsupervised learning; outputting a recognition result; establishing a pedestrian re-identification model: carrying out initial training on the visual classifier according to the labeled source data set to obtain a visual classifier; learning the label-free target data set by using the vision classifier after initial training to obtain a matching probability and space-time information; obtaining a Bayesian fusion model according to the matching probability and the space-time information; carrying out similarity matching on pedestrian images in the unlabeled target data set by the Bayesian fusion model according to the comparison target pedestrian images to obtain a similarity score; sorting the similarity scores according to a preset threshold value to obtain a sorting result; when it is detected that the current model training optimization frequency is smaller than or equal to a preset optimization threshold value, performing parameter updating on the visual classifier.

Description

technical field [0001] The present invention relates to computer vision technology, in particular to a pedestrian re-identification method, device and medium based on unsupervised learning. Background technique [0002] With the construction of digital cities, our roads and living and working areas have been covered with cameras. How to effectively use the massive data generated by these cameras to promote the development of urban security, criminal investigation, intelligent transportation and other fields is a major challenge in the future. . To this end, we need to develop a cross-camera multi-target monitoring and tracking system, intelligently link multiple cameras, and make full use of the information provided by them to achieve intelligent security and intelligent transportation. [0003] Person re-identification (Person re-identification), also known as pedestrian re-identification, refers to the identification of target pedestrians in video sequences of existing po...

AI Technical Summary

Problems solved by technology

[0006] The technical problem mainly solved by the present invention is that in real-world scenarios, when faced with a large amount of pedestrian data, due to the lack of a training set with the same scale, the pedestrian re-identification model based on supervised learning cannot achieve the desired performance. For this reason, it is necessary to provide a pedestrian re-identification scheme based on unsupervised learning, so that the performance of pedestrian re-identification based on unsupervised learning can be improved.

Images