Pedestrian re-identification method and system based on neighborhood collaborative attention, medium and terminal

Abstract

The invention provides a pedestrian re-identification method and system based on neighborhood collaborative attention, a medium and a terminal. The method comprises the following steps: carrying out preliminary processing on an obtained pedestrian image to generate a to-be-identified pedestrian image after preliminary processing; carrying out feature reasoning on the to-be-identified pedestrian image to obtain a first vector feature of a to-be-identified pedestrian on the to-be-identified pedestrian image; performing feature reasoning on the target pedestrian image to obtain a second vector feature of the target pedestrian on the target pedestrian image; calculating the similarity between the first vector feature and the second vector feature, so as to achieve the pedestrian re-recognitionof the to-be-recognized pedestrian according to the similarity; according to the pedestrian re-identification method, the overall characteristics of the image and the characteristics of the local area are integrated, and the neighborhood local characteristics of different scales are combined through the context neighborhood relation of the local characteristics, so that the local detail characteristics of different scales of pedestrians are better noticed, the images of the same pedestrian are accurately matched, and the pedestrian re-identification precision is improved.

Description

technical field [0001] The invention belongs to the technical field of pedestrian re-identification, and in particular relates to a pedestrian re-identification method, system, medium and terminal based on neighborhood cooperative attention. Background technique [0002] Person Re-Identification (Person Re-Identification, also referred to as Re-ID) is one of the most challenging tasks in the field of computer vision. Pedestrian re-identification is to retrieve a given pedestrian from a large number of pedestrian images collected by different cameras. , at this stage, it has extremely important value and significance in the fields of commercial passenger flow and security; in the field of commercial security, it is often impossible to obtain high-quality face pictures in surveillance videos due to camera resolution and shooting angles. When identification fails, Re-ID becomes a very important retrieval technology. Re-ID can quickly detect suspicious persons, accurately locate...

AI Technical Summary

Problems solved by technology

[0005] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a pedestrian re-identification method, system, medium, and terminal based on neighborhood collaborative attention, which is used to solve the problem of pedestrian re-identification caused by external factors in the prior art. The problem of reduced accuracy of re-identification

Images