Target re-identification method, device, storage medium and equipment

Abstract

The present disclosure relates to a target re-identification method, device, storage medium, and equipment. The method includes two times of image deletion, including: initially selecting the first feature value of the target object picture and the second feature value set corresponding to the set of pictures to be processed. A candidate picture set is determined from the picture set to be processed, wherein the similarity value between any two pictures in the candidate picture set is greater than or equal to a preset similarity value. and identifying the first feature value and the second feature value set based on the trained graph association recognition network, and determining a target picture set that is similar to the target object in the target object picture from the candidate picture set. In this way, more accurate positive samples can be determined from the image set to be processed, and the interference of negative samples can be reduced to obtain the target image set, so that the trajectory behavior of the objects contained in it can be analyzed based on the attribute information of the images in the target image set. The accuracy of the results is improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a target re-identification method, device, storage medium and equipment. Background technique [0002] Object re-identification is an important problem in the field of computer vision and intelligent video surveillance. Its purpose is to determine the location of the same object under the same or different cameras. With the advancement of urbanization and the increasing number of urban cameras, object re-identification has important practical applications in many fields, such as the analysis of pedestrian walking behavior, cross-camera pedestrian and vehicle tracking, and the detection of abnormal behavior of pedestrians and vehicles, etc. Wait. However, in practical applications, there may be interference from other pedestrians in the scene, and there may be extremely similar apparent characteristics between pedestrians and other factors, and these factors will h...

AI Technical Summary

Problems solved by technology

However, in practical applications, there may be interference from other pedestrians in the scene, and there may be extremely similar apparent characteristics between pedestrians and pedestrians, and these factors will have a negative impact on the target re-identification process.

Images