Method and device for determining body part semantic graph, model training method and pedestrian re-identification method

Abstract

The invention discloses a method for determining a body part semantic graph. The method comprises the following steps of: extracting a global feature graph of each image in a plurality of images of the same pedestrian; clustering all pixels in all the global feature maps to acquire a plurality of categories related to the body parts; for each pixel, according to the category to which the pixel belongs, generating a corresponding category label at the position of the pixel in the global feature map to which the pixel belongs, and respectively determining the obtained global feature map with the category label at each pixel position as a body part semantic map mapped by the global feature map, therefore, the acquisition efficiency of the image with the body part label is improved.

Description

technical field

[0001] The present invention relates to the technical field of computer vision, and in particular to a method and device for determining a semantic map of body parts, a training method and device for a pedestrian re-identification model, a method and device for re-identifying pedestrians based on unsupervised, computer equipment, and a storage medium. Background technique

[0002] Person re-identification (person re-ID) technology is becoming more and more popular in the field of contemporary computer vision, because it has important significance in the research and application of intelligent security and other fields. The goal of this technology is to identify the same person who wants to query and locate on different monitoring devices. In real scenes, how to accurately identify and match pedestrians has become a very challenging problem due to factors such as human body posture, camera angle changes, and lighting conditions. With the successful applicatio...

Images