Unsupervised pedestrian re-identification method based on category adaptive clustering

Abstract

The invention provides an unsupervised pedestrian re-identification method based on category adaptive clustering. The method comprises the following steps: firstly, pre-distributing an initializationlabel for a label-free data set, and extracting high-dimensional features of a pedestrian image by utilizing a CNN model; then, carrying out staged category adaptive clustering on the feature set, updating an image label, calculating an average contour coefficient of a clustering result of the stage, and alternately updating a feature extraction CNN model and a category adaptive clustering model until an inflection point appears in the average contour coefficient; and finally, extracting test pedestrian image features by using the CNN model at the inflection point obtained by training, and calculating a feature distance to obtain an unsupervised pedestrian re-identification result. The method can solve the problem that the number of individuals in an unmarked data set pedestrian re-identification task cannot be determined, can dynamically adapt to data sets of different scales, and has high algorithm efficiency and precision.

Description

technical field [0001] The invention belongs to the technical fields of computer vision and pedestrian re-identification, and in particular relates to an unsupervised pedestrian re-identification method based on category adaptive clustering. Background technique [0002] With the continuous growth of the urban population, people pay more and more attention to social and public security issues. At present, many public places are covered with large-scale network cameras, which are an important guarantee for monitoring security. In order to improve the security intelligence level of network cameras, pedestrian re-identification technology is a research hotspot in the field of visual analysis, and has received extensive attention from the academic community. Pedestrian re-identification is aimed at pedestrian matching in a non-overlapping multi-camera network, that is, to confirm whether the pedestrian targets captured by cameras in different positions at different times are the...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the prior art, the present invention provides an unsupervised pedestrian re-identification method based on category adaptive clustering, aiming to solve the problem that the existing unsupervised pedestrian re-identification method is difficult to extract discriminative features from pedestrian images and accurately identify low rate problem

Images