Image processing method and device, electronic device and storage medium

Abstract

The present disclosure relates to an image processing method and device, an electronic device, and a storage medium, wherein the method includes: establishing a first distance matrix between each image according to a feature vector of each image in an image data set; The matrix determines k1 first adjacent images with the smallest first distance between the feature vectors of each image, and selects k2 second adjacent images that meet the first rule from the k1 first adjacent images , wherein k1 is greater than or equal to k2, and both k1 and k2 are integers greater than 1; based on the k2 second adjacent images of each image, a second distance matrix between each image is established; using the first The distance matrix and the second distance matrix perform grouping and clustering on the images in the image data set. The present disclosure can improve the accuracy of clustering and grouping.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular to an image processing method and device, electronic equipment, and a storage medium. Background technique [0002] Pedestrian clustering is an important part of intelligent video retrieval and analysis. The general process of pedestrian clustering is to first extract pedestrian features through the pedestrian feature extraction model, and then use the extracted features and corresponding clustering algorithms to The images of pedestrians are clustered. [0003] In the field of pedestrian re-identification, the purpose of pedestrian clustering is mainly to cluster images of the same pedestrian. At present, the clustering algorithm used in pedestrian clustering in pedestrian re-identification is mainly based on iterative graph search method, and its main disadvantage is that the clustering period will increase exponentially with the increase of the number of pedestrians....

AI Technical Summary

Problems solved by technology

At present, the clustering algorithm used in pedestrian clustering in pedestrian re-identification is mainly based on iterative graph search method, and its main disadvantage is that the clustering period will increase exponentially with the increase in the number of pedestrians.

[0004] On the other hand, if you simply use a clustering algorithm to cluster pedestrians, the features of the image cannot be extracted most effectively, and the accuracy of pedestrian clustering cannot be effectively improved.

Images