Clustering effect evaluation method, system, medium and device

Abstract

The invention belongs to the technical field of image data processing, and particularly relates to a clustering effect evaluation method and system, a medium and a device. The objective of the invention is to solve the problem that an existing evaluation method cannot effectively evaluate the cross-mirror tracking effect of a clustering system in shopping mall service. In order to achieve the purpose, all to-be-clustered data samples containing annotation information are utilized, and after all prediction classification groups are obtained after all to-be-clustered data samples are clustered by a clustering system, all prediction classification groups are obtained based on the total amount of all to-be-clustered data samples, the total amount of associated data samples and the total amount of correctly associated data samples. And calculating a clustering effect evaluation index for the clustering system by using the confusion matrix. Therefore, the method is different from an existing evaluation method which focuses on the arrangement effect of the data samples in each classification group, but more pays attention to the comprehensive accuracy of the clustering result, so that the cross-mirror tracking effect of the clustering system in the shopping mall service can be effectively evaluated.

Description

technical field [0001] The invention belongs to the technical field of image data processing, and in particular relates to a clustering effect evaluation method, system, medium and device. Background technique [0002] Clustering is a method of data mining. In the field of image processing technology, image clustering is a process of dividing multiple images into multiple classes composed of similar images based on image features. Image clustering plays an important role in image segmentation, object tracking and other fields. At present, in commercial scenarios, clustering systems and cross-mirror tracking (ReId) technology are widely used. The purpose is to solve the identification and retrieval of pedestrians in cross-camera and cross-scenario situations. Tracking, enhancing the spatio-temporal continuity of data. For example, in a large shopping mall, clustering the snapshots collected by the cameras at each point of the shopping mall can depict the movement trajector...

AI Technical Summary

Problems solved by technology

[0007] In order to solve or at least partially solve the problem that existing evaluation methods cannot effectively evaluate the effect of cross-mirror tracking of clustering systems in shopping malls

Images