A peer identification method, device, system and computer storage medium

Abstract

The present invention provides a method, device, system, and computer storage medium for identifying persons in the same company. The identifying method for accompanying persons includes: acquiring snapshot data of the target person and generating a first data set; determining an effective snapshot time according to the first data set Segment and predetermined coverage area, obtain the snapshot data of the predetermined coverage area within the effective capture time period, and save it as the second data set; extract the face image in it based on the second data set, and save it as the snapshot data Face collection; cluster the face images in the snapshot data face collection to obtain accurate peer recognition results. According to the method, device, system and computer storage medium of the present invention, accurate and comprehensive snapshot data are obtained through area search and secondary recognition of snapshot images, and peer-to-peer analysis of human faces is performed to ensure the accuracy of the results.

Description

technical field [0001] The present invention relates to the technical field of personnel identification, and more particularly relates to a method and device for identification of accompanying personnel. Background technique [0002] With the rapid development of face recognition in recent years, the analysis of existing peers is based on the comparison of the snapshot data before and after the current capture of faces, and the ones with the highest number of occurrences are considered to be their peers. However, this is subject to the following problems, resulting in inaccurate results: When calculating with the camera as the location of the peers, since the face checkpoints are generally security checkpoints, which are not necessary areas, fellow perpetrators will deliberately avoid a certain distance from their accomplices , resulting in many times the person with the highest number of occurrences is not his peers, and the real peers are lost in the lower number of peers ...

AI Technical Summary

Problems solved by technology

However, this is subject to the following problems, resulting in inaccurate results: When calculating with the camera as the location of the peers, since the face checkpoints are generally security checkpoints, which are not necessary areas, fellow perpetrators will deliberately avoid a certain distance from their accomplices , resulting in many times the person with the highest number of occurrences is not his peers, and the real peers are lost in the lower number of peers at the current point, and cannot be found out; and the camera misses when facing a large number of people passing by, resulting in Loss of data, resulting in inaccurate results

[0003] Therefore, there is a problem in the prior art that it is difficult to ensure the accuracy of the results of the analysis of the techniques and tactics by the current peers

Images