Surveillance video character identity identification system and method thereof fusing facial multi-angle feature

Abstract

The invention discloses a surveillance video character identity identification system and a surveillance video character identity identification method fusing facial multi-angle features. The surveillance video character identity identification system comprises a target detection module, a multi-angle face identification module and an identity matching module, wherein the target detection module is used for converting a section of surveillance video into a keyframe set containing people; the multi-angle face identification module is used for converting the keyframe set containing people into a face image sequence with angle value tags; and the identity matching module is used for completing feature vector similarity matching of the face image sequence with the angle value tags and an image sequence in an identity library, and finding out proximate identity output as an identification result. The surveillance video character identity identification system and the surveillance video character identity identification method can integrate multi-angle feature information of a face in the surveillance video, thereby improving precision of identity identification when character attitudes in the surveillance video are of great randomness.

Description

Technical field [0001] The invention belongs to the field of intelligent video monitoring, and relates to technologies such as pattern recognition and artificial intelligence, and in particular to a monitoring video person identification system and method that integrates multi-angle features. Background technique [0002] In modern society, there are more and more places that require identity authentication. Face recognition is a technology that uses the biological characteristics of humans to perform identity authentication. With the development of video surveillance, information security, access control and other application fields, the video face recognition system has huge application prospects in these fields. [0003] At present, face recognition is mainly used in fields such as time attendance and access control identity verification, and there is no relatively complete face recognition monitoring device used in monitoring scenarios. It is mainly due to the fact that face r...

AI Technical Summary

Problems solved by technology

Its defect is that it is subject to a lot of external interference. Once the face is rotated, occluded or partially blurred, causing some features to disappear and resulting in incomplete face image features, this algorithm will fail, resulting in

Images