System and method for achieving face recognition based on wide-angle gun camera and multiple dome cameras

Abstract

The invention relates to a system and method for achieving face recognition based on a wide-angle gun camera and multiple dome cameras. The system comprises the wide-angle gun camera, the multiple dome cameras and a server. The wide-angle gun camera is used for conducting pedestrian detection and calculation of pedestrian spatial positions in images of the wide-angle gun camera. The dome camera corresponding to the position of a target pedestrian is utilized to conduct real-time tracking and face image extraction on the target pedestrian. The server is used for distributing tracking tasks to the dome camera corresponding to the position in real time according to the position, determined by the wide-angle gun camera, of the target pedestrian and utilizing a face image extracted by the dome camera for face recognition. By the adoption of the system and method for achieving face recognition based on the wide-angle gun camera and the multiple dome cameras, the problem of face recognition under the real-time video monitoring environment of important places is solved, by the cooperation of the wide-angle gun camera and the multiple dome cameras, accuracy and usability of face recognition under the real-time monitoring environment are achieved, practicability of the system used for monitoring, security and protection and other fields is improved, and the wider application range is possessed.

Description

technical field [0001] The invention relates to the field of computer image recognition, in particular to the field of computer vision and pattern recognition, and specifically refers to a system and method for realizing face recognition based on a wide-angle gun camera and a multi-ball camera. Background technique [0002] Face recognition is one of the most important tasks of biometrics. Its purpose is to automatically identify or confirm the identity of people in input static images or dynamic video images through the registered face database. Usually a face recognition system mainly includes four main parts: face detection and tracking, face alignment, feature extraction and feature matching, such as image 3 shown. [0003] In the past few decades, with the development of computer hardware technology, image processing, pattern recognition, computer vision and other related fields, the research of face recognition has made great progress. Very well established, it has a...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the above-mentioned shortcoming of prior art, provide a kind of face recognition problem that can solve key place real-time video monitoring environment, effectively overcome the problem of poor face image quality under traditional video monitoring environment, improve Face recognition accuracy in monitoring environment, system and method for realizing face recognition based on wide-angle gun camera and multi-ball camera with wider application range

Images