Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-camera-based face recognition method and multi-camera-based face recognition system

A face recognition system and face recognition technology, applied in closed-circuit television systems, character and pattern recognition, computer parts, etc., can solve the problems of blind spots for monitoring, insufficient field of view of the main camera, and inability to cover monitoring areas.

Inactive Publication Date: 2012-08-22
东北大学秦皇岛分校
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, modern buildings often have many irregular areas (such as the Japanese Pavilion, the French Pavilion, and the British Pavilion at the Shanghai World Expo). These irregular monitoring areas cannot be provided with a main monitoring area that can cover the entire monitoring area due to the complexity of the spatial structure. Cameras; or there are many occluders in regular areas (such as art galleries and museums with many showcases), in such monitoring areas, the main camera will produce monitoring blind spots due to occlusions; or super-large areas (such as airports, trains, etc.) station, gymnasium), in this type of monitoring area, the main camera will not be able to cover the entire monitoring area due to insufficient field of view

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-camera-based face recognition method and multi-camera-based face recognition system
  • Multi-camera-based face recognition method and multi-camera-based face recognition system
  • Multi-camera-based face recognition method and multi-camera-based face recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Embodiment 1, face recognition method based on multi-camera, such as figure 1 shown, including the following steps:

[0045] S1, the camera locates and tracks the target appearing in its preset monitoring sub-area, and judges the facial posture parameters of the target;

[0046] S2, select a suitable camera according to the target position information and face posture parameters to form a working group and collect multi-view face images;

[0047] S3, using a multi-view face recognition method to identify the target;

[0048] S4, when the target enters the preset monitoring sub-area of ​​another camera, go to S1.

[0049] In the above method, the camera adopts an active camera, that is, a PTZ (Pan-Tilt-Zoom) camera, so that clear images of human faces can be obtained.

[0050] In the above method, the camera used for positioning and tracking in the working group does not move during the working process, and other cameras rotate to collect multi-view face images, where...

Embodiment 2

[0076] Example 2, Figure 4 It is a real layout map of a museum, 22 of which are clapboards. refer to Figure 4 , a face recognition system based on multi-camera cooperation is used to monitor and recognize human targets in irregular areas: it includes a central processor 21 and a plurality of cameras 1-20. The central processor 21 and each camera form a local area network in a wired or wireless manner, and the central processor 21 can communicate with any camera in the monitoring system.

[0077] A set of specific large-capacity face database and high-performance face recognition program are stored in the central processing unit 21, as well as a dictionary for selecting suitable cameras to form a working group and a set of preset monitoring sub-areas containing each camera. Electronic map of the distribution. The tasks of the central processor 21 are: 1) receiving the position information and the facial posture parameters of the human target delivered by the camera, and sa...

Embodiment 3

[0097] Example 3, Figure 5 It is a layout diagram with a regular shielded area, in which 22 is a partition. refer to Figure 5 , a face recognition system based on multi-camera cooperation is used to monitor and recognize human targets in occluded areas. Its concrete implementation steps are identical with embodiment 2.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-camera-based face recognition method and a multi-camera-based face recognition system. The method comprises the following steps of: 1, positioning and tracking a target in a preset monitoring sub-region of one camera by the camera, and discriminating face attitude parameters of the target; 2, selecting the proper camera to build a working group according to the position information of the target and the face attitude parameters and acquiring a multi-viewing-angle face image; 3, identifying the target by using a multi-viewing-angle face recognition method; and 4, when the target enters the preset monitoring sub-region of another camera, executing the step 1. The invention has the advantages that: a plurality of cameras finish the positioning and tracking of the target one by one; the method and the system are applicable to monitoring of irregular, blocked and super-large regions; the multi-viewing-angle face image of the target is acquired by using the working group, dynamically built, of the camera, so the availability of the acquired face image is improved, and the maximum efficiency of the camera is achieved; and a monitoring mode without a main camera has expandability and robustness.

Description

technical field [0001] The invention relates to a face recognition method and system based on multi-cameras in irregular, occluded and super large areas, and belongs to the technical field of face recognition of a single target. Background technique [0002] Among the many existing biometric identification technologies, face recognition technology has been widely concerned in recent years because of its unique advantages of initiative, non-invasiveness and user-friendliness. At present, the video surveillance system is a mainstream direction in the practical application of face recognition technology. Usually, the video surveillance system uses multiple cameras to cooperate to complete the face recognition task. The advantages are: 1) more face images from various perspectives can be obtained without the cooperation of human targets; 2) multiple cameras can Better coverage of the monitoring area, without monitoring blind spots. Video surveillance system is mainly used in p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00H04N7/18
Inventor 汪晋宽才溪韩光
Owner 东北大学秦皇岛分校
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com