CN108073859A - The monitoring device and method of a kind of specific region - Google Patents
The monitoring device and method of a kind of specific region Download PDFInfo
- Publication number
- CN108073859A CN108073859A CN201611006080.7A CN201611006080A CN108073859A CN 108073859 A CN108073859 A CN 108073859A CN 201611006080 A CN201611006080 A CN 201611006080A CN 108073859 A CN108073859 A CN 108073859A
- Authority
- CN
- China
- Prior art keywords
- face
- camera
- image
- facial image
- cameras
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses the monitoring devices and monitoring method of a kind of specific region, include 44 high-resolution cameras and be respectively arranged 4 positions in space, the camera shooting angle of each camera is 90 degree, to ensure that each position in surveillance area has 4 cameras to be covered.The human face photo image of shooting is compared with the facial image in storage unit.If the image that shooting is found after comparing is the facial image in database, alarm will not be sent, if the image that shooting is found after comparing is not the facial image in database, alarm can be sent.The apparatus and method utilize machine vision technique, reduce human cost, it is more accurate to enter region recognition simultaneously for strange personnel.
Description
Technical field
The invention belongs to image monitoring field, especially suitable for the device and method by image identifying invader.
Background technology
At present, personnel monitoring is generally carried out using camera for the personnel monitoring of public domain.When the peace for being responsible for monitoring
When guarantor person has found there are the strange personnel to enter feature region, implement corresponding security implementations.This method needs prolonged see
Examine display.Add human cost.The present invention reduces human cost, simultaneously for strange personnel using machine vision technique
It is more accurate into region recognition.
The content of the invention
A kind of specific region monitoring device is respectively arranged 4 positions in space including 4 high-resolution cameras,
The camera shooting angle of each camera is 90 degree, to ensure that each position in surveillance area has 4 cameras to be covered.Work as someone
For member into fashionable, at least two camera of high-resolution camera can take the face of people.4 camera data can be transmitted
To the face recognition portion of monitoring device.Identification part has face recognition unit, if the edge of two pictures appears in face, the face
Portion's recognition unit handles the edge image of two cameras, to be integrated into a complete face face picture.Identification part
Also there is storage unit, which is stored with the facial image of staff in the monitoring area.At face recognition unit
The human face photo managed is compared with the facial image in storage unit.If the image that shooting is found after comparing is in database
Facial image when, then will not send alarm, if finding the image of shooting after comparing when not being the facial image in database,
Alarm can be sent.
A kind of specific region monitoring method, includes the following steps：
1) 4 high-resolution cameras of setting are respectively arranged 4 positions in space, and the camera shooting angle of each camera is
90 degree, to ensure that each position in surveillance area has 4 cameras to be covered.When there is personnel to enter, the high-resolution
At least two camera of rate camera can take the face of people.
2) 4 camera data can be transferred to the face recognition portion of monitoring device.Identification part has face recognition list
Member, if the edge of two pictures appears in face, which handles the edge image of two cameras, with whole
It is combined into a complete face face picture.
3) storage unit of an identification part is provided, which is stored with the face figure of staff in the monitoring area
Picture.The human face photo that face recognition cell processing is crossed is compared with the facial image in storage unit.If it finds to clap after comparing
When the image taken the photograph is the facial image in database, then alarm will not be sent, if the image that shooting is found after comparing is not data
During facial image in storehouse, then alarm can be sent.
Description of the drawings
Fig. 1：The present invention implements schematic diagram
Specific embodiment
A kind of specific region monitoring device is respectively arranged in space including 4 high-resolution cameras 1a, 1b, 1c, 1d
4 positions, the camera shooting angle of each camera is 90 degree, to ensure that each position in surveillance area has 4 cameras to be covered
It covers.When there is personnel to enter, at least one camera can take people in described high-resolution camera 1a, 1b, 1c, 1d
Face.4 camera data can be transferred to the face recognition portion 2 of monitoring device.Identification part 2 has face recognition unit, if two
The edge of pictures appears in face, which handles the edge image of two cameras, to be integrated into one
Open complete face face picture.The identification part 2 also has storage unit, which is stored with work in the monitoring area
The facial image of personnel.The human face photo that face recognition cell processing is crossed is compared with the facial image in storage unit.If
When the image that shooting is found after comparison is the facial image in database, then alarm will not be sent, if finding shooting after comparing
When image is not the facial image in database, then alarm can be sent.
Implement the method that above device is alarmed in addition, further including.Include the following steps：
1) 4 high-resolution cameras 1a, 1b, 1c, 1d of setting are respectively arranged 4 positions in space, each to image
The camera shooting angle of head is 90 degree, to ensure that each position in surveillance area has 4 cameras 1a, 1b, 1c, 1d to be covered.When
When having the personnel to enter, at least two camera of high-resolution camera can take the face of people.
2) 4 camera data can be transferred to the face recognition portion 2 of monitoring device.Know with face the identification part 2
Other unit, if the edge of two pictures appears in face, which handles the edge image of two cameras,
To be integrated into a complete face face picture.
3) storage unit of an identification part 2 is provided, which is stored with the face of staff in the monitoring area
Image.The human face photo that face recognition cell processing is crossed is compared with the facial image in storage unit.If it is found after comparing
When the image of shooting is the facial image in database, then alarm will not be sent, the image of shooting is not several if being found after comparing
During according to facial image in storehouse, then alarm can be sent.
Edge extraction technology common in this field has been used in this apparatus and method.There are two even existing
Image that camera is taken pictures is overlapped to be happened, but has the part mutually repeated in the edge of image.Identification
The part repeated can be carried out the complete continuous facial image of formation stitched together by place by known software.
4 high-resolution cameras are distributed in the corner in monitoring region, to ensure that the personnel into the region exist
Its face of any position is all covered by camera.
Claims (2)
1. a kind of specific region monitoring device is respectively arranged in space including 4 high-resolution cameras (1a, 1b, 1c, 1d)
4 positions, the camera shooting angle of each camera is 90 degree, to ensure that each position in surveillance area has 4 cameras to be covered
It covers.When there is personnel to enter, at least one camera can take people in the high-resolution camera (1a, 1b, 1c, 1d)
Face.4 camera data can be transferred to the face recognition portion (2) of monitoring device.Identification part (2) has face recognition list
Member, if the edge of two pictures appears in face, which handles the edge image of two cameras, with whole
It is combined into a complete face face picture.The identification part (2) also has storage unit, which is stored with the monitored space
The facial image of staff in domain.Facial image in human face photo and storage unit that face recognition cell processing is crossed carries out
It compares.If the image that shooting is found after comparing is the facial image in database, alarm will not be sent, if being found after comparing
When the image of shooting is not the facial image in database, then alarm can be sent.
2. a kind of specific region monitoring method, includes the following steps：
1) 4 high-resolution cameras (1a, 1b, 1c, 1d) of setting are respectively arranged 4 positions in space, each camera
Camera shooting angle be 90 degree, to ensure that each position in surveillance area has 4 cameras (1a, 1b, 1c, 1d) to be covered.When
When having the personnel to enter, at least two camera of high-resolution camera can take the face of people.
2) 4 camera data can be transferred to the face recognition portion (2) of monitoring device.Know with face the identification part (2)
Other unit, if the edge of two pictures appears in face, which handles the edge image of two cameras,
To be integrated into a complete face face picture.
3) storage unit of an identification part (2) is provided, which is stored with the face figure of staff in the monitoring area
Picture.The human face photo that face recognition cell processing is crossed is compared with the facial image in storage unit.If it finds to clap after comparing
When the image taken the photograph is the facial image in database, then alarm will not be sent, if the image that shooting is found after comparing is not data
During facial image in storehouse, then alarm can be sent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611006080.7A CN108073859A (en) | 2016-11-16 | 2016-11-16 | The monitoring device and method of a kind of specific region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611006080.7A CN108073859A (en) | 2016-11-16 | 2016-11-16 | The monitoring device and method of a kind of specific region |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108073859A true CN108073859A (en) | 2018-05-25 |
Family
ID=62162687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611006080.7A Pending CN108073859A (en) | 2016-11-16 | 2016-11-16 | The monitoring device and method of a kind of specific region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108073859A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109218679A (en) * | 2018-10-19 | 2019-01-15 | 福建省南安市大大电子有限公司 | A kind of railway security management-control method based on Internet of Things |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236599A (en) * | 2007-12-29 | 2008-08-06 | 浙江工业大学 | Human face recognition detection device based on multi- video camera information integration |
| CN102103689A (en) * | 2011-03-07 | 2011-06-22 | 北京大学 | Frontal face image synthesis-based face recognition method |
| US20130188070A1 (en) * | 2012-01-19 | 2013-07-25 | Electronics And Telecommunications Research Institute | Apparatus and method for acquiring face image using multiple cameras so as to identify human located at remote site |
| CN104509097A (en) * | 2012-05-30 | 2015-04-08 | 株式会社日立制作所 | Monitoring camera control device and visual monitoring system |
| CN105894702A (en) * | 2016-06-21 | 2016-08-24 | 南京工业大学 | Intrusion detection alarm system based on multi-camera data fusion and detection method thereof |
| CN105956518A (en) * | 2016-04-21 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Face identification method, device and system |
| CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
-
2016
- 2016-11-16 CN CN201611006080.7A patent/CN108073859A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236599A (en) * | 2007-12-29 | 2008-08-06 | 浙江工业大学 | Human face recognition detection device based on multi- video camera information integration |
| CN102103689A (en) * | 2011-03-07 | 2011-06-22 | 北京大学 | Frontal face image synthesis-based face recognition method |
| US20130188070A1 (en) * | 2012-01-19 | 2013-07-25 | Electronics And Telecommunications Research Institute | Apparatus and method for acquiring face image using multiple cameras so as to identify human located at remote site |
| CN104509097A (en) * | 2012-05-30 | 2015-04-08 | 株式会社日立制作所 | Monitoring camera control device and visual monitoring system |
| CN105956518A (en) * | 2016-04-21 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Face identification method, device and system |
| CN105894702A (en) * | 2016-06-21 | 2016-08-24 | 南京工业大学 | Intrusion detection alarm system based on multi-camera data fusion and detection method thereof |
| CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
Non-Patent Citations (1)
| Title |
|---|
| 郭红健: "人脸检测与定位的硬件实现", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109218679A (en) * | 2018-10-19 | 2019-01-15 | 福建省南安市大大电子有限公司 | A kind of railway security management-control method based on Internet of Things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020125406A1 (en) | Safety guardianship method, apparatus, terminal and computer readable storage medium | |
| CN106600760B (en) | A kind of guests' information and the guest room personnel's detection system and method for moving in number automatic identification | |
| US20140307076A1 (en) | Systems and methods for monitoring personal protection equipment and promoting worker safety | |
| TWI681305B (en) | Surveillance method, surveillance device and surveillance system | |
| CN106951849B (en) | Monitoring method and system for preventing children from accidents | |
| US20210201610A1 (en) | Methods and System for Distributed Cameras and Demographics Analysis | |
| CN111626210B (en) | Personnel dressing detection method, processing terminal and storage medium | |
| KR102012672B1 (en) | Anti-crime system and method using face recognition based people feature recognition | |
| RU2012119843A (en) | METHOD FOR DISPLAYING VIDEO DATA ON A MOBILE DEVICE | |
| CN104200558A (en) | Security sending and pickup control system based on biometric feature recognition and security sending and pickup control method based on biometric feature recognition | |
| KR101754152B1 (en) | Thermal Patient Monitering System by Using Multiple Band Camera and Method thereof | |
| JP2012208610A (en) | Face image authentication apparatus | |
| CN113971782B (en) | Comprehensive monitoring information management method and system | |
| US20190068924A1 (en) | Monitoring system having personal information protection function and method thereof | |
| US9965612B2 (en) | Method and system for visual authentication | |
| CN107704851B (en) | Character identification method, public media display device, server and system | |
| TWI713368B (en) | Image device and method for detecting a thief | |
| CN104299176A (en) | Student pick-up and drop-off security management system | |
| WO2018086420A1 (en) | Displaying method and device, and smart mirror | |
| KR101822091B1 (en) | system for deciding and watching abnormal situation using biometric data and image data | |
| US20210264766A1 (en) | Anti-lost method and system for wearable terminal and wearable terminal | |
| CN108073859A (en) | The monitoring device and method of a kind of specific region | |
| JP5730000B2 (en) | Face matching system, face matching device, and face matching method | |
| CN110443134B (en) | Face recognition tracking system based on video stream and working method | |
| US20230135997A1 (en) | Ai monitoring and processing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180525 |