CN107688767A - The system and method for human body feature is extracted under a kind of high-noise environment - Google Patents
The system and method for human body feature is extracted under a kind of high-noise environment Download PDFInfo
- Publication number
- CN107688767A CN107688767A CN201610628912.2A CN201610628912A CN107688767A CN 107688767 A CN107688767 A CN 107688767A CN 201610628912 A CN201610628912 A CN 201610628912A CN 107688767 A CN107688767 A CN 107688767A
- Authority
- CN
- China
- Prior art keywords
- face
- main control
- control computer
- noise
- follow
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Abstract
The invention discloses the system that human body feature is extracted under a kind of high-noise environment, including high-definition camera, noise level indicator, Face datection and follow-up mechanism, image pick-up card, Face detection device, human eye positioner, face geometry and optical correction device, feature-extraction analysis device and face data bank indexing unit；The output end of the high-definition camera and noise level indicator is electrically connected with the input of main control computer, the data storage device and data transmission device are connected with main control computer by LAN, the output end of the Face datection and follow-up mechanism and the input of main control computer are electrically connected with, and the output end of the Face detection device and human eye positioner is electrically connected with the input of Face datection and follow-up mechanism.The present invention carries out face seizure using high-definition camera, and noise level indicator avoids noise jamming, and collection image is carried out into geometry and optical correction.
Description
Technical field
The present invention relates to the system regions of extraction human body feature, people is extracted under specifically a kind of high-noise environment
The system and method for body region feature.
Background technology
Face capture refers to detect portrait in a frame of piece image or video flowing and separates portrait from background
Out, and automatically preserved.Portrait tracking refers to utilize portrait capture technique, shot when specified portrait in camera
In the range of automatically it is tracked when moving.It is poor recognition performance to be present in the human body recognition system that there is currently, in high noisy
The deficiencies of precise positioning can not be carried out under environment, it is therefore desirable to human body feature is extracted under a kind of new high-noise environment
System.
The content of the invention
For above-mentioned the shortcomings of the prior art, it is an object of the invention to provide extract human body under a kind of high-noise environment
The system and method for genius loci.
To achieve these goals, the technical solution adopted in the present invention is：Human body portion is extracted under a kind of high-noise environment
The system of position feature, including high-definition camera, noise level indicator, Face datection and follow-up mechanism, image pick-up card, Face detection
Device, human eye positioner, face geometry and optical correction device, feature-extraction analysis device and face data bank index dress
Put；The output end of the high-definition camera and noise level indicator is electrically connected with the input of main control computer, the data
Storage device and data transmission device are connected with main control computer by LAN, the output of the Face datection and follow-up mechanism
The input of end and main control computer is electrically connected with, and described image capture card is connected with main control computer by LAN, described
The output end of Face detection device and human eye positioner is electrically connected with the input of Face datection and follow-up mechanism, described
Face geometry and optical correction device and feature-extraction analysis device pass through office with Face detection device and human eye positioner
Domain net connection, the face data bank indexing unit are connected with main control computer by LAN.
The systemic effect method of human body feature is extracted under a kind of high-noise environment：Comprise the following steps, step 1 is right
Noise is analyzed and peeled off；Step 2, Face datection and follow-up mechanism keep track；Step 3, face geometry and optics are rectified
Equipment correction catches image；Step 4, main control computer store results.
Wherein in described step one, the accurate seizure that is carried out using high-definition camera to face, while noise monitoring
Instrument is analyzed and peeled off to noise, clears the sound source for catching object；
In described step two, kept track by Face datection and follow-up mechanism to catching object；
In described step three, the image of seizure is corrected by face geometry and optical correction device, detected simultaneously
Face and human eye；
In described step four, the testing result in step 3 is inputted into face data bank indexing unit, it is finally that result is defeated
Main control computer is delivered to, by main control computer store results.
Further, the inside of the noise level indicator is provided with sound/shake signal condition instrument and high speed data acquisition system.
Further, the inside of the main control computer is provided with failure detector.
Further, the output end of the sound/shake signal condition instrument and high speed data acquisition system is defeated with noise level indicator
Enter end to be electrically connected with.
After adopting the above technical scheme, the invention has the advantages that compared with the prior art,：
The system that human body feature is extracted under a kind of high-noise environment of the present invention, face is carried out using high-definition camera
Catch, it is relatively sharp, sound/shake signal condition instrument is set in noise level indicator and high speed data acquisition system avoids the dry of noisy environment
Disturb, and analyze the sound source for catching object, schemed using Face datection and follow-up mechanism to catching object persistence tracking, and by collection
As carrying out geometry and optical correction, the image captured is more accurate, and entering face data bank by LAN connection indexes, and searches
Suo Xiaoguo is good, accurate positioning, and transmits information to main control computer, and main control computer can realize data storage and transmission.
Brief description of the drawings
The present invention is further described with reference to the accompanying drawings and examples：
Fig. 1 is the theory diagram of the present invention；
Fig. 2 is the control principle drawing of the present invention；
In reference：1- high-definition cameras；2- noise level indicators；21- sound/shake signal condition instrument；22- high-speed data acquisitions
Device；3- main control computers；4- data storage devices；5- data transmission devices；6- failure detectors；7- Face datections and tracking
Device；8- image pick-up cards；9- Face detection devices；10- human eye positioners；11- faces geometry and optical correction device；
12- feature-extraction analysis devices；13- face data bank indexing units.
Embodiment
As described below is only presently preferred embodiments of the present invention, is not intended to limit the scope of the present invention.
Embodiment, as shown in figure 1, the system of human body feature is extracted under a kind of high-noise environment, including high-definition camera
Machine 1, noise level indicator 2, Face datection and follow-up mechanism 7, image pick-up card 8, Face detection device 9, human eye positioner 10,
Face geometry and optical correction device 11, feature-extraction analysis device 12 and face data bank indexing unit 13；High-definition camera 1
It is electrically connected with the input of the output end of noise level indicator 2 with main control computer 3, data storage device 4 and data transfer
Device 5 is connected with main control computer 3 by LAN, the output end and main control computer 3 of Face datection and follow-up mechanism 7 it is defeated
Enter end to be electrically connected with, image pick-up card 8 is connected with main control computer 3 by LAN, Face detection device 9 and human eye positioning dress
Put 10 output end to be electrically connected with the input of Face datection and follow-up mechanism 7, face geometry and optical correction device 11
It is connected with feature-extraction analysis device 12 with Face detection device 9 and human eye positioner 10 by LAN, face data
Storehouse indexing unit 13 is connected with main control computer 3 by LAN.The inside of noise level indicator 2 is provided with sound/shake signal condition instrument
21 and high speed data acquisition system 22, the inside of main control computer 3 is provided with failure detector 6, and sound/shake signal condition instrument 21 and height
The output end of fast data acquisition unit 22 is electrically connected with the input of noise level indicator 2.
The systemic effect method of human body feature is extracted under a kind of high-noise environment：Comprise the following steps, step 1, make an uproar
Sound is analyzed and peeled off；Step 2, Face datection and follow-up mechanism keep track；Step 3, face geometry and optical correction
Device correction catches image；Step 4, main control computer store results；
Wherein in described step one, the accurate seizure that is carried out using high-definition camera 1 to face, while noise level indicator 2
Noise is analyzed and peeled off, clears the sound source for catching object；
In described step two, kept track by Face datection and follow-up mechanism 7 to catching object；
In described step three, the image of seizure is corrected by face geometry and optical correction device 11, examined simultaneously
Survey face and human eye；
In described step four, the testing result in step 3 is inputted into face data bank indexing unit 13, finally by result
Main control computer 3 is delivered to, by main control computer store results.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.
Described above, only presently preferred embodiments of the present invention is not intended to limit the invention, every skill according to the present invention
Any trickle amendment, equivalent substitution and the improvement that art is substantially made to above example, should be included in technical solution of the present invention
Protection domain within.
Claims (5)
1. the system of human body feature is extracted under a kind of high-noise environment, including high-definition camera（1）, noise level indicator（2）、
Face datection and follow-up mechanism（7）, image pick-up card（8）, Face detection device（9）, human eye positioner（10）, face geometry
With optical correction device（11）, feature-extraction analysis device（12）With face data bank indexing unit（13）；It is characterized in that：Institute
State high-definition camera（1）And noise level indicator（2）Output end and main control computer（3）Input be electrically connected with, it is described
Data storage device（4）And data transmission device（5）With main control computer（3）Connected by LAN, the Face datection and
Follow-up mechanism（7）Output end and main control computer（3）Input be electrically connected with, described image capture card（8）With master control meter
Calculation machine（3）Connected by LAN, the Face detection device（9）With human eye positioner（10）Output end with face examine
Survey and follow-up mechanism（7）Input be electrically connected with, the face geometry and optical correction device（11）And feature-extraction analysis
Device（12）With Face detection device（9）With human eye positioner（10）Connected by LAN, the face data bank rope
Leading-in device（13）With main control computer（3）Connected by LAN.
2. the systemic effect method of human body feature is extracted under a kind of high-noise environment：Comprise the following steps, step 1, noise
Analysis and stripping；Step 2, Face datection and follow-up mechanism keep track；Step 3, face geometry and optical correction device school
It is positive to catch image；Step 4, main control computer store results；It is characterized in that：
Wherein in described step one, using high-definition camera（1）The accurate seizure carried out to face, while noise level indicator
（2）Noise is analyzed and peeled off, clears the sound source for catching object；
In described step two, pass through Face datection and follow-up mechanism（7）Keep track to catching object；
In described step three, pass through face geometry and optical correction device（11）The image of seizure is corrected, simultaneously
Detect face and human eye；
In described step four, the testing result in step 3 is inputted into face data bank indexing unit（13）, finally will knot
Fruit is delivered to main control computer（3）, by main control computer store results.
3. the system of human body feature is extracted under a kind of high-noise environment according to claim 1, it is characterised in that：Institute
State noise level indicator（2）Inside be provided with sound/shake signal condition instrument（21）And high speed data acquisition system（22）.
4. the system of human body feature is extracted under a kind of high-noise environment according to claim 1, it is characterised in that：Institute
State main control computer（3）Inside be provided with failure detector（6）.
5. the system of human body feature is extracted under a kind of high-noise environment according to claim 1, it is characterised in that：Institute
State sound/shake signal condition instrument（21）And high speed data acquisition system（22）Output end and noise level indicator（2）Input electricity
Property connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610628912.2A CN107688767A (en) | 2016-08-04 | 2016-08-04 | The system and method for human body feature is extracted under a kind of high-noise environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610628912.2A CN107688767A (en) | 2016-08-04 | 2016-08-04 | The system and method for human body feature is extracted under a kind of high-noise environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107688767A true CN107688767A (en) | 2018-02-13 |
Family
ID=61151579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610628912.2A Pending CN107688767A (en) | 2016-08-04 | 2016-08-04 | The system and method for human body feature is extracted under a kind of high-noise environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107688767A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460288A (en) * | 2018-04-02 | 2018-08-28 | 惠州学院 | Big data safe encryption method, device, storage medium and mobile terminal |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200962629Y (en) * | 2006-10-27 | 2007-10-17 | 天津市亚安科技电子有限公司 | Video camera with the sound-finding and positioning function |
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracing identification system for artificial neural control |
| CN101739548A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Eye detection method and system |
| CN102547123A (en) * | 2012-01-05 | 2012-07-04 | 天津师范大学 | Self-adapting sightline tracking system and method based on face recognition technology |
| CN202794106U (en) * | 2012-04-06 | 2013-03-13 | 南京航空航天大学 | Stress detecting device based on Barkhausen principle |
| CN105681920A (en) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | Network teaching method and system with voice recognition function |
| CN205356567U (en) * | 2015-12-21 | 2016-06-29 | 常州信息职业技术学院 | Pattern fabrication intelligence high definition video monitored control system based on optics and electricity are rectified |
| CN105798917A (en) * | 2016-04-29 | 2016-07-27 | 深圳市神州云海智能科技有限公司 | Community safety alarm method and patrol robot |
-
2016
- 2016-08-04 CN CN201610628912.2A patent/CN107688767A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN200962629Y (en) * | 2006-10-27 | 2007-10-17 | 天津市亚安科技电子有限公司 | Video camera with the sound-finding and positioning function |
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracing identification system for artificial neural control |
| CN101739548A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Eye detection method and system |
| CN102547123A (en) * | 2012-01-05 | 2012-07-04 | 天津师范大学 | Self-adapting sightline tracking system and method based on face recognition technology |
| CN202794106U (en) * | 2012-04-06 | 2013-03-13 | 南京航空航天大学 | Stress detecting device based on Barkhausen principle |
| CN205356567U (en) * | 2015-12-21 | 2016-06-29 | 常州信息职业技术学院 | Pattern fabrication intelligence high definition video monitored control system based on optics and electricity are rectified |
| CN105681920A (en) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | Network teaching method and system with voice recognition function |
| CN105798917A (en) * | 2016-04-29 | 2016-07-27 | 深圳市神州云海智能科技有限公司 | Community safety alarm method and patrol robot |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460288A (en) * | 2018-04-02 | 2018-08-28 | 惠州学院 | Big data safe encryption method, device, storage medium and mobile terminal |
| CN108460288B (en) * | 2018-04-02 | 2022-02-08 | 惠州学院 | Big data security encryption method and device, storage medium and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Drone detection based on an audio-assisted camera array | |
| CN105718470B (en) | A kind of POI data treating method and apparatus | |
| Huang et al. | Detection of violent crowd behavior based on statistical characteristics of the optical flow | |
| Pan et al. | Power line detection via background noise removal | |
| CN103632488A (en) | Human face capturing alarm device and method thereof | |
| Goudelis et al. | Fall detection using history triple features | |
| JP2017174343A (en) | Customer attribute extraction device and customer attribute extraction program | |
| CN111814510A (en) | Detection method and device for remnant body | |
| KR101995523B1 (en) | Apparatus and method for object detection with shadow removed | |
| Nan et al. | Intelligent detection of Multi-Class pitaya fruits in target picking row based on WGB-YOLO network | |
| Hsu et al. | Design and implementation of image electronic fence with 5G technology for smart farms | |
| CN105678805A (en) | ARM platform-based aerial-photography target detection system | |
| CN107688767A (en) | The system and method for human body feature is extracted under a kind of high-noise environment | |
| CN103914850B (en) | Automatic video labeling method and system based on motion matching | |
| US20190311192A1 (en) | Video monitoring | |
| Mistry et al. | Drone-vs-bird: Drone detection using yolov7 with csrt tracker | |
| CN102506815A (en) | Multi-target tracking and passive distance measuring device based on image recognition | |
| CN106295469A (en) | A kind of guest's property analysis method based on face, Apparatus and system | |
| CN106210467A (en) | Identification system and method to same video object under a kind of different angles | |
| Radha et al. | Detection of unauthorized human entity in surveillance video | |
| CN111461104B (en) | Visual recognition method, device, equipment and storage medium | |
| Xue et al. | Action recognition based on dense trajectories and human detection | |
| Liu et al. | RGB-D based multi-attribute people search in intelligent visual surveillance | |
| Ahir et al. | A review on abnormal activity detection methods | |
| Duan et al. | Automatic person identification in camera video by motion correlation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180213 |
|
| RJ01 | Rejection of invention patent application after publication |