CN106897678B - A kind of remote human face recognition methods of combination heartbeat signal, device and system - Google Patents
A kind of remote human face recognition methods of combination heartbeat signal, device and system Download PDFInfo
- Publication number
- CN106897678B CN106897678B CN201710069368.7A CN201710069368A CN106897678B CN 106897678 B CN106897678 B CN 106897678B CN 201710069368 A CN201710069368 A CN 201710069368A CN 106897678 B CN106897678 B CN 106897678B
- Authority
- CN
- China
- Prior art keywords
- face
- pedestrian
- image
- spatial position
- heartbeat signal
- 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.)
- Active
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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of remote human face recognition methods of combination heartbeat signal, device and system, and the method includes the following steps: the image in acquisition monitoring area, and pedestrian image is extracted from acquired image and determines pedestrian spatial position;According to pedestrian spatial position, the spatial position of pedestrian's heartbeat signal is obtained using light vibration imaging technique;According to the natural place relationship of heartbeat signal and face, the face spatial position of pedestrian is positioned;According to face spatial position, pickup area is adjusted to human face region, acquires clear face image.Present invention utilizes the spatial positions of heartbeat signal, quickly calculate the spatial position of face, and locating human face region, capture high-resolution human face image can improve the discrimination and practicability of remote human face identifying system rapidly.
Description
Technical field
The invention belongs to living things feature recognition field more particularly to a kind of remote human face identification sides of combination heartbeat signal
Method, device and system.
Background technique
Recognition of face refers to a kind of technology that authentication is carried out using the invariant feature of face.Face is as a kind of allusion quotation
The biological characteristic of type, with the uniqueness different from other people and the stability remained unchanged in the regular period.Compared to tradition
Identity identifying method (identity card/passport/key/password etc.), biological characteristic will not be lost, be not easy to forge and palm off, at any time may be used
With being ideal identity authentication carrier.
Recognition of face simultaneously is a kind of no invasive, living things feature recognition mode conveniently, friendly.It is according to camera
Distance to user can be classified as short distance recognition of face and remote human face identification technology.Short distance recognition of face generally needs
User cooperates, and remote human face identification technology does not need the cooperation of object, object will not be made to discover, and is very suitable to emphasis scene
Monitoring application, can be used for:
Access control: white list personage enters, automatic opening entrance.
Sensitive objects identification: dangerous person (such as terrorist or criminal) enters monitoring area, auto-alarm-signal keying device.
Region control: personage, which enters, does not obtain permission region, automatic alarm.
Logout: automatic capture enters the facial image of some region of whole personages, is registered and is recorded.
Market analysis: in record market the consumption track of crowd, analyzes its behavioral characteristic.
To sum up, remote human face identification technology suffers from wide application prospect in terms of business, security protection and national defence.But no
It is same as in short distance recognition of face, camera can easily capture high-resolution facial image, and remote human face identification needs
Extensive area is monitored, large-range monitoring image is selected, is only capable of obtaining the facial image of low resolution, but identify face biological characteristic
High-resolution facial image is needed, the demand of subsequent recognition of face and authentication is unable to satisfy.If to meet face knowledge
Other high-resolution requires entire monitoring area, then equipment cost is unbearable, and there is also a large amount of wastings of resources.It is existing
Remote human face identification technology remote human face identification scene in, mobile pedestrian and lesser pedestrian image do not ensure that but
Clear face image is exported, certain influence will cause on the accuracy of identification in this way, how to obtain can be used for reliable recognition
Clear face image is to realize the critical issue of remote human face identification.Another aspect remote human face identifying system needs to supervise entrance
People's quick response in region is controlled, monitoring area will appear multiple targets simultaneously, and target may fast move, even across monitoring
Region, how quickly to position and capture human face region is also existing remote human face identification technology problem to be solved.
Summary of the invention
The purpose of the present invention is to provide a kind of remote human face recognition methods of combination heartbeat signal, device and it is
System, it is intended to solve to cannot be guaranteed output clear face image in remote human face identification scene in existing remote human face identification technology
The problem of, and the problem of cannot quickly position and capture human face region.
The object of the present invention is achieved like this, a kind of remote human face recognition methods of combination heartbeat signal, is used for multiple spot
The remote human face of active vision system identifies, which is characterized in that described method includes following steps:
The image in monitoring area is acquired, pedestrian image is extracted from acquired image and determines pedestrian spatial position;
According to pedestrian spatial position, the spatial position of pedestrian's heartbeat signal is obtained using light vibration imaging technique;
According to the natural place relationship of heartbeat signal and face, the face spatial position of pedestrian is positioned;
According to face spatial position, pickup area is adjusted to human face region, acquires clear face image.
Preferably, described to extract pedestrian image from acquired image and determine pedestrian spatial position, including following step
It is rapid:
Segment in sliding window is extracted using multi-scale sliding window mouth method to image is collected, parses the direction ladder of segment in sliding window
Histogram feature is spent, pedestrian detection window is obtained using support vector machines analysis directions histogram of gradients feature, extracts pedestrian detection
Pedestrian image in window, and obtain the spatial position of pedestrian.
Preferably, the spatial position that pedestrian's heartbeat signal is obtained using light vibration imaging technique, is specifically included following
Step:
According to pedestrian spatial position, pedestrian is irradiated using modulated structure light, structure light is after reflection by position sensing
Detector array receives, and carries out the vibration information that Fourier transformation exports pedestrian to signal is received, from obtained vibration information
In extract the spatial position of heartbeat signal.
Preferably, the natural place relationship according to heartbeat signal and face positions the face spatial position of pedestrian, tool
Body the following steps are included:
The proportionate relationship of pedestrian and pedestrian image are obtained according to pedestrian image, proportionally relationship and heartbeat signal and face
Natural place relationship, calculate in image and be moved to distance required for face from heartbeat signal, thus in conjunction with heartbeat signal
Spatial position determine face spatial position.
It is preferably, described to adjust pickup area according to face spatial position to human face region, acquire clear face image,
Specifically includes the following steps:
According to face spatial position, pass through the face spatial position after 0.2~0.5s of Kalman prediction pedestrian, adjustment
Behind man face image acquiring area to prediction face spatial position, the clear face image of pedestrian is obtained, and store.
Preferably, in conjunction with the remote human face recognition methods of heartbeat signal further include:
According to facial image is collected, facial image is shear off, is transmitted to recognition of face device, is completed to pedestrian's face
Identification and authentication.
Another object of the present invention is to provide a kind of remote human face identification devices of combination heartbeat signal, are used for multiple spot master
The remote human face identification of dynamic vision system, which is characterized in that described device includes:
Pedestrian position acquisition unit, acquire monitoring area in image, from acquired image extract pedestrian image and
Determine pedestrian spatial position;
Heartbeat signal sension unit obtains pedestrian's heartbeat signal using light vibration imaging technique according to pedestrian spatial position
Spatial position;
Face coordinate setting unit positions the face space of pedestrian according to the natural place relationship of heartbeat signal and face
Position;
Man face image acquiring unit adjusts pickup area to human face region, acquires clear face according to face spatial position
Image.
Preferably, the pedestrian position acquisition unit includes more than one wide field's camera and pedestrian image processing mould
Block, wide field's camera acquire pedestrian image for detecting and tracking target pedestrian, the pedestrian image processing module
Segment in sliding window is extracted using multi-scale sliding window mouth method to image is collected, parses the histograms of oriented gradients of segment in sliding window
Feature obtains pedestrian detection window using support vector machines analysis directions histogram of gradients feature, extracts the row in pedestrian detection window
People's image, and obtain the spatial position of pedestrian.
Preferably, the heartbeat signal sension unit includes: light vibration image-forming module, for perceiving the small of heartbeat generation
Displacement obtains the spatial position coordinate of target line people heartbeat signal, and the light vibration image-forming module includes: light source, position sensing
Detector array, signal processing circuit and microcontroller, the light source are described for generating modulated structure light irradiation pedestrian
Position-Sensitive Detector array is used to receive the echo-signal of structure light irradiation pedestrian, and the signal processing circuit is used for position
The signal that sensitive detector array receives is filtered noise reduction process, and the microcontroller is used to carry out in Fu reception signal
Leaf transformation exports the vibration information of pedestrian, and the spatial position of heartbeat signal is extracted from obtained vibration information.
Preferably, the face coordinate setting unit includes Face detection module, and the Face detection module is according to pedestrian
Image obtains the proportionate relationship of pedestrian and pedestrian image, proportionally the natural place relationship of relationship and heartbeat signal and face,
It calculates in image and is moved to distance required for face from heartbeat signal, so that the spatial position in conjunction with heartbeat signal determines people
Face spatial position.
Preferably, the man face image acquiring unit includes face prediction module, more than one narrow visual field camera and
With the holder of narrow visual field camera pairing, the face location prediction module is used to pass through Kalman prediction pedestrian
Face spatial position after 0.2~0.5s, the narrow visual field camera are mounted on the holder of pairing, according to prediction face
Spatial position, by narrow visual field camera shooting angle and direction described in the cradle head control, alignment focuses human face region, acquisition
Clear face image.
Preferably, the remote human face identification device of the combination heartbeat signal further includes that facial image cuts module and face
Identifier, the facial image cut module and are used to be sheared and be sent to the recognition of face to collecting facial image
Device, the recognition of face device are used to identify face characteristic, completion pedestrian using convolutional neural networks to the facial image sheared
Recognition of face and authentication.
Another object of the present invention is to provide a kind of, and the remote human face comprising the above-mentioned combination heartbeat signal of right identifies dress
The system set.
It can be seen from the above technical proposal that the space of heartbeat signal is obtained using light vibration imaging technique in the present invention
Position, according to the natural place relationship of face spatial position and heartbeat signal coordinate, face space needed for effective acquisition system
Position quickly guides holder to adjust camera to face location, and calculating process is extremely simple, and time-consuming is few, is almost not take up
Hardware resource is significantly saved and calculates consumption, and system performance is improved, and solving in the prior art cannot fast fast positioning and capture
The problem of human face region.
It cannot be protected in such a way that multi-cam has complementary functions as in remote human face identification scene in the present invention simultaneously
Card output clear face image solution to the problem, wide field's camera of low resolution are responsible for monitoring whole region, be carried out
The pedestrian detection in region, high-resolution narrow visual field camera are responsible for obtaining high definition facial image, can face to pedestrian into
The Image Acquisition of row high definition solves the problems, such as in the prior art it cannot be guaranteed that clear face image is exported, to improve
Face identification rate.
Present invention utilizes the spatial positions of heartbeat signal, quickly calculate the spatial position of face, and manipulation holder movement makes
Human face region can be reached rapidly by obtaining narrow visual field camera, captured high-resolution human face image, improved remote human face identifying system
Discrimination and practicability.
Detailed description of the invention
Fig. 1 is that the embodiment of the present invention provides the flow chart for combining the remote human face recognition methods of heartbeat signal;
Fig. 2 is the composite structural diagram of the remote human face identification device of combination heartbeat signal provided in an embodiment of the present invention;
Fig. 3 long-range heartbeat signal detection schematic diagram provided in an embodiment of the present invention;
The dual camera pictorial diagram of Fig. 4 embodiment of embodiment of the present invention offer device.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Embodiment one:
The stream for the remote human face recognition methods that the embodiment of the present invention is provided in conjunction with heartbeat signal is shown referring to Fig. 1, Fig. 1
Journey, details are as follows for this method process:
In step s101, the image in monitoring area is acquired, pedestrian image and determination are extracted from acquired image
Pedestrian spatial position, specific step include: to collecting image using multi-scale sliding window mouth in embodiments of the present invention
Method extracts segment in sliding window, parses the histograms of oriented gradients feature of segment in sliding window, utilizes support vector machines analysis directions ladder
Degree histogram feature obtains pedestrian detection window, extracts the pedestrian image in pedestrian detection window, and obtain the spatial position of pedestrian;
In step s 102, according to pedestrian spatial position, the sky of pedestrian's heartbeat signal is obtained using light vibration imaging technique
Between position, specific step includes: to be shone using modulated structure light according to pedestrian spatial position in embodiments of the present invention
Pedestrian is penetrated, structure light carries out Fourier transformation output to signal is received after reflection by Position-Sensitive Detector array received
The vibration information of pedestrian extracts the spatial position of heartbeat signal from obtained vibration information;
In step s 103, according to the natural place relationship of heartbeat signal and face, the face spatial position of pedestrian is positioned,
Its specific step includes: that the proportionate relationship of pedestrian and pedestrian image are obtained according to pedestrian image in embodiments of the present invention, is pressed
According to the natural place relationship of proportionate relationship and heartbeat signal and face, calculates in image and be moved to needed for face from heartbeat signal
The distance wanted, so that the spatial position in conjunction with heartbeat signal determines face spatial position;
In step S104, according to face spatial position, pickup area is adjusted to human face region, acquires clear face figure
Picture, specific step include: to pass through Kalman prediction pedestrian according to face spatial position in embodiments of the present invention
Face spatial position after 0.2~0.5s, adjustment man face image acquiring area obtain the clear of pedestrian to after predicting face spatial position
Clear facial image, and store.
As another embodiment of the present invention, the remote human face recognition methods of the combination heartbeat signal further includes following step
It is rapid:
According to facial image is collected, facial image is shear off, is transmitted to recognition of face device, is completed to pedestrian's face
Identification and authentication.
Embodiment two:
Referring to fig. 2, the composition knot of the remote human face identification device of the combination heartbeat signal provided Fig. 2 shows embodiment
Structure, only parts related to embodiments of the present invention are shown.
This combines the remote human face identification device of heartbeat signal that can be operate in software unit in each application system, hard
Part unit or software and hardware unit.
It includes pedestrian position acquisition unit 201, heartbeat signal perception that this, which combines the remote human face identification device of heartbeat signal,
Unit 202, face coordinate setting unit 203 and man face image acquiring unit 204.Wherein, the concrete function of each unit is as follows:
Pedestrian position acquisition unit 201 acquires the image in monitoring area, pedestrian image is extracted from acquired image
With determining pedestrian spatial position, specific device includes: wide field's camera 2011 and pedestrian's figure in embodiments of the present invention
As processing module 2012, wide field's camera 2011 acquires pedestrian image for detecting and tracking target pedestrian, described
Pedestrian image processing module 2012 parses in sliding window to image is collected using segment in multi-scale sliding window mouth method extraction sliding window
The histograms of oriented gradients feature of segment obtains pedestrian detection window using support vector machines analysis directions histogram of gradients feature,
The pedestrian image in pedestrian detection window is extracted, and obtains the spatial position of pedestrian;
Heartbeat signal sension unit 202 obtains pedestrian's heartbeat using light vibration imaging technique and believes according to pedestrian spatial position
Number spatial position, specific device includes: light vibration image-forming module 2021 in embodiments of the present invention, for perceiving heartbeat
The micro-displacement of generation obtains the spatial position coordinate of target line people heartbeat signal, referring to light vibration image-forming module described in Fig. 3
2021 include: light source 301, Position-Sensitive Detector array 302, signal processing circuit 303 and microcontroller 304, referring to Fig. 3,
The light source 301 is for generating modulated structure light irradiation pedestrian, and the Position-Sensitive Detector array 302 is for receiving knot
Structure light irradiates the echo-signal of pedestrian, what the signal processing circuit 303 was received for location sensitive detector array 302
Signal is filtered noise reduction process, and the microcontroller 304 is used for the vibration to signal progress Fourier transformation output pedestrian is received
Information is moved, and extracts the spatial position of heartbeat signal from obtained vibration information;
Face coordinate setting unit 203, according to the natural place relationship of heartbeat signal and face, the face for positioning pedestrian is empty
Between position, specific device includes: Face detection module 2031 in embodiments of the present invention, the Face detection module 2031
The proportionate relationship of pedestrian and pedestrian image are obtained according to pedestrian image, proportionally the natural position of relationship and heartbeat signal and face
Relationship is set, calculates in image and is moved to distance required for face from heartbeat signal, thus in conjunction with the space bit of heartbeat signal
Set determining face spatial position.
Man face image acquiring unit 204 adjusts pickup area to human face region, acquisition is clear according to face spatial position
Facial image, specific device include: face location prediction module 2041, narrow visual field camera in embodiments of the present invention
2042 and the holder 2043 with narrow visual field camera pairing, the face location prediction module 2041 is for passing through Kalman
Face spatial position after 0.2~0.5s of filter forecasting pedestrian, the narrow visual field camera 2042 are mounted on the cloud of pairing
On platform 2043, according to prediction face spatial position, 2042 shooting angle of narrow visual field camera is controlled by the holder 2043
Degree and direction, alignment focus human face region, acquire clear face image.
Further, the remote human face identification device of the combination heartbeat signal further includes that facial image cuts module 205
With recognition of face device 206, the facial image cuts module 205 and is used to be sheared and be sent to institute to collecting facial image
Recognition of face device 206 is stated, the recognition of face device 206 is used to identify people using convolutional neural networks to the facial image sheared
Face feature completes pedestrian's recognition of face and authentication.
In the present embodiment, the recognition of face device 206 is including but not limited to using open source identification software
SeetaFaceEngine completes recognition of face, and one 9 layers of convolutional neural networks (CNN) is used to identify face characteristic, In
Reach 97.1% precision on internal authority recognition of face open test collection (Labeled Faces in the Wild, LFW).
In embodiments of the present invention, present apparatus working principle are as follows: first using wide field's camera to monitoring area pedestrian
It is detected and is tracked, then by light vibration imaging technique detecting pedestrian heartbeat signal, and obtain the space of its heartbeat signal
Position obtains the spatial position of pedestrian's face by simple computation according to the natural place relationship of heartbeat signal and face, according to
This adjusts narrow visual field camera, it is made quickly to reach human face region, acquires the clear face image with enough resolution ratio.It needs
What is illustrated is that the natural place relationship of heartbeat signal and face refers to the distance relation of heart to vertical direction human face center, body
The human body face center of high 170cm is normally at 30~40cm of heart vertical direction or so.
The remote human face identification device of combination heartbeat signal provided in this embodiment can be used in aforementioned corresponding combination
The remote human face recognition methods of heartbeat signal, details referring to above-mentioned combination heartbeat signal remote human face recognition methods embodiment one
Associated description, no longer Ao Shu herein.
As another preferred embodiment of the invention, Fig. 4 illustrates the dual camera pictorial diagram of the present embodiment device, configuration
1 wide field's camera and 1 narrow visual field camera.Using dual camera as solution, the wide field of low resolution
Camera is responsible for monitoring whole region, carries out the pedestrian detection in region.High-resolution narrow visual field camera is responsible for obtaining high definition
Facial image.After device obtains the face spatial position of current pedestrian, holder adjusts rotation, and narrow visual field camera is adjusted rapidly
To face location.The present invention can also be preferably configured multiple wide or narrow visual field cameras according to scene demand.
It will be appreciated by those skilled in the art that only logically being divided for each unit included by above-mentioned apparatus
, but be not limited to the above division, as long as corresponding functions can be realized;In addition, the specific name of each functional unit
Title also simply facilitates mutual differentiation, the protection scope being not intended to restrict the invention.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvement, replacement and variation can also be made.These are improved, replacement and variation are not being departed from by subsidiary right
It is required that and its under the premise of the range of equivalent technologies, also should be regarded as protection scope of the present invention.
Claims (11)
1. a kind of remote human face recognition methods of combination heartbeat signal, the remote human face for multiple spot active vision system is identified,
It is characterized in that, described method includes following steps:
The image in monitoring area is acquired, pedestrian image is extracted from acquired image and determines pedestrian spatial position;
According to pedestrian spatial position, the spatial position of pedestrian's heartbeat signal is obtained using light vibration imaging technique;
The spatial position that pedestrian's heartbeat signal is obtained using light vibration imaging technique, specifically includes the following steps:
According to pedestrian spatial position, pedestrian is irradiated using modulated structure light, structure light is detected by position sensing after reflection
Device array received, and the vibration information that Fourier transformation exports pedestrian is carried out to signal is received, it is mentioned from obtained vibration information
Take out the spatial position of heartbeat signal;
According to the natural place relationship of heartbeat signal and face, the face spatial position of pedestrian is positioned;
According to face spatial position, pickup area is adjusted to human face region, acquires clear face image.
2. combining the remote human face recognition methods of heartbeat signal as described in claim 1, which is characterized in that described from collecting
Image in extract pedestrian image and determine pedestrian spatial position, comprising the following steps:
Segment in sliding window is extracted using multi-scale sliding window mouth method to image is collected, the direction gradient for parsing segment in sliding window is straight
Square figure feature obtains pedestrian detection window using support vector machines analysis directions histogram of gradients feature, extracts in pedestrian detection window
Pedestrian image, and obtain the spatial position of pedestrian.
3. combining the remote human face recognition methods of heartbeat signal as described in claim 1, which is characterized in that described according to heartbeat
The natural place relationship of signal and face positions the face spatial position of pedestrian, specifically includes the following steps:
The proportionate relationship of pedestrian and pedestrian image are obtained according to pedestrian image, proportionally the day of relationship and heartbeat signal and face
Right positional relationship calculates in image and is moved to distance required for face from heartbeat signal, thus in conjunction with the sky of heartbeat signal
Between position determine face spatial position.
4. combining the remote human face recognition methods of heartbeat signal as described in claim 1, which is characterized in that described according to face
Spatial position, adjustment pickup area to human face region acquire clear face image, specifically includes the following steps:
Face is adjusted by the face spatial position after 0.2~0.5s of Kalman prediction pedestrian according to face spatial position
Behind image acquisition areas to prediction face spatial position, the clear face image of pedestrian is obtained, and store.
5. such as the remote human face recognition methods of the described in any item combination heartbeat signals of Claims 1 to 4, which is characterized in that institute
State method further include:
According to facial image is collected, facial image is shear off, is transmitted to recognition of face device, is completed to pedestrian's recognition of face
And authentication.
6. a kind of remote human face identification device of combination heartbeat signal, the remote human face for multiple spot active vision system is identified,
It is characterized in that, described device includes:
Pedestrian position acquisition unit acquires the image in monitoring area, and pedestrian image and determination are extracted from acquired image
Pedestrian spatial position;
Heartbeat signal sension unit obtains the sky of pedestrian's heartbeat signal using light vibration imaging technique according to pedestrian spatial position
Between position;
The heartbeat signal sension unit includes: light vibration image-forming module, for perceiving the micro-displacement of heartbeat generation, obtains mesh
Mark pedestrian's heartbeat signal spatial position coordinate, the light vibration image-forming module include: light source, Position-Sensitive Detector array,
Signal processing circuit and microcontroller, the light source are visited for generating modulated structure light irradiation pedestrian, the position sensing
The echo-signal that device array is used to receive structure light irradiation pedestrian is surveyed, the signal processing circuit is used for location sensitive detector
Array received to signal be filtered noise reduction process, the microcontroller is used to carry out Fourier transformation output to receiving signal
The vibration information of pedestrian, and extract from obtained vibration information the spatial position of heartbeat signal;
Face coordinate setting unit positions the face spatial position of pedestrian according to the natural place relationship of heartbeat signal and face;
Man face image acquiring unit adjusts pickup area to human face region, acquires clear face figure according to face spatial position
Picture.
7. combining the remote human face identification device of heartbeat signal as claimed in claim 6, which is characterized in that the pedestrian position
Acquisition unit includes more than one wide field's camera and pedestrian image processing module, wide field's camera for detecting and
Target pedestrian is tracked, and acquires pedestrian image, the pedestrian image processing module uses multi-scale sliding window to image is collected
Mouth method extracts segment in sliding window, parses the histograms of oriented gradients feature of segment in sliding window, utilizes support vector machines analysis directions
Histogram of gradients feature obtains pedestrian detection window, extracts the pedestrian image in pedestrian detection window, and obtain the spatial position of pedestrian.
8. combining the remote human face identification device of heartbeat signal as claimed in claim 6, which is characterized in that the face coordinate
Positioning unit includes Face detection module, and the Face detection module obtains the ratio of pedestrian and pedestrian image according to pedestrian image
Relationship, proportionally the natural place relationship of relationship and heartbeat signal and face, calculates in image and is moved to from heartbeat signal
Distance required for face, so that the spatial position in conjunction with heartbeat signal determines face spatial position.
9. combining the remote human face identification device of heartbeat signal as claimed in claim 6, which is characterized in that the facial image
Acquisition unit includes face prediction module, more than one narrow visual field camera and the cloud with narrow visual field camera pairing
Platform, the face location prediction module are used for through the face spatial position after 0.2~0.5s of Kalman prediction pedestrian, institute
It states narrow visual field camera to be mounted on the holder of pairing, according to prediction face spatial position, passes through the cradle head control institute
Narrow visual field camera shooting angle and direction are stated, alignment focuses human face region, acquires clear face image.
10. combining the remote human face identification device of heartbeat signal as claimed in claim 6, which is characterized in that device further includes
Facial image cuts module and recognition of face device, and the facial image cuts module and is used to shear to collecting facial image
And it is sent to the recognition of face device, the recognition of face device is used to know the facial image sheared using convolutional neural networks
Other face characteristic completes pedestrian's recognition of face and authentication.
11. a kind of system of the remote human face identification device of the combination heartbeat signal comprising any one of claim 6~10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710069368.7A CN106897678B (en) | 2017-02-08 | 2017-02-08 | A kind of remote human face recognition methods of combination heartbeat signal, device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710069368.7A CN106897678B (en) | 2017-02-08 | 2017-02-08 | A kind of remote human face recognition methods of combination heartbeat signal, device and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106897678A CN106897678A (en) | 2017-06-27 |
CN106897678B true CN106897678B (en) | 2019-11-12 |
Family
ID=59199059
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710069368.7A Active CN106897678B (en) | 2017-02-08 | 2017-02-08 | A kind of remote human face recognition methods of combination heartbeat signal, device and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106897678B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107633244A (en) * | 2017-11-13 | 2018-01-26 | 姜茂清 | Human body direct picture harvester, the image capturing system comprising it and its application |
CN110321756A (en) * | 2018-03-28 | 2019-10-11 | 北京语智科技有限公司 | In vivo detection system and method |
CN109448026A (en) * | 2018-11-16 | 2019-03-08 | 南京甄视智能科技有限公司 | Passenger flow statistical method and system based on head and shoulder detection |
CN109754602A (en) * | 2019-01-15 | 2019-05-14 | 珠海格力电器股份有限公司 | The method and apparatus of the anti-erroneous judgement of pedestrian running red light |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100347721C (en) * | 2006-06-29 | 2007-11-07 | 南京大学 | Face setting method based on structured light |
CN101216885A (en) * | 2008-01-04 | 2008-07-09 | 中山大学 | Passerby face detection and tracing algorithm based on video |
JP6349075B2 (en) * | 2013-11-22 | 2018-06-27 | 三星電子株式会社Samsung Electronics Co.,Ltd. | Heart rate measuring device and heart rate measuring method |
CN103761514B (en) * | 2014-01-26 | 2017-08-29 | 公安部第三研究所 | The system and method for recognition of face is realized based on wide-angle gunlock and many ball machines |
-
2017
- 2017-02-08 CN CN201710069368.7A patent/CN106897678B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN106897678A (en) | 2017-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10672140B2 (en) | Video monitoring method and video monitoring system | |
CN106897678B (en) | A kind of remote human face recognition methods of combination heartbeat signal, device and system | |
CN107093171B (en) | Image processing method, device and system | |
CN104992075B (en) | A kind of multi-source information correlating method and device based on big data | |
KR101172747B1 (en) | Camera tracking monitoring system and method using thermal image coordinates | |
CN103106393B (en) | A kind of embedded human face identification intelligent identity authorization system based on robot platform | |
CN105631515B (en) | People flow counting system | |
CN105279496B (en) | A kind of method and apparatus of recognition of face | |
JP2020524928A (en) | Method of providing a device with an information element that allows identifying an unauthorized user in a restricted area | |
Stahlschmidt et al. | Applications for a people detection and tracking algorithm using a time-of-flight camera | |
US10997474B2 (en) | Apparatus and method for person detection, tracking, and identification utilizing wireless signals and images | |
KR100885418B1 (en) | System and method for detecting and tracking people from overhead camera video | |
KR101579275B1 (en) | Security system using real-time monitoring with location-trace for dangerous-object | |
JP5937763B2 (en) | Authentication method for 3D entity image acquisition | |
Yoon et al. | Tracking System for mobile user Based on CCTV | |
KR20190047218A (en) | Method and apparatus of providing traffic information, and computer program for executing the method. | |
CN108540748A (en) | Monitor video and the associated method, apparatus of electronic device identification and system | |
CN109344776A (en) | Data processing method | |
CN110026982A (en) | Robot servo system | |
KR101829274B1 (en) | System and apparatus for image security using beacon | |
CN111277789A (en) | Video-based community security method and device, electronic equipment and storage medium | |
CN110991316B (en) | Method for automatically acquiring shape and identity information applied to open environment | |
CN111277745A (en) | Target person tracking method and device, electronic equipment and readable storage medium | |
CN109740464A (en) | The identification follower method of target | |
CN111078804A (en) | Information association method, system and computer terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |