CN109918990A - A kind of real time face tracking method, equipment and computer readable storage medium - Google Patents
A kind of real time face tracking method, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109918990A CN109918990A CN201910014796.9A CN201910014796A CN109918990A CN 109918990 A CN109918990 A CN 109918990A CN 201910014796 A CN201910014796 A CN 201910014796A CN 109918990 A CN109918990 A CN 109918990A
- Authority
- CN
- China
- Prior art keywords
- face
- real time
- region
- human face
- frame
- 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
Abstract
The invention discloses a kind of real time face tracking method, equipment and computer readable storage mediums, wherein this method comprises: obtaining the frame data of human face region image；Then, in the frame data, if the confidence level of former frame is higher than preset threshold, the human face region is extended, the candidate interest region as a later frame；Subsequently, the face matrix size and coordinate of a later frame are calculated in the candidate interest region；Finally, being screened to obtain confidence level highest, the area maximum face of the human face region according to the face matrix size and coordinate.A kind of more perfect recognition of face and face tracking association schemes are realized, save processing time and resource overhead, the user experience is improved.
Description
Technical field
The present invention relates to electronic technology field more particularly to a kind of real time face tracking methods, equipment and computer-readable
Storage medium.
Background technique
In the prior art, the tracking of personnel is widely used in various security protection scenes, for example, office building doorway with
The disengaging of track personnel, tracking individuals walks about in classroom.Making rapid progress and developing with technology, people are to security protection field
The security and guard technology of scape, people require the related security and guard technology of security product higher and higher.By capturing some disclosed identity
The information of identification, such as face information finger print information, voiceprint, in the higher ranked scene of security protection, or even there are also irises to believe
Breath, Lai Zengqiang security protection grade, while being also the protection to other privacy information, such as ID card information etc..
In disclosed identity information, it is the most simple and efficient to obtain face information, that is, by face recognition technology, it is right
Face is identified, determines the identity of personnel.But in the prior art, recognition of face and face tracking are combined
Scheme is perfect not enough.
Summary of the invention
In order to solve above-mentioned technological deficiency in the prior art, the invention proposes a kind of real time face tracking methods, should
Method includes:
Obtain the frame data of human face region image；
In the frame data, if the confidence level of former frame is higher than preset threshold, the human face region is extended, as rear
The candidate interest region of one frame；
The face matrix size and coordinate of a later frame are calculated in the candidate interest region；
It is screened to obtain confidence level highest, the area most adult of the human face region according to the face matrix size and coordinate
Face.
Optionally, this method further include:
Reinspection survey operation is executed to the frame data are continuously lost.
It is optionally, described to survey operation to continuously losing the frame data and execute reinspection, comprising:
Within the scope of the frame number of Face datection, operational staff's identity determines operation.
Optionally, this method further include:
In the tracking phase of the human face region, the recognition of face calculating operation in the human face region is removed.
Optionally, this method further include:
In the tracking phase of the human face region, execute the human face region image rendering operations and the face area
The Attitude estimation in domain operates.
The invention also provides a kind of real time face tracking equipment, which includes memory, processor and is stored in institute
The computer program that can be run on memory and on the processor is stated, when the computer program is executed by the processor
It realizes:
Obtain the frame data of human face region image；
In the frame data, if the confidence level of former frame is higher than preset threshold, the human face region is extended, as rear
The candidate interest region of one frame；
The face matrix size and coordinate of a later frame are calculated in the candidate interest region；
It is screened to obtain confidence level highest, the area most adult of the human face region according to the face matrix size and coordinate
Face.
Optionally, it is realized when the computer program is executed by the processor:
Reinspection survey operation is executed to the frame data are continuously lost.
Optionally, it is realized when the computer program is executed by the processor:
Within the scope of the frame number of Face datection, operational staff's identity determines operation.
Optionally, it is realized when the computer program is executed by the processor:
In the tracking phase of the human face region, the recognition of face calculating operation in the human face region is removed；
In the tracking phase of the human face region, execute the human face region image rendering operations and the face area
The Attitude estimation in domain operates.
The invention also provides a kind of computer readable storage medium, face is stored on the computer readable storage medium
Real-time tracking program, real time face tracking program realize real time face tracking as described in any one of the above embodiments when being executed by processor
The step of method.
Implement real time face tracking method, equipment and computer readable storage medium of the invention, by obtaining people
The frame data of face area image；Then, in the frame data, if the confidence level of former frame is higher than preset threshold, institute is extended
Human face region is stated, the candidate interest region as a later frame；Subsequently, be calculated in the candidate interest region it is described after
The face matrix size and coordinate of one frame；Finally, screening to obtain the human face region according to the face matrix size and coordinate
Confidence level highest, area maximum face.A kind of more perfect recognition of face and face tracking association schemes are realized, are saved
Processing time and resource overhead, the user experience is improved.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the flow chart of face method for real time tracking first embodiment of the present invention；
Fig. 2 is the flow chart of face method for real time tracking second embodiment of the present invention；
Fig. 3 is the flow chart of face method for real time tracking 3rd embodiment of the present invention；
Fig. 4 is the flow chart of face method for real time tracking fourth embodiment of the present invention；
Fig. 5 is the flow chart of the 5th embodiment of face method for real time tracking of the present invention；
Fig. 6 is the flow chart of face method for real time tracking sixth embodiment of the present invention；
Fig. 7 is the structural block diagram of the 7th embodiment of face method for real time tracking of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
In subsequent description, it is only using the suffix for indicating such as " module ", " component " or " unit " of element
Be conducive to explanation of the invention, itself there is no a specific meaning.Therefore, " module ", " component " or " unit " can mix
Ground uses.
Embodiment one
Fig. 1 is the flow chart of face method for real time tracking first embodiment of the present invention.A kind of real time face tracking method, should
Method includes:
S1, the frame data for obtaining human face region image；
S2, in the frame data, if the confidence level of former frame be higher than preset threshold, extend the human face region, make
For the candidate interest region of a later frame；
S3, the face matrix size and coordinate that a later frame is calculated in the candidate interest region；
S4, the confidence level highest for obtaining the human face region, area are screened most according to the face matrix size and coordinate
Big face.
In the present embodiment, firstly, obtaining the frame data of human face region image；Then, in the frame data, if
The confidence level of former frame is higher than preset threshold, then extends the human face region, the candidate interest region as a later frame；Again so
Afterwards, the face matrix size and coordinate of a later frame are calculated in the candidate interest region；Finally, according to the people
Face matrix size and coordinate screen to obtain the confidence level highest of the human face region, area maximum face.
Optionally, in the present embodiment, the code of this programme is written as neon compilation source code, the remittance of ARM platform is utilized
Instruction set is compiled to accelerate；
Optionally, in the present embodiment, the head Pnet of the network structure of Pnet-Rnet-Onet is tightened, is reduced below
The calculating cost of two cascade networks Rnet, Onet；
Optionally, in the present embodiment, it when only detecting a maximum face, is improved on algorithm flow, that is,
Just the calculating that subsequent detection alternative frame is no longer carried out when network when front filters out satisfactory maximum face, to save
It saves time and resource overhead.
Optionally, the present embodiment can be applied to the embedded platforms such as armv7, armv8；
Optionally, the present embodiment can be applied to RK3288 (armv7) embedded platform, and real-time rate is up to 42 frames/second.
Optionally, in the present embodiment, this method further include:
Reinspection survey operation is executed to the frame data are continuously lost.
It is optionally, described to survey operation to continuously losing the frame data and execute reinspection, comprising:
Within the scope of the frame number of Face datection, operational staff's identity determines operation.
Optionally, in the present embodiment, this method further include:
In the tracking phase of the human face region, the recognition of face calculating operation in the human face region is removed.
Optionally, in the present embodiment, this method further include:
In the tracking phase of the human face region, execute the human face region image rendering operations and the face area
The Attitude estimation in domain operates.
The beneficial effect of the present embodiment is, by the frame data for obtaining human face region image；Then, in the frame
In data, if the confidence level of former frame is higher than preset threshold, the human face region is extended, the candidate region of interest as a later frame
Domain；Subsequently, the face matrix size and coordinate of a later frame are calculated in the candidate interest region；Finally, root
It screens to obtain confidence level highest, the area maximum face of the human face region according to the face matrix size and coordinate.It realizes
A kind of more perfect recognition of face and face tracking association schemes save processing time and resource overhead, improve user
Experience.
Embodiment two
Fig. 2 is the flow chart of face method for real time tracking second embodiment of the present invention, based on the above embodiment, the present embodiment
Provide the system installation and initialization scheme of a kind of recognition of face.
Specifically, in the present embodiment, firstly, then recognition of face accessing terminal to network, is sent out by terminal to server
The information of specific format is sent, then judges whether server receives and respond the information, if not receiving, user is prompted not connect
It connects, reconnects and verify after waiting preset time, if having received, when terminal receives server response, prompt user
It has connected, at this point, super keepe can log in management system, executes addition equipment, addition administrator and personnel's typing etc.
Operation.
It is understood that the real time face tracking scheme of above-described embodiment can establish the present embodiment through installation with
On the system of initialization, the identical technical effect of above-mentioned real time face tracking scheme equally may be implemented.
Embodiment three
Fig. 3 is the flow chart of face method for real time tracking 3rd embodiment of the present invention, based on the above embodiment, the present embodiment
Provide a kind of gated area application scheme of recognition of face.
Specifically, in the present embodiment, firstly, choosing gated area in systems, face is detected in the area, thus
Human face data is obtained, then, the matching operation of human face data is carried out from the authorization database of current access point, if unauthorized,
Then prompt denied access, accessed after please registering, then return to default interface, and if authorized, execute door open command, meanwhile,
Access record is saved and is uploaded to management system.
Likewise, it is understood that the real time face tracking scheme of above-described embodiment can establish in the present embodiment
On gate identification system, the identical technical effect of above-mentioned real time face tracking scheme equally may be implemented.
Example IV
Fig. 4 is the flow chart of face method for real time tracking fourth embodiment of the present invention, based on the above embodiment, the present embodiment
Provide a kind of application scheme of the face storage of recognition of face.
Specifically, in the present embodiment, firstly, clicking to enter login page, being stepped on by recognition of face or account number cipher
Land administrator's account can choose personal management module if logging in success, in personal management module, further select people
Member enters library module, then, facial image and perfect relevant information is captured by equipment, finally, the face for being committed to this programme enters
Library system.
Likewise, it is understood that the real time face tracking scheme of above-described embodiment can establish in the present embodiment
On face Input System, the identical technical effect of above-mentioned real time face tracking scheme equally may be implemented.
Embodiment five
Fig. 5 is the flow chart of the 5th embodiment of face method for real time tracking of the present invention, based on the above embodiment, the present embodiment
Provide a kind of application scheme of personnel's account management of recognition of face.
Specifically, in the present embodiment, firstly, log in administration page, then, select according to demand personal management module or
Person's account management module can execute increase to authorized person's information list, screening, update if selection personal management module
And delete etc. operation, thus to the information list improve and update, and if select account management module, can be to personal information
It is updated, likewise, the operations such as increase, screening, update and deletion can be executed to personal information.
Likewise, it is understood that the real time face tracking scheme of above-described embodiment can establish in the present embodiment
On personnel's account management system, the identical technical effect of above-mentioned real time face tracking scheme equally may be implemented.
Embodiment six
Fig. 6 is the flow chart of face method for real time tracking sixth embodiment of the present invention, based on the above embodiment, the present embodiment
Provide a kind of application scheme of the comprehensive application system of recognition of face.
Specifically, in the present embodiment, this comprehensive application system include personal management module, access record management module,
System management module and account management module, wherein personal management module, access record management module and account management mould
Block has been described in previous embodiment, and details are not described herein.It should be noted that in the present embodiment, increasing system log mould newly
Block, the module can execute screening and be updated to system log and be operated.
Likewise, it is understood that the real time face tracking scheme of above-described embodiment can establish in the present embodiment
On comprehensive application system, the identical technical effect of above-mentioned real time face tracking scheme equally may be implemented.
Embodiment seven
Fig. 7 is the structural block diagram of the 7th embodiment of face method for real time tracking of the present invention, based on the above embodiment, this implementation
Example provides a kind of application scheme of the access control system of recognition of face.
Specifically, in the present embodiment, including WEB management end connected to the network and recognition of face terminal, wherein people
Face identification terminal is connected with access controller, and access controller is connected with access control equipment, and the present embodiment further includes application program pipe
End is managed, for example, wechat management end etc., which can be connected with Cloud Server, to realize long-range control.
Embodiment eight
Based on the above embodiment, the invention also provides a kind of computer readable storage medium, the computer-readable storages
It is stored with real time face tracking program on medium, realizes when real time face tracking program is executed by processor such as any of the above-described institute
The step of real time face tracking method stated.
Implement real time face tracking method, equipment and computer readable storage medium of the invention, by obtaining people
The frame data of face area image；Then, in the frame data, if the confidence level of former frame is higher than preset threshold, institute is extended
Human face region is stated, the candidate interest region as a later frame；Subsequently, be calculated in the candidate interest region it is described after
The face matrix size and coordinate of one frame；Finally, screening to obtain the human face region according to the face matrix size and coordinate
Confidence level highest, area maximum face.A kind of more perfect recognition of face and face tracking association schemes are realized, are saved
Processing time and resource overhead, the user experience is improved.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, service
Device, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (10)
1. a kind of real time face tracking method, which is characterized in that the described method includes:
Obtain the frame data of human face region image；
In the frame data, if the confidence level of former frame is higher than preset threshold, the human face region is extended, as a later frame
Candidate interest region；
The face matrix size and coordinate of a later frame are calculated in the candidate interest region；
It is screened to obtain confidence level highest, the area maximum face of the human face region according to the face matrix size and coordinate.
2. real time face tracking method according to claim 1, which is characterized in that further include:
Reinspection survey operation is executed to the frame data are continuously lost.
3. real time face tracking method according to claim 2, which is characterized in that described to continuously losing the frame number
Operation is surveyed according to executing to recheck, comprising:
Within the scope of the frame number of Face datection, operational staff's identity determines operation.
4. real time face tracking method according to claim 3, which is characterized in that further include:
In the tracking phase of the human face region, the recognition of face calculating operation in the human face region is removed.
5. real time face tracking method according to claim 4, which is characterized in that further include:
In the tracking phase of the human face region, the image rendering operations and the human face region of the human face region are executed
Attitude estimation operation.
6. a kind of real time face tracking equipment, which is characterized in that the equipment includes memory, processor and is stored in described deposit
It is real when the computer program is executed by the processor on reservoir and the computer program that can run on the processor
It is existing:
Obtain the frame data of human face region image；
In the frame data, if the confidence level of former frame is higher than preset threshold, the human face region is extended, as a later frame
Candidate interest region；
The face matrix size and coordinate of a later frame are calculated in the candidate interest region；
It is screened to obtain confidence level highest, the area maximum face of the human face region according to the face matrix size and coordinate.
7. real time face tracking equipment according to claim 6, which is characterized in that the computer program is by the processing
Device is realized when executing:
Reinspection survey operation is executed to the frame data are continuously lost.
8. real time face tracking method according to claim 7, which is characterized in that the computer program is by the processing
Device is realized when executing:
Within the scope of the frame number of Face datection, operational staff's identity determines operation.
9. real time face tracking method according to claim 8, which is characterized in that the computer program is by the processing
Device is realized when executing:
In the tracking phase of the human face region, the recognition of face calculating operation in the human face region is removed；
In the tracking phase of the human face region, the image rendering operations and the human face region of the human face region are executed
Attitude estimation operation.
10. a kind of computer readable storage medium, which is characterized in that be stored with face reality on the computer readable storage medium
When trace routine, when the real time face tracking program is executed by processor realize as described in any one of claims 1 to 5
The step of real time face tracking method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910014796.9A CN109918990A (en) | 2019-01-08 | 2019-01-08 | A kind of real time face tracking method, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910014796.9A CN109918990A (en) | 2019-01-08 | 2019-01-08 | A kind of real time face tracking method, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109918990A true CN109918990A (en) | 2019-06-21 |
Family
ID=66960095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910014796.9A Pending CN109918990A (en) | 2019-01-08 | 2019-01-08 | A kind of real time face tracking method, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109918990A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198330A (en) * | 2013-03-19 | 2013-07-10 | 东南大学 | Real-time human face attitude estimation method based on depth video streaming |
| US20130272570A1 (en) * | 2012-04-16 | 2013-10-17 | Qualcomm Incorporated | Robust and efficient learning object tracker |
| CN106778585A (en) * | 2016-12-08 | 2017-05-31 | 腾讯科技（上海）有限公司 | A kind of face key point-tracking method and device |
| CN109033955A (en) * | 2018-06-15 | 2018-12-18 | 中国科学院半导体研究所 | A kind of face tracking method and system |
-
2019
- 2019-01-08 CN CN201910014796.9A patent/CN109918990A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130272570A1 (en) * | 2012-04-16 | 2013-10-17 | Qualcomm Incorporated | Robust and efficient learning object tracker |
| CN103198330A (en) * | 2013-03-19 | 2013-07-10 | 东南大学 | Real-time human face attitude estimation method based on depth video streaming |
| CN106778585A (en) * | 2016-12-08 | 2017-05-31 | 腾讯科技（上海）有限公司 | A kind of face key point-tracking method and device |
| CN109033955A (en) * | 2018-06-15 | 2018-12-18 | 中国科学院半导体研究所 | A kind of face tracking method and system |
Non-Patent Citations (1)
| Title |
|---|
| 洪汉玉: "《目标探测多谱图像复原方法与应用》", 31 October 2017 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107066983B (en) | Identity verification method and device | |
| CN112562161A (en) | Based on 5G thing networking and AI intelligent entrance guard integrated management system | |
| US20210201610A1 (en) | Methods and System for Distributed Cameras and Demographics Analysis | |
| CN105096420A (en) | Access control system and data processing method for same | |
| US20120240220A1 (en) | Method and system for controlling data access on user interfaces | |
| CN110009543A (en) | Based on artificial intelligence community access control management method and device and system and storage medium | |
| CN108269331A (en) | A kind of intelligent video big data processing system | |
| CN105261105A (en) | Safety access control method | |
| CN110135262A (en) | The anti-peeping processing method of sensitive data, device, equipment and storage medium | |
| CN106228146A (en) | A kind of subregion dynamic identifying method and system | |
| WO2016045225A1 (en) | Password fault tolerance method based on mouse behaviour | |
| CN110737728A (en) | Project domain topic analysis system based on big data analysis technology | |
| CN109918990A (en) | A kind of real time face tracking method, equipment and computer readable storage medium | |
| CN112269969A (en) | Digital content safety protection system | |
| CN110084213B (en) | Face image processing method and device | |
| US20210034671A1 (en) | Method and system for enhancing a vms by intelligently employing access control information therein | |
| US20220353259A1 (en) | Method and apparatus for multifactor authentication and authorization | |
| CN115147921A (en) | Key area target abnormal behavior detection and positioning method based on multi-domain information fusion | |
| KR102069567B1 (en) | Structured Cabling System Using Biometric Authentication | |
| CN112420146A (en) | Information security management method and system | |
| CN110309664A (en) | User's license control method and system | |
| Thomopoulos et al. | Anomaly detection with noisy and missing data using a deep learning architecture | |
| US20220130174A1 (en) | Image processing apparatus, control method, and non-transitory storage medium | |
| CN113269916B (en) | Guest prejudging analysis method and system based on face recognition | |
| CN107463812B (en) | Electronic equipment security defense method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190621 |