CN105354552B - A kind of on-line monitoring system and method based on recognition of face and Expression analysis - Google Patents
A kind of on-line monitoring system and method based on recognition of face and Expression analysis Download PDFInfo
- Publication number
- CN105354552B CN105354552B CN201510759205.2A CN201510759205A CN105354552B CN 105354552 B CN105354552 B CN 105354552B CN 201510759205 A CN201510759205 A CN 201510759205A CN 105354552 B CN105354552 B CN 105354552B
- Authority
- CN
- China
- Prior art keywords
- image
- security protection
- module
- personnel
- facial image
- 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
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of on-line monitoring system and method based on recognition of face and Expression analysis, system includes sequentially connected image capture module, data analysis center and security protection control centre；Image capture module is for being acquired the facial image in security protection region, data analysis center is used to carry out face and Expression analysis to acquired image, the result that security protection control centre is used to be analyzed according to data analysis center carries out security protection scheduling, it is ensured that the safety in security protection region.The present invention provides a kind of on-line monitoring system and method based on recognition of face and Expression analysis, can by facial image to the personnel in security protection region whether be it is illegal enter determine, and by taking security protection Operation Measures；Expression analysis can also be carried out to legal entrance personnel simultaneously, it be determined, and take security protection Operation Measures when there are security risk with the presence or absence of security risk, guarantee the safety and stablization in security protection region.
Description
Technical field
The present invention relates to a kind of on-line monitoring system and method based on recognition of face and Expression analysis.
Background technique
Safety and protection system refers to using technological means such as precautions by persons, equipment and techniques have detection, delay, reaction etc. basic
Function has great work to maintaining public order to stablize for preventing, preventing criminal offence and great public order incident
With.
Existing security system is both provided with access control equipment mostly, and access control equipment be mostly based on fingerprint detection,
In living community, there is no be monitored Intra-cell and the means of security protection other than gate inhibition's detection, it is likely that has external
Personnel follow Intra-cell resident, and as resident enters cell in opening time, there is some potential safety problemss.
There are some very important facilities, such as power supply unit in living community, for net equipment etc., if be considered
It destroys, it will seriously affect quality of life, under normal circumstances, external staff hardly enters community, and the resident inside community is not yet
It may go to destroy these facilities, but be not excluded for after some special circumstances, such as community internal members excessive drinking occur, just have
It may be in unconscious middle these equipment of destruction.
In life, expression tends to reaction heart condition and physiological status；And people is in different expressions, it is facial each
Partial profile and shape is also different, such as in happiness, and eyebrow and the corners of the mouth can all have corresponding variation, after excessive drinking,
From eye expression it can also be seen that corresponding change.
Therefore, security system deployment is carried out in conjunction with image and Expression analysis and implements to carry out security monitor to keeping the peace
Stabilization has huge benefit.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of based on recognition of face and Expression analysis
Line monitoring system and method, can by facial image to the personnel in security protection region whether be it is illegal enter determine, and
By taking security protection Operation Measures；Expression analysis can also be carried out to legal entrance personnel simultaneously, security risk whether there is to it
Determined, and take security protection Operation Measures when there are security risk, guarantees the safety and stablization in security protection region.
The purpose of the present invention is achieved through the following technical solutions: it is a kind of based on recognition of face and Expression analysis
Line monitoring system, including sequentially connected image capture module, data analysis center and security protection control centre；
The image capture module is for being acquired the facial image in security protection region；
The data analysis center includes image analysis module, Expression analysis module and memory module；Image analysis mould
Block and Expression analysis module are connect with memory module respectively；
The image analysis module judges that the corresponding personnel identity of image is for analyzing acquired image
The no permission having into security protection region；
The Expression analysis module is used to carry out facial Expression Analysis to acquired image, obtains corresponding dangerous ginseng
Number；
The memory module is used to store the facial image of the personnel with security protection region access entitlements, and the image is right
Unified shooting is carried out when answering personnel's expression normal；
The result that the security protection control centre is used to be analyzed according to data analysis center carries out security protection scheduling, it is ensured that
Safety in security protection region.
The image capture module includes distributed multiple cameras, institute in image pre-processing module and security protection region
The image pre-processing module stated obtains and image size one in memory for pre-processing to camera acquired image
The facial image of cause.
A kind of implementation method of on-line monitoring system based on recognition of face and Expression analysis, including following step
It is rapid:
S1. man face image acquiring is carried out to the mobile personnel in security system region using image capture module, and will adopted
The real-time data transmission collected is to data analysis center；
S2. data analysis center carries out image analysis to current acquired image, and judging whether can be in memory module
In find facial image corresponding with current acquired image:
(1) facial image corresponding with current acquired image can be found in a storage module, and counterpart personnel has
It is legal entrance into the permission in security protection region, extracts the corresponding facial image of the memory module personnel, and go to step
S3；
(2) facial image corresponding with current acquired image can not be found in a storage module, and counterpart personnel is not
With the permission for entering security protection region, enter to be illegal, go to step S5；
S3. data analysis center carries out Expression analysis to current collected facial image, obtains corresponding risk parameters；
S4. data analysis center judges whether risk parameters are less than risk parameters threshold value:
(1) if risk parameters are less than risk parameters threshold value, expression is normal, and security risk is not present, this analysis terminates,
Image capture module acquisition next facial image of transmission is waited, and carries out the processing of step S2 ~ S5 to it；
(2) if risk parameters are not less than risk parameters threshold value, expression is abnormal, and go to step S5；
S5. security protection control centre takes corresponding security protection Operation Measures, it is ensured that the safety in security protection region, this analysis knot
Beam waits image capture module acquisition next facial image of transmission, and carries out the processing of step S2 ~ S5 to it.
The step S1 includes following sub-step:
S11. the camera in security protection region carries out Image Acquisition to the personnel of process in real time, and it is real-time to collect image
It is transferred to image pre-processing module；
S12. image pre-processing module pre-processes acquired image, obtains facial image, and adjusts and to obtain
Facial image keeps it in the same size with image in memory；
S13. by pretreated facial image real-time Transmission to data analysis center.
The step S3 includes following sub-step:
S31. it defines current collected facial image and establishes x-o- using the center of image A as coordinate origin o for image A
Y rectangular coordinate system；
S32. defining the facial image extracted from memory module is image B, by image B placement Chong Die with image A；
S33. for the point M (any point on face) on face, its corresponding pixel coordinate in image A is found out
A1(x1, y1), and find out its corresponding pixel coordinate B1(x2, y2 in image B)；
S34. A1 is found out in x-o-y rectangular coordinate system at a distance from B1；
S35. for each point on face, S33 ~ S34 is repeated, the point corresponding coordinate in image A and image B is acquired
Distance is completed until the corresponding coordinate distance of all the points solves；
S36. the corresponding coordinate distance of all the points is summed, obtains risk parameters.
Further, during carrying out asking a to parameter, it may be considered that corresponding to eyebrow, mouth and eyes on face
All the points carry out specially treated: carrying out in summation process, eyebrow, mouth and the corresponding all the points of eyes are schemed at two
Corresponding coordinate distance amplifies 10 times (multiplied by 10) as in, then participates in summation and obtain risk parameters.
Security protection control centre takes corresponding security protection Operation Measures in step S5, it is ensured that the safety in security protection region, be divided into
Lower two kinds of situations:
(1) analysis according to data analysis center to image, do not have into security protection zone permission personnel illegally into
Fashionable, sacurity dispatching module reminds security personnel to find and ask the appearance of the personnel illegally entered；
(2) analysis according to data analysis center to expression is legal entrance and its facial image facial image in personnel
Risk parameters when being not less than threshold value, corresponding facial image is supplied to security personnel by security protection scheduling, and security personnel is reminded to carry out manually
Differentiate and confirms；Security personnel are manually determining facial image, after confirmation counterpart personnel has security risk, hold to it
Continuous monitoring.
The beneficial effects of the present invention are: (1) can by facial image to the personnel in security protection region whether be illegally into
Enter to be determined, and by taking security protection Operation Measures, ensure that the safety and stability in security protection region.
(2) Expression analysis is carried out to legal entrance personnel, it is determined with the presence or absence of security risk, and pacifies existing
Security protection Operation Measures are taken when full hidden danger, guarantee the safety and stablization in security protection region.
(3) when carrying out Expression analysis, under the same coordinate system, by normal facial image and current collected face
The summation of corresponding pixel points distance obtains parameter in image, further according to the method that parameter compares with threshold value, can Effective selection go out
The abnormal facial image of expression, to further determine whether to avoid and misdeem there are security risk by manual analysis
Additional workload caused by accidentally.
Detailed description of the invention
Fig. 1 is the functional block diagram of present system；
Fig. 2 is the method for the present invention flow chart.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawing, but protection scope of the present invention is not limited to
It is as described below.
As shown in Figure 1, a kind of on-line monitoring system based on recognition of face and Expression analysis, including sequentially connected image
Acquisition module, data analysis center and security protection control centre；
The image capture module is for being acquired the facial image in security protection region；
The data analysis center includes image analysis module, Expression analysis module and memory module；Image analysis mould
Block and Expression analysis module are connect with memory module respectively；
The image analysis module judges that the corresponding personnel identity of image is for analyzing acquired image
The no permission having into security protection region；Image analysis module may also be referred to as being face recognition module；
The Expression analysis module is used to carry out facial Expression Analysis to acquired image, obtains corresponding dangerous ginseng
Number；
The memory module is used to store the facial image of the personnel with security protection region access entitlements, and the image is right
Unified shooting is carried out when answering personnel's expression normal；
The result that the security protection control centre is used to be analyzed according to data analysis center carries out security protection scheduling, it is ensured that
Safety in security protection region.
The image capture module includes distributed multiple cameras, institute in image pre-processing module and security protection region
The image pre-processing module stated obtains and image size one in memory for pre-processing to camera acquired image
The facial image of cause.
As shown in Fig. 2, a kind of implementation method of on-line monitoring system based on recognition of face and Expression analysis, packet
Include following steps:
S1. man face image acquiring is carried out to the mobile personnel in security system region using image capture module, and will adopted
The real-time data transmission collected is to data analysis center；
S2. data analysis center carries out image analysis to current acquired image, and judging whether can be in memory module
In find facial image corresponding with current acquired image:
(1) facial image corresponding with current acquired image can be found in a storage module, and counterpart personnel has
It is legal entrance into the permission in security protection region, extracts the corresponding facial image of the memory module personnel, and go to step
S3；
(2) facial image corresponding with current acquired image can not be found in a storage module, and counterpart personnel is not
With the permission for entering security protection region, enter to be illegal, go to step S5；
S3. data analysis center carries out Expression analysis to current collected facial image, obtains corresponding risk parameters；
S4. data analysis center judges whether risk parameters are less than risk parameters threshold value:
(1) if risk parameters are less than risk parameters threshold value, expression is normal, and security risk is not present, this analysis terminates,
Image capture module acquisition next facial image of transmission is waited, and carries out the processing of step S2 ~ S5 to it；
(2) if risk parameters are not less than risk parameters threshold value, expression is abnormal, and go to step S5；
S5. security protection control centre takes corresponding security protection Operation Measures, it is ensured that the safety in security protection region, this analysis knot
Beam waits image capture module acquisition next facial image of transmission, and carries out the processing of step S2 ~ S5 to it.
The step S1 includes following sub-step:
S11. the camera in security protection region carries out Image Acquisition to the personnel of process in real time, and will collect image transmitting
To image pre-processing module；
S12. image pre-processing module pre-processes acquired image, obtains facial image, and adjusts and to obtain
Facial image keeps it in the same size with image in memory；
S13. by pretreated facial image real-time Transmission to data analysis center.
Further, for the real-time of image capture module acquisition data and transmission data, data analysis center is
The image of analysis only has one；Even if multiple distributed cameras seem imaging simultaneously, but imaged
Time fining, always has a subtle lead time, and this subtle lead time enough computer softwares or program
An image (current collected facial image) is handled；So being not in data in the medium feelings to be processed of buffer area
Condition, the image being presently processing also only have one；And it is this acquisition and processing real-time ensure that security risk and
Shi Faxian avoids the unnecessary loss of time delays bring.
The step S3 includes following sub-step:
S31. it defines current collected facial image and establishes x-o- using the center of image A as coordinate origin o for image A
Y rectangular coordinate system；
S32. defining the facial image extracted from memory module is image B, by image B placement Chong Die with image A；
S33. for the point M on face, its corresponding pixel coordinate A1(x1, y1 in image A is found out), and find out it
Corresponding pixel coordinate B1(x2, y2 in image B)；
S34. A1 is found out in x-o-y rectangular coordinate system at a distance from B1；
S35. for each point on face, S33 ~ S34 is repeated, the point corresponding coordinate in image A and image B is acquired
Distance is completed until the corresponding coordinate distance of all the points solves；
S36. the corresponding coordinate distance of all the points is summed, obtains risk parameters.
Further, during carrying out asking a to parameter, it may be considered that corresponding to eyebrow, mouth and eyes on face
All the points carry out specially treated: carrying out in summation process, eyebrow, mouth and the corresponding all the points of eyes are schemed at two
Corresponding coordinate distance amplifies 10 times (multiplied by 10) as in, then participates in summation and obtain risk parameters.
Security protection control centre takes corresponding security protection Operation Measures in step S5, it is ensured that the safety in security protection region, be divided into
Lower two kinds of situations:
(1) analysis according to data analysis center to image, do not have into security protection zone permission personnel illegally into
Fashionable, sacurity dispatching module reminds security personnel to find and ask the appearance of the personnel illegally entered；
(2) analysis according to data analysis center to expression is legal entrance and its facial image facial image in personnel
Risk parameters when being not less than threshold value, corresponding facial image is supplied to security personnel by security protection scheduling, and security personnel is reminded to carry out manually
Differentiate and confirms；Security personnel are manually determining facial image, after confirmation counterpart personnel has security risk, hold to it
Continuous monitoring.
Claims (3)
1. a kind of implementation method of the on-line monitoring system based on recognition of face and Expression analysis, the on-line monitoring system include
Sequentially connected image capture module, data analysis center and security protection control centre；
The image capture module is for being acquired the facial image in security protection region；
The data analysis center includes image analysis module, Expression analysis module and memory module；Image analysis module and
Expression analysis module is connect with memory module respectively；
The image analysis module judges whether the corresponding personnel identity of image has for analyzing acquired image
There is the permission into security protection region；
The Expression analysis module is used to carry out facial Expression Analysis to acquired image, obtains corresponding risk parameters；
The memory module is used to store the facial image of the personnel with security protection region access entitlements, and the image is in corresponding people
Member's expression carries out unified shooting when normal；
The result that the security protection control centre is used to be analyzed according to data analysis center carries out security protection scheduling, it is ensured that security protection
Safety in region；
The image capture module includes distributed multiple cameras in image pre-processing module and security protection region, described
Image pre-processing module obtains of the same size with image in memory for pre-processing to camera acquired image
Facial image；
Its implementation is characterized in that: the following steps are included:
S1. man face image acquiring is carried out to the mobile personnel in security system region using image capture module, and will collected
Real-time data transmission to data analysis center；
S2. data analysis center carries out image analysis to current acquired image, judges whether to look in a storage module
To facial image corresponding with current acquired image:
(1) facial image corresponding with current acquired image can be found in a storage module, and counterpart personnel, which has, to be entered
The permission in security protection region is legal entrance, extracts the corresponding facial image of the memory module personnel, and the S3 that gos to step；
(2) facial image corresponding with current acquired image can not be found in a storage module, and counterpart personnel does not have
Into the permission in security protection region, enter to be illegal, go to step S5；
S3. data analysis center carries out Expression analysis to current collected facial image, obtains corresponding risk parameters；
S4. data analysis center judges whether risk parameters are less than risk parameters threshold value:
(1) if risk parameters are less than risk parameters threshold value, expression is normal, and security risk is not present, this analysis terminates, and waits
Image capture module acquisition next facial image of transmission, and the processing of step S2 ~ S5 is carried out to it；
(2) if risk parameters are not less than risk parameters threshold value, expression is abnormal, and go to step S5；
S5. security protection control centre takes corresponding security protection Operation Measures, it is ensured that and the safety in security protection region, this analysis terminate, etc.
Next facial image of transmission is acquired to image capture module, and carries out the processing of step S2 ~ S5 to it；
The step S3 includes following sub-step:
S31. it defines current collected facial image and it is straight to establish x-o-y using the center of image A as coordinate origin o for image A
Angular coordinate system；
S32. defining the facial image extracted from memory module is image B, by image B placement Chong Die with image A；
S33. for the point M on face, its corresponding pixel coordinate A1(x1, y1 in image A is found out), and find out it and scheming
As corresponding pixel coordinate B1(x2, y2 in B)；
S34. A1 is found out in x-o-y rectangular coordinate system at a distance from B1；
S35. for each point on face, repeat S33 ~ S34, acquire the point in image A and image B corresponding coordinate away from
From until the corresponding coordinate distance of all the points solves completion；
S36. the corresponding coordinate distance of all the points is summed, obtains risk parameters.
2. a kind of implementation method of on-line monitoring system based on recognition of face and Expression analysis according to claim 1,
It is characterized by: the step S1 includes following sub-step:
S11. the camera in security protection region carries out Image Acquisition to the personnel of process in real time, and will collect Image Real-time Transmission
To image pre-processing module；
S12. image pre-processing module pre-processes acquired image, obtains facial image, and adjust obtained face
Image keeps it in the same size with image in memory；
S13. by pretreated facial image real-time Transmission to data analysis center.
3. a kind of implementation method of on-line monitoring system based on recognition of face and Expression analysis according to claim 1,
It is characterized by: security protection control centre takes corresponding security protection Operation Measures in step S5, it is ensured that the safety in security protection region is divided into
Following two situation:
(1) analysis according to data analysis center to image, when illegally entering without the personnel into security protection zone permission,
Sacurity dispatching module reminds security personnel to find and ask the appearance of the personnel illegally entered；
(2) analysis according to data analysis center to expression is legal entrance and the danger of its facial image facial image in personnel
When dangerous parameter is not less than threshold value, corresponding facial image is supplied to security personnel by security protection scheduling, and security personnel is reminded to carry out artificial cognition
And confirmation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510759205.2A CN105354552B (en) | 2015-11-10 | 2015-11-10 | A kind of on-line monitoring system and method based on recognition of face and Expression analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510759205.2A CN105354552B (en) | 2015-11-10 | 2015-11-10 | A kind of on-line monitoring system and method based on recognition of face and Expression analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105354552A CN105354552A (en) | 2016-02-24 |
| CN105354552B true CN105354552B (en) | 2019-02-05 |
Family
ID=55330520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510759205.2A Active CN105354552B (en) | 2015-11-10 | 2015-11-10 | A kind of on-line monitoring system and method based on recognition of face and Expression analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354552B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977617A (en) * | 2017-11-24 | 2018-05-01 | 合肥博焱智能科技有限公司 | A kind of adaptive face identification system of expression |
| CN108492404B (en) * | 2018-02-07 | 2020-10-09 | 上海灵至科技有限公司 | Face lock unlocking method and device with additional expression recognition function |
| CN109345370A (en) * | 2018-08-29 | 2019-02-15 | 中国建设银行股份有限公司 | Risk Forecast Method, device, terminal and readable medium based on recognition of face |
| CN111209769B (en) * | 2018-11-06 | 2024-03-08 | 深圳市商汤科技有限公司 | Authentication system and method, electronic device and storage medium |
| CN109584050A (en) * | 2018-12-14 | 2019-04-05 | 深圳壹账通智能科技有限公司 | Consumer's risk degree analyzing method and device based on micro- Expression Recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093603A (en) * | 2007-07-03 | 2007-12-26 | 北京智安邦科技有限公司 | Module set of intellective video monitoring device, system and monitoring method |
| CN102103617A (en) * | 2009-12-22 | 2011-06-22 | 华为终端有限公司 | Method and device for acquiring expression meanings |
| CN102970438A (en) * | 2012-11-29 | 2013-03-13 | 广东欧珀移动通信有限公司 | Automatic mobile phone alarming method and device |
| CN103647953A (en) * | 2013-12-25 | 2014-03-19 | 句容云影响软件技术开发有限公司 | Intelligent monitoring system and method |
-
2015
- 2015-11-10 CN CN201510759205.2A patent/CN105354552B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093603A (en) * | 2007-07-03 | 2007-12-26 | 北京智安邦科技有限公司 | Module set of intellective video monitoring device, system and monitoring method |
| CN102103617A (en) * | 2009-12-22 | 2011-06-22 | 华为终端有限公司 | Method and device for acquiring expression meanings |
| CN102970438A (en) * | 2012-11-29 | 2013-03-13 | 广东欧珀移动通信有限公司 | Automatic mobile phone alarming method and device |
| CN103647953A (en) * | 2013-12-25 | 2014-03-19 | 句容云影响软件技术开发有限公司 | Intelligent monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105354552A (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105335727B (en) | The identity authorization system and method analyzed based on image and body-sensing | |
| CN105354552B (en) | A kind of on-line monitoring system and method based on recognition of face and Expression analysis | |
| Jung et al. | Deepvision: Deepfakes detection using human eye blinking pattern | |
| CN110477925B (en) | Fall detection and early warning method and system for elderly people in nursing home | |
| CN103714631B (en) | ATM cash dispenser intelligent monitor system based on recognition of face | |
| CN107133564B (en) | Tooling cap detection method | |
| CN106446831A (en) | Face recognition method and device | |
| CN110795963A (en) | Monitoring method, device and equipment based on face recognition | |
| CN111797677B (en) | Face recognition living body detection method based on face iris recognition and thermal imaging technology | |
| CN105518710B (en) | Video detecting method, video detection system and computer program product | |
| CN108364374A (en) | Face access control device based on deep learning and method | |
| CN111564224A (en) | Intelligent monitoring system with health monitoring function and implementation method thereof | |
| CN111126219A (en) | Transformer substation personnel identity recognition system and method based on artificial intelligence | |
| CN111582110B (en) | Security check personnel behavior analysis method, device and equipment based on face recognition | |
| CN108416289A (en) | A kind of working at height personnel safety band wears detection device and detection method for early warning | |
| CN110472574A (en) | A kind of nonstandard method, apparatus of detection dressing and system | |
| RU2713876C1 (en) | Method and system for detecting alarm events when interacting with self-service device | |
| Alioua et al. | Eye state analysis using iris detection based on Circular Hough Transform | |
| CN113822164A (en) | Dynamic emotion recognition method and device, computer equipment and storage medium | |
| CN110070055A (en) | A kind of capital construction scene safety detecting system and method based on deep learning | |
| US20210364356A1 (en) | System and method for using artificial intelligence to enable elevated temperature detection of persons using commodity-based thermal cameras | |
| KR20090001848A (en) | Method and system monitoring facial expression | |
| CN111652185A (en) | Safety construction method, system, device and storage medium based on violation behavior recognition | |
| CN107220623A (en) | A kind of face identification method and system | |
| CN204926116U (en) | Picture system is declared in safety inspection containing video analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |