CN111523380A - Mask wearing condition monitoring method based on face and posture recognition - Google Patents
Mask wearing condition monitoring method based on face and posture recognition Download PDFInfo
- Publication number
- CN111523380A CN111523380A CN202010165764.1A CN202010165764A CN111523380A CN 111523380 A CN111523380 A CN 111523380A CN 202010165764 A CN202010165764 A CN 202010165764A CN 111523380 A CN111523380 A CN 111523380A
- Authority
- CN
- China
- Prior art keywords
- mask
- face
- target
- reminding
- detection
- 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.)
- Granted
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Abstract
A mask wearing condition monitoring method based on face and posture recognition comprises the following steps: step 1: acquiring a monitoring video; step 2: carrying out face detection on an image in the video data, and detecting whether a face exists in the image; and step 3: if the face exists in the image, identifying the face and performing identity authentication to determine a target identity corresponding to the face, and returning to the step 1 if all target identities cannot be determined; and 4, step 4: carrying out mask detection on the detected face area, and detecting whether a target wears a mask or not and whether the mask is worn correctly or not; and 5: if the target does not wear the mask or does not wear the mask correctly, reminding the target; step 6: and carrying out posture detection on the target, if the hand touches the mouth and nose areas, reminding the target, and otherwise, continuing to carry out posture detection. The mask wearing device can automatically monitor and remind people of wearing the mask, and correct bad habits of wearing the mask.
Description
Technical Field
The invention relates to the field of image processing and the field of target detection, in particular to a mask wearing condition monitoring method based on face and posture recognition.
Background
The mask is a common sanitary protective article, can filter air entering the mouth and the nose by simple wearing, has obvious effects on blocking dust, spray, harmful gas and the like, and is mainly used for occasions needing to filter the air in factories, construction sites, hospitals and the like. In case of epidemic diseases, wearing the mask is a good method for preventing the infectious diseases from being transmitted by droplets, and the mask needs to be worn by all people. However, some people may not wear the mask or wear the mask correctly for some reasons, and the mask protection effect is not effectively exerted due to wrong actions after wearing the mask. In response to these situations, people need to be reminded appropriately, and if the people check and remind the people manually, human resources are consumed and the infection risk is increased, so that a method capable of automatically identifying and guiding the people to wear the mask is needed.
Disclosure of Invention
In order to overcome the problems in the related art, the invention provides a mask wearing condition monitoring method based on face and posture recognition, which can monitor the mask wearing condition of people and remind people of wrong behaviors in the occasions needing to wear masks all the time.
In order to solve the technical problems, the invention provides the following technical scheme:
a mask wearing condition monitoring method based on face and posture recognition comprises the following steps:
step 1: acquiring a monitoring video;
step 2: carrying out face detection on the image in the video data, detecting whether a face exists in the image, and returning to the step 1 if the face does not exist in the image;
and step 3: if the face exists in the image, identifying the face and performing identity authentication to determine a target identity corresponding to the face, and returning to the step 1 if all target identities cannot be determined;
and 4, step 4: carrying out mask detection on the face area obtained by the detection in the step (2), and detecting whether a target wears a mask or not and whether the mask is worn correctly or not;
and 5: if the target does not wear the mask or does not wear the mask correctly, reminding the target; if the target correctly wears the mask, returning to the step 4;
step 6: and carrying out posture detection on the target, if the hand touches the mouth and nose areas, reminding the target, and otherwise, continuing to carry out posture detection.
Further, in step 2, the face detection process is as follows:
extracting image data from the video data at intervals of a certain number of frames, detecting faces in the images, and returning to the size, position and number of the face detection frames if the faces exist.
Still further, in step 3, the identity authentication process is:
and identifying the face characteristics of the face detection frame area, comparing the face characteristics with the existing face identity information database, if the similarity is greater than a certain threshold value, the identity authentication is successful, and otherwise, the authentication is failed.
Further, in the step 4, the mask detecting process includes:
and (3) detecting the mask by using a deep learning method for the face region detected in the step (1) so as to obtain the wearing condition of the target mask.
In the step 5, the reminding process is as follows:
and sending reminding information to a contact account in a target identity information base by using instant messaging software, e-mails, short messages and the like, sending different reminders according to specific reasons for reminding, reminding a target to wear the mask if the mask is not worn, reminding the correct wearing mode of the target if the mask is not worn, and reminding the target to disinfect in time if hands touch the mouth and the nose.
In step 6, the attitude detection process is as follows:
the method comprises the steps of capturing posture characteristics of the head and the hand, and acquiring the relative position between the head and the hand to confirm whether the hand touches the mouth and the nose area.
The scheme of the invention has the beneficial effects that:
1. the original monitoring system can be used without replacing hardware equipment;
2. the computer is used for automatic identification and reminding, so that the communication among personnel is reduced, and a large amount of human resources can be saved;
3. the posture recognition is combined, so that a prompt can be given when people touch the mouth and the nose unconsciously, and the infection risk of people is reduced;
4. by monitoring and alerting the target person to wear the mask correctly, the probability of spreading infectious diseases through droplets can be reduced.
Drawings
Fig. 1 is a flow chart of a mask wearing condition monitoring method based on face and posture recognition according to the present invention;
fig. 2 is a block diagram of a mask wearing condition monitoring method based on face and posture recognition according to the present invention.
Detailed Description
Embodiments of the mask wearing condition monitoring method based on face and posture recognition according to the present invention will be described in detail below with reference to the accompanying drawings, so as to make the objects, technical solutions and advantages of the present invention more apparent.
Referring to fig. 1 and 2, a mask wearing condition monitoring method based on face and posture recognition comprises the following steps:
step 1: acquiring a monitoring video;
step 2: carrying out face detection on the image in the video data, detecting whether a face exists in the image, and returning to the step 1 if the face does not exist in the image;
the face detection process comprises the following steps: extracting image data from the video data at intervals of a certain number of frames, detecting faces in the images, and returning to the size, position and number of the face detection frames if the faces exist;
and step 3: if the face exists in the image, identifying the face and performing identity authentication to determine a target identity corresponding to the face, and returning to the step 1 if all target identities cannot be determined;
the identity authentication process comprises the following steps: identifying the face characteristics of the face detection frame area, comparing the face characteristics with an existing face identity information database, if the similarity is greater than a certain threshold value, the identity authentication is successful, otherwise, the authentication is failed;
and 4, step 4: carrying out mask detection on the face area obtained by the detection in the step (2), and detecting whether a target wears a mask or not and whether the mask is worn correctly or not;
and 5: if the target does not wear the mask or does not wear the mask correctly, reminding the target; if the target correctly wears the mask, returning to the step 4;
the reminding process comprises the following steps: sending reminding information to a contact account in a target identity information base by using instant messaging software, e-mails, short messages and the like, sending different reminders according to specific reasons for reminding, reminding a target to wear a mask if the mask is not worn, reminding the target of a correct wearing mode if the mask is not worn, and reminding the target to disinfect in time if hands touch the mouth and the nose;
step 6: carrying out posture detection on the target, if the mouth and nose areas are touched by the hands, sending a prompt to the target, otherwise, continuing to carry out posture detection;
the attitude detection process comprises the following steps: the method comprises the steps of capturing posture characteristics of the head and the hand, and acquiring the relative position between the head and the hand to confirm whether the hand touches the mouth and the nose area.
By adopting the mask wearing condition monitoring based on the face and posture recognition, the technical problems that whether the mask is worn or not can only be monitored, and the wearing error and the bad habit in the mask wearing state can not be monitored in the prior art are solved, the problem that whether the mask is worn correctly or not is solved by a deep learning method, and the bad habit in the mask wearing state is solved by a method combined with the posture recognition, so that the technical problems are effectively solved.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A mask wearing condition monitoring method based on face and posture recognition is characterized by comprising the following steps:
step 1: acquiring a monitoring video;
step 2: carrying out face detection on the image in the video data, detecting whether a face exists in the image, and returning to the step 1 if the face does not exist in the image;
and step 3: if the face exists in the image, identifying the face and performing identity authentication to determine a target identity corresponding to the face, and returning to the step 1 if all target identities cannot be determined;
and 4, step 4: carrying out mask detection on the face area obtained by the detection in the step (2), and detecting whether a target wears a mask or not and whether the mask is worn correctly or not;
and 5: if the target does not wear the mask or does not wear the mask correctly, reminding the target; if the target correctly wears the mask, returning to the step 4;
step 6: and carrying out posture detection on the target, if the hand touches the mouth and nose areas, reminding the target, and otherwise, continuing to carry out posture detection.
2. The mask wearing condition monitoring method based on face and posture recognition according to claim 1, wherein in the step 2, the face detection process is as follows:
extracting image data from the video data at intervals of a certain number of frames, detecting faces in the images, and returning to the size, position and number of the face detection frames if the faces exist.
3. The mask wearing condition monitoring method based on face and posture recognition according to claim 1 or 2, wherein in the step 3, the identity authentication process is as follows:
and identifying the face characteristics of the face detection frame area, comparing the face characteristics with the existing face identity information database, if the similarity is greater than a certain threshold value, the identity authentication is successful, and otherwise, the authentication is failed.
4. The mask wearing condition monitoring method based on face and posture recognition according to claim 1 or 2, wherein in the step 4, the mask detection process is as follows:
and (3) detecting the mask by using a deep learning method for the face region detected in the step (1) so as to obtain the wearing condition of the target mask.
5. The mask wearing condition monitoring method based on face and posture recognition according to claim 1 or 2, characterized in that in the step 5, the reminding process is as follows:
and sending reminding information to a contact account in a target identity information base by using instant communication software, e-mails and short messages, sending different reminders according to specific reasons for reminding, reminding a target to wear the mask if the mask is not worn, reminding the target of a correct wearing mode if the mask is not worn, and reminding the target of timely disinfecting if hands touch the mouth and the nose.
6. The mask wearing condition monitoring method based on face and posture recognition according to claim 1 or 2, wherein in the step 6, the posture detection process is as follows:
the method comprises the steps of capturing posture characteristics of the head and the hand, and acquiring the relative position between the head and the hand to confirm whether the hand touches the mouth and the nose area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010165764.1A CN111523380B (en) | 2020-03-11 | 2020-03-11 | Mask wearing condition monitoring method based on face and gesture recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010165764.1A CN111523380B (en) | 2020-03-11 | 2020-03-11 | Mask wearing condition monitoring method based on face and gesture recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111523380A true CN111523380A (en) | 2020-08-11 |
| CN111523380B CN111523380B (en) | 2023-06-30 |
Family
ID=71910408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010165764.1A Active CN111523380B (en) | 2020-03-11 | 2020-03-11 | Mask wearing condition monitoring method based on face and gesture recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523380B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016822A (en) * | 2020-08-17 | 2020-12-01 | 广东电网有限责任公司 | Wisdom building site management system |
| CN112115803A (en) * | 2020-08-26 | 2020-12-22 | 深圳市优必选科技股份有限公司 | Mask state reminding method and device and mobile terminal |
| CN112287827A (en) * | 2020-10-29 | 2021-01-29 | 南通中铁华宇电气有限公司 | Complex environment pedestrian mask wearing detection method and system based on intelligent lamp pole |
| CN112381694A (en) * | 2020-12-09 | 2021-02-19 | 兰和科技（深圳）有限公司 | Campus public health comprehensive intelligent control system and method based on Internet |
| CN112464827A (en) * | 2020-11-30 | 2021-03-09 | 深圳集智数字科技有限公司 | Mask wearing identification method, device, equipment and storage medium |
| CN112507948A (en) * | 2020-12-18 | 2021-03-16 | Oppo广东移动通信有限公司 | Mask wearing prompting method and related device |
| CN112800885A (en) * | 2021-01-16 | 2021-05-14 | 南京众鑫云创软件科技有限公司 | Data processing system and method based on big data |
| CN112912893A (en) * | 2021-01-28 | 2021-06-04 | 深圳市锐明技术股份有限公司 | Detection method and device for wearing mask, terminal equipment and readable storage medium |
| CN113197403A (en) * | 2021-05-14 | 2021-08-03 | 广东华联云谷科技研究院有限公司 | Method capable of preventing virus infection and smart bracelet |
| CN113628760A (en) * | 2021-08-31 | 2021-11-09 | 南华大学 | Intelligent monitoring system of mobile vaccination vehicle |
| CN114255517A (en) * | 2022-03-02 | 2022-03-29 | 中运科技股份有限公司 | Scenic spot tourist behavior monitoring system and method based on artificial intelligence analysis |
| CN114415528A (en) * | 2021-12-08 | 2022-04-29 | 珠海格力电器股份有限公司 | Intelligent household equipment reminding method and device, computer equipment and storage medium |
| CN115620209A (en) * | 2022-11-15 | 2023-01-17 | 北京梦天门科技股份有限公司 | Method for generating public health video supervision result and related equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012139241A1 (en) * | 2011-04-11 | 2012-10-18 | Intel Corporation | Hand gesture recognition system |
| CN104573659A (en) * | 2015-01-09 | 2015-04-29 | 安徽清新互联信息科技有限公司 | Driver call-making and call-answering monitoring method based on svm |
| CN109271554A (en) * | 2018-09-07 | 2019-01-25 | 江西省云眼大视界科技有限公司 | A kind of intelligent video identifying system and its application |
| EP3467707A1 (en) * | 2017-10-07 | 2019-04-10 | Tata Consultancy Services Limited | System and method for deep learning based hand gesture recognition in first person view |
-
2020
- 2020-03-11 CN CN202010165764.1A patent/CN111523380B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012139241A1 (en) * | 2011-04-11 | 2012-10-18 | Intel Corporation | Hand gesture recognition system |
| CN104573659A (en) * | 2015-01-09 | 2015-04-29 | 安徽清新互联信息科技有限公司 | Driver call-making and call-answering monitoring method based on svm |
| EP3467707A1 (en) * | 2017-10-07 | 2019-04-10 | Tata Consultancy Services Limited | System and method for deep learning based hand gesture recognition in first person view |
| CN109271554A (en) * | 2018-09-07 | 2019-01-25 | 江西省云眼大视界科技有限公司 | A kind of intelligent video identifying system and its application |
Non-Patent Citations (2)
| Title |
|---|
| OSAMA MAZHAR等: "A real-time human-robot interaction framework with robust background invariant hand gesture detection" * |
| 王远大: "UCloud开放人脸口罩检测服务 借助AI算法加快疫情防控" * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016822A (en) * | 2020-08-17 | 2020-12-01 | 广东电网有限责任公司 | Wisdom building site management system |
| CN112115803A (en) * | 2020-08-26 | 2020-12-22 | 深圳市优必选科技股份有限公司 | Mask state reminding method and device and mobile terminal |
| CN112115803B (en) * | 2020-08-26 | 2023-10-13 | 深圳市优必选科技股份有限公司 | Mask state reminding method and device and mobile terminal |
| CN112287827A (en) * | 2020-10-29 | 2021-01-29 | 南通中铁华宇电气有限公司 | Complex environment pedestrian mask wearing detection method and system based on intelligent lamp pole |
| CN112464827A (en) * | 2020-11-30 | 2021-03-09 | 深圳集智数字科技有限公司 | Mask wearing identification method, device, equipment and storage medium |
| CN112381694B (en) * | 2020-12-09 | 2021-06-22 | 兰和科技（深圳）有限公司 | Campus public health comprehensive intelligent control system and method based on Internet |
| CN112381694A (en) * | 2020-12-09 | 2021-02-19 | 兰和科技（深圳）有限公司 | Campus public health comprehensive intelligent control system and method based on Internet |
| CN112507948A (en) * | 2020-12-18 | 2021-03-16 | Oppo广东移动通信有限公司 | Mask wearing prompting method and related device |
| CN112800885A (en) * | 2021-01-16 | 2021-05-14 | 南京众鑫云创软件科技有限公司 | Data processing system and method based on big data |
| CN112800885B (en) * | 2021-01-16 | 2023-09-26 | 南京众鑫云创软件科技有限公司 | Data processing system and method based on big data |
| CN112912893A (en) * | 2021-01-28 | 2021-06-04 | 深圳市锐明技术股份有限公司 | Detection method and device for wearing mask, terminal equipment and readable storage medium |
| WO2022160202A1 (en) * | 2021-01-28 | 2022-08-04 | 深圳市锐明技术股份有限公司 | Method and apparatus for inspecting mask wearing, terminal device and readable storage medium |
| CN113197403A (en) * | 2021-05-14 | 2021-08-03 | 广东华联云谷科技研究院有限公司 | Method capable of preventing virus infection and smart bracelet |
| CN113197403B (en) * | 2021-05-14 | 2023-02-17 | 广州乾睿医疗科技有限公司 | Method capable of preventing virus infection and smart bracelet |
| CN113628760A (en) * | 2021-08-31 | 2021-11-09 | 南华大学 | Intelligent monitoring system of mobile vaccination vehicle |
| CN114415528A (en) * | 2021-12-08 | 2022-04-29 | 珠海格力电器股份有限公司 | Intelligent household equipment reminding method and device, computer equipment and storage medium |
| CN114255517A (en) * | 2022-03-02 | 2022-03-29 | 中运科技股份有限公司 | Scenic spot tourist behavior monitoring system and method based on artificial intelligence analysis |
| CN115620209A (en) * | 2022-11-15 | 2023-01-17 | 北京梦天门科技股份有限公司 | Method for generating public health video supervision result and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111523380B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111523380B (en) | Mask wearing condition monitoring method based on face and gesture recognition | |
| US11727780B2 (en) | Systems and methods for privacy-aware motion tracking with notification feedback | |
| US20210009150A1 (en) | Method for recognizing dangerous action of personnel in vehicle, electronic device and storage medium | |
| RU2728801C1 (en) | Self-monitoring for individual protection means | |
| US20210358068A1 (en) | Method for issuing a verified health pass, use thereof for entering a venue and contact tracing method | |
| CN111428559A (en) | Method and device for detecting wearing condition of mask, electronic equipment and storage medium | |
| JP2020067939A (en) | Infection risk identification system, information terminal, and infection risk identification method | |
| US20120140054A1 (en) | Intelligent hand washing monitoring system | |
| EP3797379A1 (en) | Image-based personal protective equipment fit system using worker-specific fit test image data | |
| US20210241923A1 (en) | Sensor-based machine learning in a health prediction environment | |
| CN112236788A (en) | Personal protection device and safety management system with active worker sensing and evaluation | |
| CN105632128B (en) | A kind of alarm method and intelligent terminal | |
| D’Aurizio et al. | Preventing undesired face-touches with wearable devices and haptic feedback | |
| CN106796746A (en) | Activity monitoring approach and system | |
| CN107609474B (en) | Limb action recognition method and device, robot and storage medium | |
| CN111339901B (en) | Image-based intrusion detection method and device, electronic equipment and storage medium | |
| CN111523476A (en) | Mask wearing identification method, device, equipment and readable storage medium | |
| US20220004949A1 (en) | System and method for artificial intelligence (ai)-based activity tracking for protocol compliance | |
| CN112183390A (en) | Medical personnel hand washing monitoring system | |
| CN107392826A (en) | A kind of PE management method and system | |
| WO2017152592A1 (en) | Mobile terminal application operation method and mobile terminal | |
| CN110148092A (en) | The analysis method of teenager's sitting posture based on machine vision and emotional state | |
| CN109044375A (en) | A kind of control system and its method of real-time tracking detection eyeball fatigue strength | |
| CN114944031A (en) | Multifunctional bank self-service number taking system and method | |
| US11393318B2 (en) | Systems and methods for privacy-aware motion tracking with automatic authentication |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |