CN109907739A - The alarm method and system caught a cold when a kind of sleep based on image recognition - Google Patents

The alarm method and system caught a cold when a kind of sleep based on image recognition Download PDF

Info

Publication number
CN109907739A
CN109907739A CN201910216437.1A CN201910216437A CN109907739A CN 109907739 A CN109907739 A CN 109907739A CN 201910216437 A CN201910216437 A CN 201910216437A CN 109907739 A CN109907739 A CN 109907739A
Authority
CN
China
Prior art keywords
state value
exposed
cold
sleep
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.)
Granted
Application number
CN201910216437.1A
Other languages
Chinese (zh)
Other versions
CN109907739B (en
Inventor
路廷文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Wave Intelligent Technology Co Ltd
Original Assignee
Suzhou Wave Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Wave Intelligent Technology Co Ltd filed Critical Suzhou Wave Intelligent Technology Co Ltd
Priority to CN201910216437.1A priority Critical patent/CN109907739B/en
Publication of CN109907739A publication Critical patent/CN109907739A/en
Application granted granted Critical
Publication of CN109907739B publication Critical patent/CN109907739B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Image Processing (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Radiation Pyrometers (AREA)

Abstract

The present invention provides the alarm method caught a cold when a kind of sleep based on image recognition and systems, the present invention is by carrying out thermal infrared images acquisition to the human body in sleep, the image of acquisition is subjected to image procossing, identify the human region being exposed to except quilt, the setting for pedestrian's body state value of going forward side by side, in conjunction with current environmental temperature, setting flu critical point, when state value is more than flu critical point, alarming processing is carried out to human body, to realize the alarm caught a cold when the sleep based on image recognition.State and environment temperature when the present invention is according to sleep quality, whether the current flu of judgement is in easy hair-like state, it is preferably mankind's service for life in the prevention work that artificial intelligence application is caught a cold when for sleep to which the probability for solving the problems, such as that people catches a cold in sleep is high.

Description

The alarm method and system caught a cold when a kind of sleep based on image recognition
Technical field
The present invention relates to field of artificial intelligence, alarm that when especially a kind of sleep based on image recognition catches a cold Method and system.
Background technique
Currently, many three years old or more children are separately slept with parent, bed, according to statistics, Hen Duohai oneself are slept Son is to cover quilt not in time during sleep at night and catch a cold.In fact, either children are still adult, in the case where sleeping all Without the ability of oneself lid quilt, and due to the reduction of nocturnal temperature, in this case, the probability that when sleep catches a cold is significantly Increase.
Cash, artificial intelligence technology have slowly goed deep into the basic living of the mankind, but the utilization of artificial intelligence also in How artificial intelligence application is those skilled in the art's urgency in the prevention work caught a cold when for sleep by the primary stage Major issue to be solved.
Summary of the invention
The object of the present invention is to provide the alarm method caught a cold when a kind of sleep based on image recognition and systems, it is intended to The probability for solving the problems, such as that people catches a cold in sleep in the prior art is high, and artificial intelligence application is caught a cold when for sleep Prevention work in, preferably be mankind's service for life.
To reach above-mentioned technical purpose, the present invention provides the alarm sides to catch a cold when a kind of sleep based on image recognition Method the described method comprises the following steps:
The thermal infrared images of human body when S1, acquisition sleep;
S2, image procossing is carried out to thermal infrared images, identification is exposed to the human region except quilt;
S3, the setting that body state value is carried out according to the human region being exposed to except quilt;
S4, acquisition environment temperature, according to environment temperature and the setting flu critical point of body state value;
S5, when body state value be higher than flu critical point body state value when, carry out alarm operation.
Preferably, described image processing includes following operation:
Image enhancement is carried out to thermal infrared images, the threshold value selection of Wavelet Denoising Method is generated, carries out global image noise reduction, effectively Retain zone boundary, realize image enhancement, then the feature higher than environment temperature according to human body temperature, thermal infrared images is carried out High-pass filtering, it is preliminary to carry out human body boundary segmentation, determine limbs regional location.
Preferably, the limbs region includes head, upper limb, trunk, lower limb.
Preferably, the setting of the body state value specifically:
Only when head is exposed, state value 1, only when upper limb is exposed, state value 2, only when lower limb are exposed, state Value is 3, only when trunk is exposed, state value 4;When different parts are exposed simultaneously, state value superposition.
The present invention also provides the warning system caught a cold when a kind of sleep based on image recognition, the system comprises:
Thermal infrared images acquisition module, the thermal infrared images of human body when for acquiring sleep;
Human region identification module, for carrying out image procossing to thermal infrared images, identification is exposed to the people except quilt Body region;
Body state value setup module, for carrying out setting for body state value according to the human region being exposed to except quilt It sets;
Critical point setup module of catching a cold is felt for acquiring environment temperature according to environment temperature and the setting of body state value Emit critical point;
Alarm module carries out alarm operation when for being higher than the body state value of flu critical point when body state value.
Preferably, the human region identification module includes:
Image enhancing unit generates the threshold value selection of Wavelet Denoising Method, carries out for carrying out image enhancement to thermal infrared images Global image noise reduction is effectively retained zone boundary, realizes image enhancement;
Filter unit carries out high-pass filtering to thermal infrared images for the feature higher than environment temperature according to human body temperature, It is preliminary to carry out human body boundary segmentation, determine limbs regional location.
Preferably, the limbs region includes head, upper limb, trunk, lower limb.
Preferably, the setting of the body state value specifically:
Only when head is exposed, state value 1, only when upper limb is exposed, state value 2, only when lower limb are exposed, state Value is 3, only when trunk is exposed, state value 4;When different parts are exposed simultaneously, state value superposition.
The effect provided in summary of the invention is only the effect of embodiment, rather than invents all whole effects, above-mentioned A technical solution in technical solution have the following advantages that or the utility model has the advantages that
Compared with prior art, the present invention is by carrying out thermal infrared images acquisition to the human body in sleep, by the figure of acquisition As carrying out image procossing, the human region being exposed to except quilt is identified, the setting for pedestrian's body state value of going forward side by side, in conjunction with current Environment temperature, setting flu critical point carry out alarming processing to human body, to realize when state value is more than flu critical point The alarm caught a cold when sleep based on image recognition.State and environment temperature when the present invention is according to sleep quality, judgement are worked as Whether preceding flu is in easy hair-like state, so that the probability for solving the problems, such as that people catches a cold in sleep is high, artificial intelligence is answered It is preferably mankind's service for life in the prevention work caught a cold when for for sleep.
Detailed description of the invention
Fig. 1 is the alarm method stream caught a cold when a kind of sleep based on image recognition provided in the embodiment of the present invention Cheng Tu;
Fig. 2 is the warning system knot caught a cold when a kind of sleep based on image recognition provided in the embodiment of the present invention Structure block diagram.
Specific embodiment
In order to clearly illustrate the technical characterstic of this programme, below by specific embodiment, and its attached drawing is combined, to this Invention is described in detail.Following disclosure provides many different embodiments or example is used to realize different knots of the invention Structure.In order to simplify disclosure of the invention, hereinafter the component of specific examples and setting are described.In addition, the present invention can be with Repeat reference numerals and/or letter in different examples.This repetition is that for purposes of simplicity and clarity, itself is not indicated Relationship between various embodiments and/or setting is discussed.It should be noted that illustrated component is not necessarily to scale in the accompanying drawings It draws.Present invention omits the descriptions to known assemblies and treatment technology and process to avoid the present invention is unnecessarily limiting.
It is provided for the embodiments of the invention the announcement caught a cold when a kind of sleep based on image recognition with reference to the accompanying drawing Alarm method is described in detail with system.
As shown in Figure 1, the embodiment of the invention discloses the alarm method caught a cold when a kind of sleep based on image recognition, It the described method comprises the following steps:
The thermal infrared images of human body when S1, acquisition sleep;
S2, image procossing is carried out to thermal infrared images, identification is exposed to the human region except quilt;
S3, the setting that body state value is carried out according to the human region being exposed to except quilt;
S4, acquisition environment temperature, according to environment temperature and the setting flu critical point of body state value;
S5, when body state value be higher than flu critical point body state value when, carry out alarm operation.
Whether the embodiment of the present invention needs to adjust quilt at present according to depth in the sleep of people and current room temperature, judgement Or quilt is covered, and whether the quilt covered at present influences breathing etc., to realize that effectively prevention people suffers from sleep Flu.
By thermal infrared images acquisition device in sleep child's body carry out thermal infrared imaging.Human body temperature is usual Higher than environment temperature, when not covered by quilt, human body head and exposed limbs are higher than environment temperature, are easy red by heat Outer image collecting device identification, may recognize that the human region being exposed to except quilt accordingly.
After acquiring thermal infrared images, image enhancement is carried out to thermal infrared images, generates the threshold value selection of Wavelet Denoising Method, into Row global image noise reduction is effectively retained zone boundary, realizes image enhancement, then the spy higher than environment temperature according to human body temperature Sign carries out high-pass filtering to thermal infrared images, preliminary to carry out human body boundary segmentation, determines limbs regional location.For limb The judgement of body, including head, upper limb, trunk, lower limb, and the state value that human body is exposed to except quilt is respectively set, such as only When head is exposed, state value 1, only when upper limb is exposed, state value 2, only when lower limb are exposed, state value 3, only when When trunk is exposed, state value 4;When different parts are exposed simultaneously, state value superposition.Determine that human body is exposed to quilt with this Except region.
Using the temperature of temperature collecting device acquisition current environment, ambient temperature information is obtained.According to ambient temperature information And be exposed to except quilt body state value setting flu critical point, critical point of catching a cold threshold value setting can rule of thumb into Row setting.
For example, when room temperature is in 15 degrees Celsius, when state value is 3, for critical point of catching a cold;When room temperature is in 20 degrees Celsius When, when state value is 6, for critical point of catching a cold;When state value is higher than the state value of flu critical point, the probability caught a cold can be risen Height, therefore when being higher than flu critical point, it needs to alert the people in sleep, prompts to need lid quilt.
User can according to the actual situation, for example the weather conditions on the ground such as northeast or Guangzhou carry out Initialize installation.
The embodiment of the present invention carries out image by carrying out thermal infrared images acquisition to the human body in sleep, by the image of acquisition Processing, identifies the human region being exposed to except quilt, the setting for pedestrian's body state value of going forward side by side, in conjunction with current environmental temperature, Setting flu critical point is carried out alarming processing to human body, is known to realize based on image when state value is more than flu critical point The alarm caught a cold when other sleep.Whether state and environment temperature when the present invention is according to sleep quality judge current flu In easy hair-like state, to solve the problems, such as that people's probability for catching a cold in sleep is high, by artificial intelligence application in for sleeping It is preferably mankind's service for life in the prevention work caught a cold when dormancy.
As shown in Fig. 2, the embodiment of the invention also discloses the alarm systems to catch a cold when a kind of sleep based on image recognition System, the system comprises:
Thermal infrared images acquisition module, the thermal infrared images of human body when for acquiring sleep;
Human region identification module, for carrying out image procossing to thermal infrared images, identification is exposed to the people except quilt Body region;
Body state value setup module, for carrying out setting for body state value according to the human region being exposed to except quilt It sets;
Critical point setup module of catching a cold is felt for acquiring environment temperature according to environment temperature and the setting of body state value Emit critical point;
Alarm module carries out alarm operation when for being higher than the body state value of flu critical point when body state value.
The human region identification module includes:
Image enhancing unit generates the threshold value selection of Wavelet Denoising Method, carries out for carrying out image enhancement to thermal infrared images Global image noise reduction is effectively retained zone boundary, realizes image enhancement;
Filter unit carries out high-pass filtering to thermal infrared images for the feature higher than environment temperature according to human body temperature, It is preliminary to carry out human body boundary segmentation, determine limbs regional location.
By thermal infrared images acquisition device in sleep child's body carry out thermal infrared imaging.Human body temperature is usual Higher than environment temperature, when not covered by quilt, human body head and exposed limbs are higher than environment temperature, are easy red by heat Outer image collecting device identification, may recognize that the human region being exposed to except quilt accordingly.
After acquiring thermal infrared images, image enhancement is carried out to thermal infrared images, generates the threshold value selection of Wavelet Denoising Method, into Row global image noise reduction is effectively retained zone boundary, realizes image enhancement, then the spy higher than environment temperature according to human body temperature Sign carries out high-pass filtering to thermal infrared images, preliminary to carry out human body boundary segmentation, determines limbs regional location.For limb The judgement of body, including head, upper limb, trunk, lower limb, and the state value that human body is exposed to except quilt is respectively set, such as only When head is exposed, state value 1, only when upper limb is exposed, state value 2, only when lower limb are exposed, state value 3, only when When trunk is exposed, state value 4;When different parts are exposed simultaneously, state value superposition.Determine that human body is exposed to quilt with this Except region.
Using the temperature of temperature collecting device acquisition current environment, ambient temperature information is obtained.According to ambient temperature information And be exposed to except quilt body state value setting flu critical point, critical point of catching a cold threshold value setting can rule of thumb into Row setting.
For example, when room temperature is in 15 degrees Celsius, when state value is 3, for critical point of catching a cold;When room temperature is in 20 degrees Celsius When, when state value is 6, for critical point of catching a cold;When state value is higher than the state value of flu critical point, the probability caught a cold can be risen Height, therefore when being higher than flu critical point, it needs to alert the people in sleep, prompts to need lid quilt.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.

Claims (8)

1. the alarm method caught a cold when a kind of sleep based on image recognition, which is characterized in that the method includes following steps It is rapid:
The thermal infrared images of human body when S1, acquisition sleep;
S2, image procossing is carried out to thermal infrared images, identification is exposed to the human region except quilt;
S3, the setting that body state value is carried out according to the human region being exposed to except quilt;
S4, acquisition environment temperature, according to environment temperature and the setting flu critical point of body state value;
S5, when body state value be higher than flu critical point body state value when, carry out alarm operation.
2. the alarm method caught a cold when a kind of sleep based on image recognition according to claim 1, which is characterized in that Described image processing includes following operation:
Image enhancement is carried out to thermal infrared images, the threshold value selection of Wavelet Denoising Method is generated, carries out global image noise reduction, be effectively retained Image enhancement is realized, then the feature higher than environment temperature according to human body temperature in zone boundary, carries out high pass to thermal infrared images Filtering, it is preliminary to carry out human body boundary segmentation, determine limbs regional location.
3. the alarm method caught a cold when a kind of sleep based on image recognition according to claim 2, which is characterized in that The limbs region includes head, upper limb, trunk, lower limb.
4. the alarm method caught a cold when a kind of sleep based on image recognition according to claim 3, which is characterized in that The setting of the body state value specifically:
Only when head is exposed, state value 1, only when upper limb is exposed, state value 2, only when lower limb are exposed, state value is 3, only when trunk is exposed, state value 4;When different parts are exposed simultaneously, state value superposition.
5. the warning system caught a cold when a kind of sleep based on image recognition, which is characterized in that the system comprises:
Thermal infrared images acquisition module, the thermal infrared images of human body when for acquiring sleep;
Human region identification module, for carrying out image procossing to thermal infrared images, identification is exposed to the human body area except quilt Domain;
Body state value setup module, for carrying out the setting of body state value according to the human region being exposed to except quilt;
Critical point setup module of catching a cold is faced for acquiring environment temperature according to environment temperature and body state value setting flu Boundary's point;
Alarm module carries out alarm operation when for being higher than the body state value of flu critical point when body state value.
6. the warning system caught a cold when a kind of sleep based on image recognition according to claim 5, which is characterized in that The human region identification module includes:
Image enhancing unit generates the threshold value selection of Wavelet Denoising Method, carries out global for carrying out image enhancement to thermal infrared images Image noise reduction is effectively retained zone boundary, realizes image enhancement;
Filter unit carries out high-pass filtering to thermal infrared images, tentatively for the feature higher than environment temperature according to human body temperature Human body boundary segmentation is carried out, determines limbs regional location.
7. the warning system caught a cold when a kind of sleep based on image recognition according to claim 6, which is characterized in that The limbs region includes head, upper limb, trunk, lower limb.
8. the warning system caught a cold when a kind of sleep based on image recognition according to claim 7 any one, It is characterized in that, the setting of the body state value specifically:
Only when head is exposed, state value 1, only when upper limb is exposed, state value 2, only when lower limb are exposed, state value is 3, only when trunk is exposed, state value 4;When different parts are exposed simultaneously, state value superposition.
CN201910216437.1A 2019-03-21 2019-03-21 Image recognition-based method and system for alarming cold during sleep Active CN109907739B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910216437.1A CN109907739B (en) 2019-03-21 2019-03-21 Image recognition-based method and system for alarming cold during sleep

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910216437.1A CN109907739B (en) 2019-03-21 2019-03-21 Image recognition-based method and system for alarming cold during sleep

Publications (2)

Publication Number Publication Date
CN109907739A true CN109907739A (en) 2019-06-21
CN109907739B CN109907739B (en) 2021-07-30

Family

ID=66965999

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910216437.1A Active CN109907739B (en) 2019-03-21 2019-03-21 Image recognition-based method and system for alarming cold during sleep

Country Status (1)

Country Link
CN (1) CN109907739B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112802300A (en) * 2020-12-23 2021-05-14 张慧东 Dynamic triggering system based on wireless communication
CN113520306A (en) * 2020-04-17 2021-10-22 青岛海尔空调器有限总公司 Human sleep state monitoring method and intelligent household device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104684465A (en) * 2012-07-12 2015-06-03 菲力尔系统公司 Infant monitoring systems and methods using thermal imaging
CN105681756A (en) * 2016-02-04 2016-06-15 四川长虹电器股份有限公司 Air conditioning system and image processing method capable of intelligently recognizing sleeping posture under high wind refrigeration
CN105930778A (en) * 2016-04-14 2016-09-07 厦门理工学院 Nighttime human sleeping posture monitoring method and system based on infrared image
CN106361293A (en) * 2016-11-08 2017-02-01 广东顺德鲁棒智能技术有限公司 Infant sleeping state monitoring device and method based on infrared temperature measurement
CN107067670A (en) * 2016-11-23 2017-08-18 深圳市元征科技股份有限公司 One kind detection alarm method and system
WO2018058132A1 (en) * 2016-09-26 2018-03-29 Whirlpool Corporation Controlled microclimate system
CN108986121A (en) * 2018-07-31 2018-12-11 王乾宇 Baby sleep monitoring device and monitoring method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104684465A (en) * 2012-07-12 2015-06-03 菲力尔系统公司 Infant monitoring systems and methods using thermal imaging
CN105681756A (en) * 2016-02-04 2016-06-15 四川长虹电器股份有限公司 Air conditioning system and image processing method capable of intelligently recognizing sleeping posture under high wind refrigeration
CN105930778A (en) * 2016-04-14 2016-09-07 厦门理工学院 Nighttime human sleeping posture monitoring method and system based on infrared image
WO2018058132A1 (en) * 2016-09-26 2018-03-29 Whirlpool Corporation Controlled microclimate system
CN106361293A (en) * 2016-11-08 2017-02-01 广东顺德鲁棒智能技术有限公司 Infant sleeping state monitoring device and method based on infrared temperature measurement
CN107067670A (en) * 2016-11-23 2017-08-18 深圳市元征科技股份有限公司 One kind detection alarm method and system
CN108986121A (en) * 2018-07-31 2018-12-11 王乾宇 Baby sleep monitoring device and monitoring method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113520306A (en) * 2020-04-17 2021-10-22 青岛海尔空调器有限总公司 Human sleep state monitoring method and intelligent household device
CN113520306B (en) * 2020-04-17 2024-03-22 青岛海尔空调器有限总公司 Human sleep state monitoring method and intelligent household device
CN112802300A (en) * 2020-12-23 2021-05-14 张慧东 Dynamic triggering system based on wireless communication

Also Published As

Publication number Publication date
CN109907739B (en) 2021-07-30

Similar Documents

Publication Publication Date Title
CN111383421B (en) Privacy protection fall detection method and system
Zhao et al. Real-time detection of fall from bed using a single depth camera
CN101593425B (en) Machine vision based fatigue driving monitoring method and system
CN105448041B (en) A kind of falling over of human body intelligence control system and its method
CN109907739A (en) The alarm method and system caught a cold when a kind of sleep based on image recognition
CN102263937B (en) Driver's driving behavior monitoring device and monitoring method based on video detection
CN108986121B (en) Baby sleep monitoring device and monitoring method
CN105894735B (en) A kind of intelligent vehicle-mounted fatigue monitoring system and method
CN110443102B (en) Living body face detection method and device
CN104537857B (en) Based reminding method and system based on driving video instrument identification traffic-control device
CN107609474B (en) Limb action recognition method and device, robot and storage medium
CN107194367A (en) Biopsy method in finger vena identification process
CN105078436A (en) Sleep monitoring system and method capable of preventing nightmare
KR102182660B1 (en) System and method for detecting violence using spatiotemporal features and computer readable recording media storing program for executing method thereof
Basavaraj et al. Vision based surveillance system for detection of human fall
CN103247150A (en) Fatigue driving preventing system
Begam et al. Eyeblink artefact removal from EEG using independent component analysis
CN116386278B (en) Intelligent recognition reminding method, device and equipment based on infant sleeping posture
CN108597168A (en) Security alarm method, apparatus based on optical filter and household appliance
JP2019008515A (en) Watching support system and method for controlling the same
Zhou et al. Nighttime in-home action monitoring for eldercare
CN104616424A (en) System for preventing children from kicking quilt
CN106333681A (en) sleep state monitoring method and system based on self-learning
CN106562771A (en) Embedded platform-oriented pet sleep identification method
Ali et al. Human fall detection

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