CN107832744A - A kind of baby sleep monitoring system and its method - Google Patents
A kind of baby sleep monitoring system and its method Download PDFInfo
- Publication number
- CN107832744A CN107832744A CN201711237755.3A CN201711237755A CN107832744A CN 107832744 A CN107832744 A CN 107832744A CN 201711237755 A CN201711237755 A CN 201711237755A CN 107832744 A CN107832744 A CN 107832744A
- Authority
- CN
- China
- Prior art keywords
- baby
- image
- face
- state
- processing equipment
- 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.)
- Withdrawn
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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/04—Babies, e.g. for SIDS detection
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Anesthesiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of baby sleep monitoring system and its method, including：Harvester, data processing equipment, alarm device；Wherein, the harvester is used to gather baby image；The data processing equipment electrically connects the harvester, and for receiving the baby image, sleeping condition of baby and baby's face occlusion state are extracted according to the baby image；The alarm device electrically connects the data processing equipment, for sending alarm signal to monitor terminal according to the result of the data processing equipment.Baby sleep monitoring system and its method provided by the invention, extract whether baby wake up or whether baby is blocked by foreign matter bed clothes according to baby's realtime image data, and the dangerous scene is notified into guardian in time, effective feature and substantial amounts of sample need not be selected to be trained, computational complexity is low, reduce the stronger data of a large amount of repeatability to calculate, so that algorithm speed is very fast.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of baby sleep monitoring system and its method.
Background technology
Sleep is an indispensable part in everyone normal life, and good sleep can adjust body condition, dispelling fatigue,
Be advantageous to the metabolism of body, enhancing development.In each age level, the time requirement to sleep is different.
Neonate is about 20 hours the daily length of one's sleep；Daily about 18 hours of the baby of 2 months；About 16 daily at 4 months
Hour；About 15 hours at 9 months；About 13 hours of or so 1 one full year of life.It is therefore seen that baby's most of the time is in sleep
State.
Data show, the death by accident related to sleep, including SIDS (SIDS), cause about 3500 every year
Name baby's unexpected death.A big chunk reason of sudden death of the baby is because the face of baby is blocked by foreign matter bed clothes, causes baby
Youngster can not breathe, caused by tragedy.In addition, the guardian for looking after baby tends not to accompany and attend to beside baby at any time, unavoidably
Need to split to handle other household chores.However, during managing one's household, it can divert attention again and worry whether baby has waken up
To need to look after, in this way, causing guardian not take into account looks after baby with managing one's household.Due to the fast development of science and technology, market
On there are many nursing systems, but be the mode using Dynamic Photography mostly, user supplied in a manner of webpage or video streams
Check, user must voluntarily connect the situation that net checks the baby guarded at present.If guardian is watching monitoring picture always
Face, it can not settle down to do housework or entertain when baby falls asleep.
Therefore, the view data in monitoring how is handled, whether go out baby according to image data extraction wake up or baby
Whether blocked by foreign matter bed clothes, notify guardian to become particularly important in time.
The content of the invention
Therefore, to solve technological deficiency and deficiency existing for prior art, the present invention proposes a kind of baby sleep monitoring system
System and its method.
Specifically, a kind of baby sleep monitoring system that one embodiment of the invention proposes, including：
The harvester is used to gather baby image；
The data processing equipment electrically connects the harvester, for receiving the baby image, according to the baby
Image zooming-out sleeping condition of baby and baby's face occlusion state；
The alarm device electrically connects the data processing equipment, for the result according to the data processing equipment
Alarm signal is sent to monitor terminal.
In one embodiment of the invention, in addition to data transmission device；Wherein, the data transmission device electrical connection
The data processing equipment, for transmitting the baby image to monitoring end according to the result of the data processing equipment
End.
In one embodiment of the invention, the monitor terminal includes mobile phone, flat board and computer.
In one embodiment of the invention, the data processing equipment include image storage unit, graphics processing unit,
Sleep state judging unit and facial occlusion state judging unit；Wherein,
Described image memory cell is used to receive the baby image of the harvester and stored；
Described image processing unit connects described image memory cell, for reading the baby in described image memory cell
Image is simultaneously handled；
The sleep state judging unit connects described image processing unit, for according to the baby image after processing
Sleeping condition of baby is judged by eye state detection algorithm；
The facial occlusion state judging unit connection described image processing unit, for according to the baby after processing
Image judges the occlusion state of baby's face face by face detection algorithm.In one embodiment of the invention, the figure
As processing unit is additionally operable to read described image storage list according to the sleeping condition of baby and baby's face occlusion state
The baby image in member is transmitted to the data transmission device.
In a kind of baby sleep monitoring method that an alternative embodiment of the invention proposes, including：
Gather baby image；
Sleeping condition of baby and baby's face occlusion state are extracted according to the baby image；
Determine whether to send alarm signal to monitoring according to the sleeping condition of baby and baby's face occlusion state
Terminal.
In one embodiment of the invention, sleeping condition of baby is extracted according to the baby image, including：
Baby's face-image is identified according to the baby image；
Infant eyes image is obtained by the face-image；
Baby's eye state is determined according to the eyes image；
The sleeping condition of baby is judged according to the eye state.
In one embodiment of the invention, baby's face occlusion state is extracted according to the baby image, including：
Baby's face-image is identified according to the baby image；
Baby's face face are extracted according to baby's face-image；
Judge baby's face occlusion state according to baby's face face.
In one embodiment of the invention, the monitor terminal includes mobile phone, flat board and computer.
In one embodiment of the invention, determined according to the sleeping condition of baby and baby's face occlusion state
After sending alarm signal to monitor terminal, in addition to：
The baby image is sent to the monitor terminal.
Based on this, the present invention possesses following advantage：
1) baby sleep monitoring system proposed by the present invention extracts whether baby wake up according to baby's realtime image data
Or whether baby is blocked by foreign matter bed clothes, and the dangerous scene is notified into guardian in time.
2) baby sleep monitoring method proposed by the present invention, can be preferable by baby's eyes condition adjudgement baby sleep
Computational complexity is reduced, improves real-time, and reliability is high, is with a wide range of applications.
3) baby sleep monitoring method proposed by the present invention judges that baby's face occlusion state is calculated by face detection algorithm
The simple accuracy rate of method is high.
By the detailed description below with reference to accompanying drawing, other side of the invention and feature become obvious.But it should know
Road, the accompanying drawing is only the purpose design explained, not as the restriction of the scope of the present invention, because it should refer to
Appended claims.It should also be noted that unless otherwise noted, it is not necessary to which scale accompanying drawing, they only try hard to concept
Ground illustrates structure and flow described herein.
Brief description of the drawings
Below in conjunction with accompanying drawing, the embodiment of the present invention is described in detail.
Fig. 1 is a kind of schematic diagram of baby sleep monitoring system provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of data processing equipment provided in an embodiment of the present invention；
Fig. 3 is a kind of flow chart of baby sleep monitoring method provided in an embodiment of the present invention；
A kind of Fig. 4 infant eyes image schematic diagrames provided in an embodiment of the present invention；
Fig. 5 is a kind of infant eyes image grey level histogram provided in an embodiment of the present invention；
Fig. 6 is a kind of infant eyes image binaryzation grey level histogram provided in an embodiment of the present invention；
Fig. 7 is a kind of binaryzation infant eyes gray-scale map schematic diagram provided in an embodiment of the present invention；
Fig. 8 is a kind of baby eyes angle point grid schematic diagram provided in an embodiment of the present invention；
Fig. 9 is a kind of baby canthus angle schematic diagram provided in an embodiment of the present invention；
Figure 10 is a kind of lying position baby head image schematic diagram provided in an embodiment of the present invention；
Figure 11 is a kind of 45 degree of lying posture gesture baby head image schematic diagrames in side provided in an embodiment of the present invention；
Figure 12 is a kind of lateral position baby head image schematic diagram provided in an embodiment of the present invention；
Figure 13 is that one kind provided in an embodiment of the present invention climbs prone position gesture head image schematic diagram；
Figure 14 is a kind of 2 value image schematic diagrames of baby's facial zone provided in an embodiment of the present invention；
Figure 15 is the position coordinates schematic diagram that a kind of face of baby's facial zone provided in an embodiment of the present invention are demarcated；
Figure 16 is a kind of triangle schematic diagram of baby's face position coordinate structure provided in an embodiment of the present invention.
Embodiment
In order to facilitate the understanding of the purposes, features and advantages of the present invention, below in conjunction with the accompanying drawings to the present invention
Embodiment be described in detail.
Embodiment one
Fig. 1 is referred to, Fig. 1 is a kind of schematic diagram of baby sleep monitoring system provided in an embodiment of the present invention.The system
10 include：Harvester 11, data processing equipment 12, alarm device 13, data transmission device 14；Wherein,
The harvester 11 is used to gather baby image；
The data processing equipment 12 electrically connects the harvester 11, for receiving the baby image, according to described
Baby image extracts sleeping condition of baby and baby's face occlusion state；
The alarm device electrically connects the data processing equipment 12, for the processing according to the data processing equipment 12
As a result alarm signal is sent to monitor terminal；
The data transmission device electrically connects the data processing equipment 12, for according to the data processing equipment 12
Result transmits the baby image to monitor terminal.
Further, harvester 11 can include three cameras, be respectively arranged at the top and both sides of infanette；Or
Person's harvester 11 can also include two 180 degree cameras, be respectively arranged at the both sides of infanette.Harvester 11 is supervised in real time
The baby in infanette is controlled, the baby image collected is sent to data processing equipment 12.
Further, data processing equipment 12 is sentenced including image storage unit 121, graphics processing unit 124, sleep state
Disconnected unit 122 and facial occlusion state judging unit 123.As shown in Fig. 2 Fig. 2 is a kind of data provided in an embodiment of the present invention
The schematic diagram of processing unit.The baby image input picture memory cell 121 of the collection of harvester 11 simultaneously stores.Image procossing list
Member 124 reads the baby image in image storage unit, and is handled, and concrete processing procedure can be in extraction baby image
Baby's face-image and baby head image.Sleep state judging unit 122 reads the baby after graphics processing unit 124 is handled
Youngster's image, judge that baby's eyes open closed state and determine that baby sleeps by eye state detection algorithm according to the baby image after processing
Dormancy state；
If eye state is eyes-open state, and continues then to judge within 5~10 seconds that baby is in waking state；Because baby
Eyes also can be opened to transience in sleep procedure, but can close eyes again quickly and continue to sleep, therefore can select to open eyes
State continues 5 seconds, 6 seconds, 7 seconds, 8 seconds and 9 seconds to judge whether baby regains consciousness, and the time is too short to easily cause erroneous judgement, overlong time
Easy missing inspection baby's waking state, it can turn over or creep after baby is clear-headed, it is easy to fall under bed, cause irremediable
Injury.
If eye state is closed-eye state, and continues then to judge within 60~300 seconds that baby is in sleep state；It is because each
The time that baby enters sleep differs, therefore the duration can set definition manually according to the characteristic of baby.
Facial occlusion state judging unit reads the baby image after being handled in graphics processing unit 124, after processing
Baby image by face detection algorithm judge baby's face face whether block determine baby's face occlusion state；Because work as
After the face of baby is blocked, it is easy to cause the asphyxia of baby, if the duration is long, gently then cause cerebral anoxia to baby
Threat that is heavy then carrying out life to baby harness, therefore can will detect that baby's face continues to be judged as more than 5~10 seconds after blocking
Baby's face is in occlusion state.
Further, the sleeping condition of baby in alarm device reception sleep state judging unit 122 and face block shape
Baby's face occlusion state in state judging unit 123；
If baby is in waking state, alarm device sends alarm signal to monitor terminal；
If baby's face is in occlusion state, alarm device sends alarm signal to monitor terminal；
Wherein, monitor terminal can be mobile phone, flat board and computer, and alarm signal can bind multiple monitor terminals, be easy to
After a certain guardian does not receive or have ignored alarm signal in time, other guardians can have found to alert in time, adopt in time
Measure is taken, ensures the safety of baby.
Further, data transmission device transmits baby image to monitoring end according to the result of data processing equipment 12
End.The baby image that i.e. data transmission device is read in image storage unit 121 is sent to monitor terminal.Monitor terminal can select
Select automatic real-time reception baby image or the automatic baby received before and after the alarm device transmission alarm signal time can be selected
Image, saves internal memory, and monitor terminal can also select the baby image checked manually in image storage unit 121.
Embodiment two
Refer to Fig. 3, Fig. 3 is a kind of flow chart of baby sleep monitoring method provided in an embodiment of the present invention, this method
Including：
Step 1, collection baby image；
Step 2, sleeping condition of baby and baby's face occlusion state extracted according to the baby image；
Step 3, alarm signal is sent according to the sleeping condition of baby and baby's face occlusion state to monitoring end
End.
Wherein, in step 2 according to the baby image extract sleeping condition of baby, including：
Baby's face-image is identified according to the baby image；
Infant eyes image is obtained by the face-image；
Baby's eye state is determined according to the eyes image；
The sleeping condition of baby is judged according to the eye state.
Wherein, in step 2 according to the baby image extract baby's face occlusion state, including：
Baby's face-image is identified according to the baby image；
Baby's face face are extracted according to baby's face-image；
Judge baby's face occlusion state according to baby's face face.
Wherein, mobile phone, flat board and computer are included for monitor terminal described in step 3.
Wherein, after step 3, in addition to：
The baby image is sent to the monitor terminal.
Embodiment three
On the basis of above-described embodiment two, the present embodiment further illustrates to baby sleep monitoring method.
Step 1, collection baby image
Using three cameras, the top and both sides for being respectively arranged at infanette monitor baby image in real time；Or use
Two 180 degree cameras, the both sides for being respectively arranged at infanette monitor baby image in real time.
Step 2, according to the baby image extract sleeping condition of baby
The baby image gathered in step 1 is determined into baby head image by face recognition algorithms, by baby head
Image determines infant eyes image by face recognition algorithm, as shown in figure 4, Fig. 4 is one kind provided in an embodiment of the present invention
Infant eyes image schematic diagram.Wherein, face recognition algorithms and face recognition algorithm are ripe prior art, therefore no longer
Repeat.The eye state of baby is determined according to infant eyes image, is comprised the following steps that shown：
Step 21, extraction informer's profile
According to the contrast of area of skin color, eyeball region and white of the eye region in eyes image, calculated using three color shade watersheds
Method, extract informer's profile.
Step a), the gray value for extracting pixel
Extract the gray value of all pixels in eyes image, because area of skin color, eyeball region and this 3 areas of white of the eye region
The gray value in domain has notable difference, and in any 1 region in 3 regions, containing a greater number pixel, these pixels
Gray value be nearly at same scope.
Step b), regulation threshold value is set
Due to photo degree of accuracy reason, compensation is set；According to the different colours of skin, area of skin color, eyeball region and the white of the eye are set
The regulation threshold value in these three regions of region is the first regulation threshold value, the second regulation threshold value and the 3rd regulation threshold value.Regulative mode can
Think manually or automatically, it is as described below to automatically adjust mode：
Step b11), draw histogram curve, as shown in figure 5, Fig. 5 is a kind of infant eyes provided in an embodiment of the present invention
Image grey level histogram.Because white of the eye area grayscale value is maximum, so its gray value region is 200 or so；Eyeball area grayscale
Value is minimum, so its gray value region is 25 or so；The gray value of skin area is placed in the middle, so its gray value region is left 75
It is right.Assuming that other gray value area pixel numbers are essentially 0.For 3 kinds of regions of automatic distinguishing.It is 0 to take all pixels quantity in Fig. 5
Point, shown in equation below：
Wherein i is abscissa, and D is abscissa distance, and H is ordinate value.I.e. using i as starting point, using i+D as all of terminal
The average of ordinate sum, less than offset k, then this D point, be 0；Otherwise it is 1.
Step b12), Fig. 5 carried out shown in the result figure 6 that is formed after the fortran in step b11, Fig. 6 is the present invention
A kind of infant eyes image binaryzation grey level histogram that embodiment provides.Fig. 6 includes the first gray value interval 21, the second gray scale
It is worth the gray value interval 23 of section 22 and the 3rd.It is final to obtain the first regulation threshold value, the second regulation threshold value and the 3rd regulation threshold value, such as
Shown in following formula：
THR1=(POS1+POS2)/2
THR2=(POS3+POS4)/2
THR3=POS5
Wherein, THR1 is the first regulation threshold value, and THR2 is the second regulation threshold value, and THR3 is the 3rd regulation threshold value；POS1 is
The terminal (i.e. the maximum of the first gray value interval 21) of first gray value interval 21, POS2 are rising for the second gray value interval 22
Point (i.e. the minimum value of the second gray value interval 22), POS3 are terminal (i.e. the second gray value interval of the second gray value interval 22
22 maximum), POS4 is the starting point (i.e. the minimum value of the 3rd gray value interval 23) of the 3rd gray value interval 23, POS5 the
The terminal (i.e. the maximum of the 3rd gray value interval 23) of three gray value intervals 13.
Step c), remember for binaryzation grey level histogram, 0~THR1 of extraction all pixels as the first pixel region
For PIX1；THR1~THR2 all pixels are extracted as the second pixel region, are designated as PIX2, extraction THR2~THR3's is all
Pixel is designated as PIX3 as the 3rd pixel region.The gray value size in wherein this 3 regions is ordered as PIX1<PIX2<PIX3.
In order to simplify the operation of extraction informer's profile, it is assumed that PIX1=PIX2.The binaryzation eye gray-scale map such as Fig. 7 institutes ultimately formed
Show, Fig. 7 is a kind of binaryzation infant eyes gray-scale map schematic diagram provided in an embodiment of the present invention.
Step 22, determine canthus point
In the binaryzation eye gray-scale map that Fig. 7 is obtained, using eyeball center as the center of circle, straight line is used to enter with angle a
Row rotation, until 360 degree of rotations finish.When white pixel point (i.e. the pixel of the 3rd pixel region) is most on final straight line,
The point that the straight line has a common boundary with black and white (i.e. the second pixel region and the 3rd pixel region) is First view angle point and the second canthus point, is remembered
For T1 and T2；Similarly, when white pixel point is minimum, point that the straight line and black and white are had a common boundary is the 3rd canthus point and four eyed angle point,
It is designated as T3 and T4；As shown in figure 8, Fig. 8 is a kind of baby eyes angle point grid schematic diagram provided in an embodiment of the present invention.
Step 23, judge eye state
As shown in figure 9, Fig. 9 is a kind of baby canthus angle schematic diagram provided in an embodiment of the present invention.Connect TI, T3, T2,
T4, the first canthus angle, the second canthus angle, the 3rd canthus angle and the 4th canthus angle are obtained, is denoted as b1, b2, b3, b4.
Eye state is judged according to eye state equation.Eye state equation is as follows：
Wherein, offset0 and offset1 is error compensation, different according to the different error compensations of photographing device.When θ is got over
It is small, illustrate eyes closer to closure, otherwise θ is bigger, illustrates that the amplitude that eyes are opened is bigger.As θ=0, eyes close completely,
Due to individual difference, baby's eyes, which open state, can define threshold decision.
So far, it may determine that baby's eyes are in by the size of θ values and open state or closure state.
If eye state is eyes-open state, and continues then to determine within 5~10 seconds that baby is in waking state；Because baby
Eyes also can be opened to transience in sleep procedure, but can close eyes again quickly and continue to sleep, therefore can select to open eyes
State continues 5 seconds, 6 seconds, 7 seconds, 8 seconds and 9 seconds to judge whether baby regains consciousness, and the time is too short to easily cause erroneous judgement, overlong time
Easy missing inspection baby's waking state, it can turn over or creep after baby is clear-headed, it is easy to fall under bed, cause irremediable
Injury.
If eye state is closed-eye state, and continues then to determine within 60~300 seconds that baby is in sleep state；It is because each
The time that baby enters sleep differs, therefore the duration can set definition manually according to the characteristic of baby.
Step 3, baby's face occlusion state extracted according to the baby image, refer to Figure 10, Figure 10 is real for the present invention
A kind of lying position baby head image schematic diagram of example offer is provided；Figure 11, Figure 11 are a kind of side provided in an embodiment of the present invention
45 degree of lying posture gesture baby head image schematic diagrames；Figure 12, Figure 12 are a kind of lateral position baby head provided in an embodiment of the present invention
Portion's image schematic diagram；Figure 13, Figure 13 are that one kind provided in an embodiment of the present invention climbs prone position gesture head image schematic diagram；Figure 14, figure
14 be a kind of 2 value image schematic diagrames of baby's facial zone provided in an embodiment of the present invention；Figure 15, Figure 15 are implemented for the present invention
A kind of position coordinates schematic diagram of the face demarcation for baby's facial zone that example provides；Figure 16, Figure 16 carry for the embodiment of the present invention
A kind of triangle schematic diagram of the baby's face position coordinate structure supplied；It is specific as follows：
Step 31, face identification
Gather to form three baby images respectively by three cameras in step 1, or imaged by two 180 degrees
Three images are synthesized after head two baby images of collection, three images are respectively front plan view, left surface figure and right hand view.
Wherein, lying position is as shown in Figure 10, and 45 degree of side lying posture gesture is as shown in figure 11, and lateral position is as shown in figure 12, climbs prone position gesture such as
Shown in Figure 13.
By the baby image of the collection in step 1, use face recognition algorithms (algorithm for general-purpose algorithm, thus
Here is omitted) baby head image is determined, face recognition algorithms are used (algorithm for general-purpose algorithm, therefore here
Repeat no more), extract baby's face-image.
Baby's face region is distinguished by face and peripheral region color contrast in baby's face-image.Utilize baby
Face region and the different of baby peripheral region color carry out the value of region 2 operation to baby's face-image, obtain baby's face
The 2 value images in region, extract baby's face face.Specially：For infant eyes region, according to facial image acquisition ash
Image is spent, because eyeball is different with the colour of skin of skin, threshold value can be set according to the average of its gray value, carry out 2 value behaviour
Make, such as：Eyeball is black, and for gray value more than 200, skin is yellow gray value below 100.Therefore it is threshold to set 150
Value, the color mark more than 150 are 1, and remaining is labeled as 0.The final 2 values words image that can obtain infant eyes region, therefore can
Go out eyes respectively.This method can be used for nostril region, earhole region and mouth region.The result finally given is as shown in figure 14.
Step 32, shadowing
According to the baby's face face extracted in step 31, the position coordinates of face is demarcated.Calibrate ocular angle point
41 position coordinates, the position coordinates of nasal region central point 42, mouth region central point 43 and the position coordinates of the corners of the mouth 44, area of ear
The position coordinates of domain central point 45, as shown in figure 15.
The position coordinates demarcated according to face builds facial triagnle figure.By in ocular two angle points and nasal region
Heart line forms ocular and the first triangle 51 of nasal region, by nasal region center and two mouths of mouth region
Angle line forms the second triangle 52 of nasal region and mouth region, by two central points and mouth region of ear region
Central point line forms the 3rd triangle 53 in ear region and mouth region portion, as shown in figure 16.
As illustrated, carrying out facial shadowing by the triangle of structure, specific method is as follows：
Step 321) judges body posture；
Build the triangle in three width images of baby head image front plan view, left surface figure and right hand view.
Left surface figure and right hand view are referred to as side view.
If the triangle that only front plan view presence can be built, illustrate that babies are in lying position；
If the triangle that triangle and one of side view presence that front plan view presence can be built can be built
Figure, illustrate that babies are in 45 degree of lying posture gesture；
If the triangle that only a side view presence can be built, illustrate that babies are in posture of lying on one's side；
If the triangle that can not build, illustrate that babies are in appearance of lying prone.
Step 322), judgement is blocked and blocking position
According to the babies lying posture in step 321, baby's face is judged by the triangle in baby head image
Block and blocking position.
If appearance of lying prone, then baby's face is whole blocks；
If lying position, it is identified using front plan view and judges that baby's face blocks；
If the first triangle 51 that a) can not build, illustrates that infant eyes or nose block；
If the second triangle 52 that b) can not build, illustrates that baby's mouth or nose block；
If the 3rd triangle 53 that c) can not build, illustrate that baby ear or mouth block；
If 45 degree of side lying posture gesture, it is identified using the side view and overhead view image for the triangle that structure be present；
D) if side view and top view illustrate that infant eyes or nose hide without the first triangle 51 that can be built
Gear；
E) if side view and top view illustrate that baby's mouth or nose hide without the second triangle 52 that can be built
Gear；
F) if side view and top view illustrate that baby ear or mouth hide without the 3rd triangle 53 that can be built
Gear；
If posture of lying on one's side, it is identified using side image and judges that face blocks
If the first triangle 51 that g) can not build, illustrates that infant eyes or nose block；
If the second triangle 52 that h) can not build, illustrates that baby's mouth or nose block；
If the 3rd triangle 53 that i) can not build, illustrate that baby ear or mouth block.
So far it may determine that the occlusion state of baby's face.
Step 4, alarm signal sent to monitor terminal according to sleeping condition of baby
If baby is in waking state, alarm signal is sent to monitor terminal.
Step 5, alarm signal sent to monitor terminal according to baby's face occlusion state
If baby's face is in occlusion state, alarm signal is sent to monitor terminal；Because when the face of baby is blocked
Afterwards, it is easy to cause the asphyxia of baby, if the duration is long, cerebral anoxia weight is gently then caused to baby then to baby harness next life
The threat of life, therefore can will detect that baby's face continues 5~10 seconds to send alarm signal to monitor terminal after blocking.
Preferably, the specifying information of baby's face occlusion state can be sent；Infant eyes can be sent or nose hides
Gear, mouth or nose block still ear or mouth and blocked.
Wherein, monitor terminal can be mobile phone, flat board and computer, and alarm signal can bind multiple monitor terminals, be easy to
After a certain guardian does not receive or have ignored alarm signal in time, other guardians can have found to alert in time, adopt in time
Measure is taken, ensures the safety of baby.
Step 6, transmission baby image to monitor terminal
When alerting generation, the baby image in alarm time section is sent to monitor terminal.Monitor terminal can select
Automatic real-time reception baby image can select the automatic baby's figure received before and after the alarm device transmission alarm signal time
Picture, save internal memory；Monitor terminal can also select to check baby image manually.
In summary, specific case used herein is based on a kind of baby sleep monitoring system and its method to the present invention
It is set forth, the explanation of above example is only intended to help the method and its core concept for understanding the present invention；Meanwhile for
Those of ordinary skill in the art, according to the thought of the present invention, change is had in specific embodiments and applications
Place, in summary, this specification content should not be construed as limiting the invention, and protection scope of the present invention should be with appended power
Profit requires to be defined.
Claims (10)
- A kind of 1. baby sleep monitoring system, it is characterised in that including：Harvester, data processing equipment, alarm device；Its In,The harvester is used to gather baby image；The data processing equipment electrically connects the harvester, for receiving the baby image, according to the baby image Extract sleeping condition of baby and baby's face occlusion state；The alarm device electrically connects the data processing equipment, for being sent according to the result of the data processing equipment Alarm signal is to monitor terminal.
- 2. system according to claim 1, it is characterised in that also including data transmission device；Wherein, the data transfer Device electrically connects the data processing equipment, for transmitting the baby image according to the result of the data processing equipment To monitor terminal.
- 3. system according to claim 2, it is characterised in that the monitor terminal includes mobile phone, flat board and computer.
- 4. system according to claim 2, it is characterised in that the data processing equipment includes image storage unit, figure As processing unit, sleep state judging unit and facial occlusion state judging unit；Wherein,Described image memory cell is used to receive the baby image of the harvester and stored；Described image processing unit connects described image memory cell, for reading the baby image in described image memory cell And handled；The sleep state judging unit connects described image processing unit, for being passed through according to the baby image after processing Eye state detection algorithm judges sleeping condition of baby；The facial occlusion state judging unit connection described image processing unit, for according to the baby image after processing The occlusion state of baby's face face is judged by face detection algorithm.
- 5. system according to claim 4, it is characterised in that described image processing unit is additionally operable to be slept according to the baby The baby image that dormancy state and baby's face occlusion state are read in described image memory cell is transmitted to the number According to transmitting device.
- A kind of 6. baby sleep monitoring method, it is characterised in that including：Gather baby image；Sleeping condition of baby and baby's face occlusion state are extracted according to the baby image；Determine whether to send alarm signal to monitor terminal according to the sleeping condition of baby and baby's face occlusion state.
- 7. according to the method for claim 6, it is characterised in that sleeping condition of baby, bag are extracted according to the baby image Include：Baby's face-image is identified according to the baby image；Infant eyes image is obtained by the face-image；Baby's eye state is determined according to the eyes image；The sleeping condition of baby is judged according to the eye state.
- 8. according to the method for claim 6, it is characterised in that baby's face is extracted according to the baby image and blocks shape State, including：Baby's face-image is identified according to the baby image；Baby's face face are extracted according to baby's face-image；Judge baby's face occlusion state according to baby's face face.
- 9. according to the method for claim 6, it is characterised in that the monitor terminal includes mobile phone, flat board and computer.
- 10. according to the method for claim 6, it is characterised in that according to the sleeping condition of baby and baby face After occlusion state determines transmission alarm signal to monitor terminal, in addition to：The baby image is sent to the monitor terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711237755.3A CN107832744A (en) | 2017-11-30 | 2017-11-30 | A kind of baby sleep monitoring system and its method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711237755.3A CN107832744A (en) | 2017-11-30 | 2017-11-30 | A kind of baby sleep monitoring system and its method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107832744A true CN107832744A (en) | 2018-03-23 |
Family
ID=61646713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711237755.3A Withdrawn CN107832744A (en) | 2017-11-30 | 2017-11-30 | A kind of baby sleep monitoring system and its method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107832744A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472481A (en) * | 2019-07-01 | 2019-11-19 | 华南师范大学 | A kind of sleeping position detection method, device and equipment |
| CN112069949A (en) * | 2020-08-25 | 2020-12-11 | 开放智能机器（上海）有限公司 | Artificial intelligence-based infant sleep monitoring system and monitoring method |
| CN112220621A (en) * | 2020-10-14 | 2021-01-15 | 内蒙古民族大学 | Upper gastrointestinal hemorrhage nursing device for digestive system department |
| CN112712020A (en) * | 2020-12-29 | 2021-04-27 | 文思海辉智科科技有限公司 | Sleep monitoring method, device and system |
| CN112971730A (en) * | 2021-04-20 | 2021-06-18 | 广东德泷智能科技有限公司 | Infant sleep health data monitoring system based on block chain |
| CN113298062A (en) * | 2021-07-28 | 2021-08-24 | 宁波星巡智能科技有限公司 | Infant sleep activity state detection method, device, equipment and medium |
| CN113408477A (en) * | 2021-07-07 | 2021-09-17 | 广州安倍思科技有限公司 | Infant sleep monitoring system, method and equipment |
| CN116386278A (en) * | 2023-03-20 | 2023-07-04 | 武汉星巡智能科技有限公司 | Intelligent recognition reminding method, device and equipment based on infant sleeping posture |
| CN117173784A (en) * | 2023-08-30 | 2023-12-05 | 武汉星巡智能科技有限公司 | Infant turning-over action detection method, device, equipment and storage medium |
-
2017
- 2017-11-30 CN CN201711237755.3A patent/CN107832744A/en not_active Withdrawn
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472481B (en) * | 2019-07-01 | 2024-01-05 | 华南师范大学 | Sleeping gesture detection method, device and equipment |
| CN110472481A (en) * | 2019-07-01 | 2019-11-19 | 华南师范大学 | A kind of sleeping position detection method, device and equipment |
| CN112069949A (en) * | 2020-08-25 | 2020-12-11 | 开放智能机器（上海）有限公司 | Artificial intelligence-based infant sleep monitoring system and monitoring method |
| CN112220621A (en) * | 2020-10-14 | 2021-01-15 | 内蒙古民族大学 | Upper gastrointestinal hemorrhage nursing device for digestive system department |
| CN112220621B (en) * | 2020-10-14 | 2021-09-10 | 内蒙古民族大学 | Upper gastrointestinal hemorrhage nursing device for digestive system department |
| CN112712020A (en) * | 2020-12-29 | 2021-04-27 | 文思海辉智科科技有限公司 | Sleep monitoring method, device and system |
| CN112712020B (en) * | 2020-12-29 | 2024-05-31 | 文思海辉智科科技有限公司 | Sleep monitoring method, device and system |
| CN112971730A (en) * | 2021-04-20 | 2021-06-18 | 广东德泷智能科技有限公司 | Infant sleep health data monitoring system based on block chain |
| CN112971730B (en) * | 2021-04-20 | 2021-08-06 | 广东德泷智能科技有限公司 | Infant sleep health data monitoring system based on block chain |
| CN113408477A (en) * | 2021-07-07 | 2021-09-17 | 广州安倍思科技有限公司 | Infant sleep monitoring system, method and equipment |
| CN113298062A (en) * | 2021-07-28 | 2021-08-24 | 宁波星巡智能科技有限公司 | Infant sleep activity state detection method, device, equipment and medium |
| CN116386278B (en) * | 2023-03-20 | 2023-11-10 | 武汉星巡智能科技有限公司 | Intelligent recognition reminding method, device and equipment based on infant sleeping posture |
| CN116386278A (en) * | 2023-03-20 | 2023-07-04 | 武汉星巡智能科技有限公司 | Intelligent recognition reminding method, device and equipment based on infant sleeping posture |
| CN117173784A (en) * | 2023-08-30 | 2023-12-05 | 武汉星巡智能科技有限公司 | Infant turning-over action detection method, device, equipment and storage medium |
| CN117173784B (en) * | 2023-08-30 | 2024-05-07 | 武汉星巡智能科技有限公司 | Infant turning-over action detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832744A (en) | A kind of baby sleep monitoring system and its method | |
| CN104091408B (en) | Infant sleeping posture intelligent identification method and device based on thermal infrared imaging | |
| CN107958572A (en) | A kind of baby monitoring systems | |
| US10786183B2 (en) | Monitoring assistance system, control method thereof, and program | |
| US9141761B2 (en) | Apparatus and method for assisting user to maintain correct posture | |
| CN105354985B (en) | Fatigue driving monitoring apparatus and method | |
| CN110477925A (en) | A kind of fall detection for home for the aged old man and method for early warning and system | |
| Sigari | Driver hypo-vigilance detection based on eyelid behavior | |
| CN109887238B (en) | Tumble detection system and detection alarm method based on vision and artificial intelligence | |
| CN112712020B (en) | Sleep monitoring method, device and system | |
| CN113257440A (en) | ICU intelligent nursing system based on patient video identification | |
| CN117690159B (en) | Infant groveling and sleeping monitoring method, device and equipment based on multi-mode data fusion | |
| WO2017098265A1 (en) | Method and apparatus for monitoring | |
| CN109325474A (en) | A kind of abnormal state detection method of couple of special caregiver of need | |
| CN108010579A (en) | Health monitoring system | |
| CN107943527A (en) | The method and its system of electronic equipment is automatically closed in sleep | |
| CN113345177A (en) | Self-service book borrowing and returning system based on face recognition | |
| JP6822326B2 (en) | Watching support system and its control method | |
| CN117173784B (en) | Infant turning-over action detection method, device, equipment and storage medium | |
| CN114120214A (en) | Quilt kicking detection method, air conditioner control method and detection device | |
| CN109727426A (en) | A kind of mechanical garage personnel are strayed into monitoring identification early warning system and detection method | |
| JP2004192551A (en) | Eye opening/closing determining apparatus | |
| CN113076799A (en) | Drowning identification alarm method, drowning identification alarm device, drowning identification alarm platform, drowning identification alarm system and drowning identification alarm system storage medium | |
| CN107959756A (en) | The system and method for electronic equipment are automatically closed in sleep | |
| WO2008020458A2 (en) | A method and system to detect drowsy state of driver |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180323 |
|
| WW01 | Invention patent application withdrawn after publication |