The content of the invention
Therefore, to solve technological deficiency and deficiency existing in the prior art, the present invention proposes a kind of baby monitoring systems.
Specifically, a kind of baby monitoring systems that one embodiment of the invention proposes, including:Video acquisition device, sensing
Device, embedded equipment, first memory and display terminal;Wherein,
The video acquisition device is used to gather baby's video in real time;
The sensor is used for the environmental data for gathering baby periphery in real time;
The embedded equipment connects the video acquisition device, includes the video acquisition device collection for receiving
The environmental data on the baby periphery of baby's video and sensor collection, and analyzed and processed;
The first memory connects the embedded equipment, the baby received for storing the embedded equipment
Video;
The display terminal is used for the analysis and processing result for showing the embedded equipment.
In one embodiment of the invention, the sensor includes temperature sensor and humidity sensor.
In one embodiment of the invention, the temperature sensor includes environment temperature sensor and human body infrared temperature
Sensor;Wherein,
The environment temperature sensor is used to measure the environment temperature around baby;
The human body infrared temperature sensor is used to measure infant temperature.
In one embodiment of the invention, included according to embedded equipment:Video input interface, sensor input connect
Mouth, processor, video input and output interface and data output interface;Wherein,
The video input interface is used for the baby's video for receiving the video acquisition device collection;
The sensor input, which is used to receive, includes the environment temperature, the infant temperature and the humidity sensor
Baby's ambient humidity of device collection;
The processor connects the video input interface and the sensor input respectively, for by the institute of reception
State baby's video to be compressed, and the environment temperature of reception, the infant temperature and the ambient humidity are analyzed
Processing forms the first analysis data;
The video input and output interface connects the processor, for exporting compressed baby's video to institute
State first memory;
The data output interface connects the processor, whole to the display for exporting the first analysis data
End.
In one embodiment of the invention, the embedded equipment further includes second memory, the second memory
The processor is connected, for storing local audio.
In one embodiment of the invention, the embedded equipment further includes audio output interface, the audio output
Interface connects the processor, for sending out the local audio read from the second memory for the processor
Send to the audio output interface to play.
In one embodiment of the invention, the processor is additionally operable to carry out baby's video of reception at analysis
Reason forms the second analysis data;Wherein, the second analysis data include sleeping condition of baby and baby's face occlusion state.
In one embodiment of the invention, the second analysis data are further included according to sleeping condition of baby and baby face
The warning information that portion's occlusion state determines.
In one embodiment of the invention, the data output interface is additionally operable to export the warning information to described
Display terminal.
In one embodiment of the invention, the display terminal is mobile phone, tablet or computer.
Based on this, the present invention possesses following advantage:
1) baby monitoring systems proposed by the present invention according to baby's realtime image data extract baby whether wake up or
Whether baby is blocked by foreign matter bedding, and the danger scene is notified guardian in time.
2) baby monitoring systems proposed by the present invention can monitor the environmental parameters such as the temperature humidity around baby in time, favorably
Environmental parameter is adjusted at any time in guardian.
By the detailed description below with reference to attached drawing, other side of the invention and feature become obvious.But it should know
Road, which is only the purpose design explained, not as the restriction of the scope of the present invention, this is because it should refer to
Appended claims.It should also be noted that unless otherwise noted, it is not necessary to which scale attached drawing, they only try hard to concept
Ground illustrates structure and flow described herein.
Embodiment one
Fig. 1 and Fig. 2 are referred to, Fig. 1 is a kind of schematic diagram of baby monitoring systems provided in an embodiment of the present invention, and Fig. 2 is
A kind of schematic diagram of embedded equipment provided in an embodiment of the present invention.The system 10 includes:Video acquisition device 11, sensor
12nd, embedded equipment 13, first memory 14 and display terminal 15;Wherein,
The video acquisition device 11 is used to gather baby's video in real time;
The sensor 12 is used for the environmental data for gathering baby periphery in real time;
The embedded equipment 13 connects the video acquisition device 11, includes the video acquisition device 11 for receiving
The environmental data on the baby periphery of baby's video and the sensor 12 collection of collection, and analyzed and processed;
The first memory 14 connects the embedded equipment 13, the institute received for storing the embedded equipment 13
State baby's video;
The display terminal 15 is used for the analysis and processing result for showing the embedded equipment 13.
Further, the sensor 12 includes temperature sensor and humidity sensor.
Further, the temperature sensor includes environment temperature sensor and human body infrared temperature sensor;Wherein,
The environment temperature sensor is used to measure the environment temperature around baby;
The human body infrared temperature sensor is used to measure infant temperature.
Further, the embedded equipment 13 includes:Video input interface 131, sensor input 132, processing
Device 134, video input and output interface 136 and data output interface 137;Wherein, the video input interface 131 is used to receive institute
State baby's video of the collection of video acquisition device 11;The sensor input 132, which is used to receive, includes the environment
Baby's ambient humidity of temperature, the infant temperature and humidity sensor collection;The processor 134 connects respectively
The video input interface 131 and the sensor input 132, for baby's video of reception to be compressed,
The environment temperature of reception, the infant temperature and the ambient humidity are subjected to analyzing and processing and form the first analysis data;
The video input and output interface 136 connects the processor 134, for exporting compressed baby's video to described
First memory 14;The data output interface 137 connects the processor 134, for exporting the first analysis data extremely
The display terminal 15.
Further, the embedded equipment 13 further includes second memory, and the second memory connects the processing
Device 134, for storing local audio.
Further, the embedded equipment 13 further includes audio output interface 135, and the audio output interface 135 connects
The processor 134 is connect, for the local audio read from the second memory being sent out for the processor 134
Send to the audio output interface 135 to play.
Further, the processor 134 is additionally operable to baby's video of reception carrying out analyzing and processing formation second
Analyze data;Wherein, the second analysis data include sleeping condition of baby and baby's face occlusion state.
Further, the second analysis data are further included determines according to sleeping condition of baby and baby's face occlusion state
Warning information.
Further, the data output interface 137 is additionally operable to export warning information to the display terminal 15.
Further, the display terminal 15 includes mobile phone, tablet and computer.
The present embodiment, can be real by gathering baby's monitor video, baby's surrounding environment humiture and infant temperature in real time
When monitor baby information;In addition the present embodiment extracts out sleeping condition of baby and baby's face by analyzing baby's monitor video
Occlusion state, solves the problems, such as guardian to prevent baby's danger scene and stares at monitor video in real time, realize monitoring
The effect that people can work contentedly in baby monitor.
Embodiment two
Referring again to Fig. 1, the present embodiment further illustrates baby monitoring systems on the basis of above-described embodiment.
The system includes:Video acquisition device 11, sensor 12, embedded equipment 13, first memory 14 and display terminal 15.
Video acquisition device 11 is the camera that can be rotated by 360 ° shooting, is arranged at the top real time monitoring of infanette
Baby image;Or three cameras are used, it is respectively arranged at top and the both sides real time monitoring baby's video of infanette;Or
Using two 180 degree cameras, the both sides for being respectively arranged at infanette monitor baby image in real time.
Sensor 12 is environment temperature sensor, human body infrared temperature sensor and ambient humidity sensor.Environment temperature
Sensor and ambient humidity sensor can be chosen multiple, be respectively arranged at around infanette, can be according to the demand of user
Choose and set, gather the temperature value and humidity value of baby's surrounding environment in real time.Human body infrared temperature sensor is used to measure baby
The body temperature of youngster, monitors the body temperature of baby in real time.
Referring again to Fig. 2, baby's video that video acquisition device 11 gathers passes through the input of video input interface 131 to place
Manage device 134;The humiture and infant temperature on the baby periphery that sensor 12 gathers pass through the input of sensor input 132 to place
Manage device 134;Processor 134 is compressed processing after receiving baby's video, and compressed baby's video is passed through video input
Output interface 136 exports;Processor 134 receive baby periphery humiture and infant temperature after carry out judge formed first point
Analyse data.First analysis data be when the temperature on baby periphery it is excessive (user can manually set, and can also select default value,
Preferably default value can be chosen for 27 degrees Celsius) and the high temperature alarm that is formed, when the temperature on baby periphery is too low, (user can be with
Manually set, default value can also be selected, preferably default value can be chosen for 25 degrees Celsius) and the low temperature alarm of formation, when
The humidity on baby periphery is excessive, and (user can manually set, and can also select default value, and preferably default value can be chosen for
60%) and formed high humidity alarm, when the humidity on baby periphery it is too low (user can manually set, and can also select default value,
Preferably default value can be chosen for the low humidity alarm 30%) formed, when baby's fever that the hyperpyrexia of baby is formed
Alarm.Due to baby quilt during sleep often cover it is too thick be likely to result in body temperature rise, can select to work as infants
Fever alarm is formed when temperature is more than 37.5 degree.
Processor 134 is additionally operable to baby's video of reception carrying out analyzing and processing formation the second analysis data, the second analysis
Data are sleeping condition of baby, baby's face occlusion state and warning information.
Wherein, the deterministic process of sleeping condition of baby is as follows:
Step 1, extract baby's face image in baby's video;
Step 2, pre-process baby's face image;
21) gray processing processing is carried out to baby's face image;
Image gray processing is exactly the process for making the RGB component value of colour equal.Since the value range of RGB is 0~255,
So the rank of gray scale is 256 grades, i.e. gray level image can show 256 kinds of colors.
It will carry out gray scale stretching after the processing of baby's face image gray processing, i.e., it is straight what is compressed originally with the method for mapping
Side's figure separates, that is, gray scale stretching, the baby's face image become apparent from.
22) medium filtering is carried out to baby's face image;
Median filtering method is a kind of nonlinear image smoothing method, and each pixel grey scale in a sliding window is arranged
Sequence, the original gray scale of window center pixel is replaced with its intermediate value, if there is even number pixel in window, takes the flat of two medians
.
23) histogram equalization is carried out to baby's face image;
If f (i, j), g (i, j) (i=1,2 ... M;J=1,2 ... N), it is respectively the baby after former baby's face image and processing
Youngster's face image, the gray processing scope of baby's face image is [0,255], and histogram equalization method is specific as follows:
(231) artwork [f (i, j)] is soughtM×NGrey level histogram, if with 256 dimension vectorial hfRepresent;
(232) by hfThe intensity profile probability of former baby's face image is sought, is denoted as pf, then
Wherein, NF=M × N (M, N are respectively the length and width of image) is total number of pixels of image;
(233) the cumulative distribution probability of each gray value of facial image is calculated, is denoted as pa, then have
Wherein, p is madea(0)=0.
(231) carry out histogram equalization calculating, the pixel value of image to after handling be:
G (i, j)=255pa(k) (3)
24) binaryzation is carried out to baby's face image
Using maximum between-cluster variance thresholding method to baby's face image binaryzation.
Step 3, determine the feature of eyes and nose in baby's face image, positions the region of eyes and nose;
Fig. 3 is referred to, Fig. 3 is the administrative division map of eyes and nose in a kind of baby's face image provided in an embodiment of the present invention
As identification schematic diagram.
Baby's face image is narrowed down to the zonule of only eyes and nose, coarse positioning eyes and nose using sciagraphy
Region.
Denoising and enhancing processing are carried out to the area image of eyes and nose.It is distributed from vertical direction, nose is in eyes
In the following, searching for from top to bottom, the region of eyes and nose can be oriented.
The region of eyes and nose is accurately positioned using template matching method.
Traditional template matching method, is matched that not only operand is big but also disturbing factor is more in entire image.This hair
Because coarse localization goes out the region of eyes and nose in bright, and without the influence of the organs such as eyebrow, mouth, so right
Image continuously makees the horizontal and vertical position for projecting and taking its intersection point to be positioned as eyes and nose, improves accuracy rate.
Step 4 to step 6 refers to Fig. 4, eyes and nose in a kind of Fig. 4 baby's face images provided in an embodiment of the present invention
The coordinate sampled point schematic diagram of son.
Step 4, calculate the first relative distance;
N number of point is chosen at the upper eyelid edge of eye areas, counts the upper eyelid coordinate average value of N number of point respectively;
X point is chosen in nasal area, calculates the nose coordinate average value of X point respectively;
Upper eyelid coordinate average value is subtracted into nose coordinate and is averagely worth to the first relative distance.
Step 5, calculate the second relative distance;
M point is chosen at the lower eyelid edge of eye areas, counts the lower eyelid coordinate average value of M point respectively;
Lower eyelid coordinate average value is subtracted into nose coordinate and is averagely worth to the second relative distance.
Step 6, calculate absolute distance;
P point is respectively taken at upper eyelid edge and lower eyelid edge;
The second average value of the first average value of the P point at upper eyelid edge and the P point at lower eyelid edge is calculated respectively;
First average value is subtracted second and is averagely worth to absolute distance.
Step 7, judge eye state;
Eye state formula is as follows:
Wherein, T1For the second relative distance, T2For absolute distance, T3For the first relative distance, OFFSET1And OFFSET2For
The error compensation of facial image is gathered, error compensation is since the difference of machine is, it is necessary to manually set.
By the first relative distance obtained in step 4-6, the second relative distance, absolute distance and error set in advance
Compensation substitutes into eye state formula the value for obtaining θ.
When θ is smaller, closer to 0, illustrate that eyes more close, ideally, the theoretical minimum value of θ is 0;
Otherwise θ is bigger, closer to 1, illustrate that eyes are more opened.
Due to baby's individual difference, the θ values that eyes are opened vary with each individual, therefore, can be individual according to different babies, in advance
Threshold value is first set, θ is compared to detect with threshold value.
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 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 is for 5 seconds, 6 seconds, 7 seconds, 8 seconds and 9 seconds judge whether baby regains consciousness, the time is too short to be easy to cause erroneous judgement, overlong time
Easy missing inspection baby's waking state, can turn over or creep after baby regains consciousness, it is easy to fall under bed, cause irremediable
Injury.
If eye state is closed-eye state, and continues 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 define according to the characteristic manual setting of baby.
Wherein, baby's face occlusion state deterministic process is as follows:
According to baby's video extraction baby's face occlusion state, implement please also refer to Fig. 5 to Figure 11, Fig. 5 for the present invention
A kind of lying position baby head image schematic diagram that example provides;Fig. 6 is a kind of 45 degree of lying postures in side provided in an embodiment of the present invention
Gesture baby head image schematic diagram;Fig. 7 is a kind of lateral position baby head image schematic diagram provided in an embodiment of the present invention;Figure
8 climb prone position gesture head image schematic diagram for one kind provided in an embodiment of the present invention;Fig. 9 is a kind of baby provided in an embodiment of the present invention
2 value image schematic diagrames of youngster's facial zone;Figure 10 is a kind of face mark of baby's facial zone provided in an embodiment of the present invention
Fixed position coordinates schematic diagram;Figure 11 is a kind of triangle of baby's face position coordinate structure provided in an embodiment of the present invention
Schematic diagram;Specific execution step is as follows:
Step 1, face identification.
The baby's video gathered by video acquisition device 11 forms three baby images, and three images are respectively that front is bowed
View, left surface figure and right hand view.Wherein, lying position as shown in figure 5,45 degree of side lying posture gesture as shown in fig. 6, lateral position
As shown in fig. 7, it is as shown in Figure 8 to climb prone position gesture.
Face recognition algorithms (algorithm repeats no more here for general-purpose algorithm) are used to determine baby head figure
Picture, uses face recognition algorithms (algorithm repeats no more here for general-purpose algorithm), extracts 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 baby's face-image 2 value of region operation, 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, since 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, 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.Finally obtain that the results are shown in Figure 9.
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, 42 position coordinates of nasal region central point, 44 position coordinates of mouth region central point 43 and the corners of the mouth, area of ear
45 position coordinates of domain central point, as shown in Figure 10.
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 11.
As shown in Figure 10, facial shadowing is carried out 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, illustrates 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, illustrates 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 there is structure;
If d) the first triangle 51 that side view and top view can not built, illustrate that infant eyes or nose hide
Gear;
If e) the second triangle 52 that side view and top view can not built, illustrate that baby's mouth or nose hide
Gear;
If f) the 3rd triangle 53 that side view and top view can not built, illustrate that baby ear or mouth hide
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, illustrates that baby ear or mouth block.
So far it may determine that the occlusion state of baby's face.
Processor 134 determines whether to form alarm letter according to the sleeping condition of baby judged, baby's face occlusion state
Breath.If baby is in waking state and forms baby wakeup alarm;If baby's face is in occlusion state, forms baby's face and block
Alarm.Because after the face of baby is blocked, it is easy to the asphyxia of baby is caused, if the duration is long, gently to baby
Youngster causes cerebral anoxia weight then to carry out the threat of life to baby harness, therefore can will determine that out that baby's face continues 5~10 after blocking
Second blocks alarm to form baby's face.
Preferably, the specifying information of baby's face occlusion state can be formed;Infant eyes can be sent or nose hides
Gear, mouth or nose block the alarm that still ear or mouth block.
Second memory connection processing device 134, for storing local audio.Accused when forming baby wakeup in processor 134
After police, the local audio that processor 134 is read in second memory is played by audio output interface, the mood of baby soothing.
Whether playing music user can set in advance.
First memory 14 connect video input and output interface 136, by the compressed baby's video of processor 134 by regarding
Frequency input/output interface 136 receives and stores.
137 connection processing device 134 of data output interface, the humiture on reception baby periphery, infant temperature, the first analysis number
According to and the second analysis data and export.
Display terminal 15 can be mobile phone, tablet and computer.Display terminal 15 connects data output interface 137, is showing
15 user of terminal can check humiture, infant temperature, the first analysis data and the second analysis data on baby periphery.Work as generation
After alarm, alarm can include high temperature alarm, low temperature alarm, high humidity alarm, low humidity alarm, fever alarm, wake up alarm and face
Alarm etc. is blocked in portion, and warning information actively is sent to display terminal 15, may remind the user that operation of handling it.User can be with
Warning information is bound into multiple display terminals 15, easy to after a certain guardian does not receive or have ignored warning information in time,
Other guardians can have found to alert in time, take measures in time, ensure the safety of baby.
User can monitor baby's video in real time by display terminal 15, can also transfer the video of baby's monitoring.Processing
Device 134 is transferred baby's video in second memory by video input and output interface 136 and is decompressed, and passes through data output interface
Send to display terminal 15.When alerting generation, actively baby's video in alarm time section is sent to display terminal 15.It is aobvious
Show that terminal 15 can select automatic real-time reception baby video or can select to receive the baby for alerting and being formed before and after the time automatically
Youngster's video, saves memory;Display terminal 15 can also select to check baby image manually.
In conclusion specific case used herein is set forth the present invention based on a kind of baby monitoring systems,
The explanation of above example is only intended to help to understand method and its core concept of the invention;Meanwhile for the one of this area
As technical staff, according to the thought of the present invention, there will be changes in specific embodiments and applications, to sum up institute
State, this specification content should not be construed as limiting the invention, protection scope of the present invention should using appended claim as
It is accurate.