CN107958572B - Baby monitoring system - Google Patents
Baby monitoring system Download PDFInfo
- Publication number
- CN107958572B CN107958572B CN201711241516.5A CN201711241516A CN107958572B CN 107958572 B CN107958572 B CN 107958572B CN 201711241516 A CN201711241516 A CN 201711241516A CN 107958572 B CN107958572 B CN 107958572B
- Authority
- CN
- China
- Prior art keywords
- infant
- baby
- video
- sensor
- average value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
- G08B21/0208—Combination with audio or video communication, e.g. combination with "baby phone" function
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a baby monitoring system comprising: the device comprises a video acquisition device, a sensor, an embedded device, a first memory and a display terminal; the video acquisition device is used for acquiring a baby video in real time; the sensor is used for acquiring environmental data around the infant in real time; the embedded device is connected with the video acquisition device and the sensor and is used for receiving the baby video acquired by the video acquisition device and the environmental data around the baby acquired by the sensor and analyzing and processing the data; the first memory is connected with the embedded device and used for storing the baby video received by the embedded device; and the display terminal is used for displaying the analysis processing result of the embedded device. The baby monitoring system provided by the invention can monitor real-time video data of a baby and the environmental parameters of the baby, extract alarm information and inform a guardian of danger information in time.
Description
Technical Field
The invention relates to the technical field of monitoring, in particular to a baby monitoring system.
background
The monitoring service has a long history and is widely applied to the field of security protection. In recent years, with the rapid development of digital image processing technology and digital circuit technology, both dynamic monitoring and field monitoring have become practical, and have relatively high sensitivity and reliability. The monitoring system is visual, convenient and rich in information content, and is widely applied to various fields such as financial systems, traffic systems, public security systems, education systems, medical systems and the like.
With the development of audio-video and network technologies, more and more monitoring technologies are applied in home monitoring, such as baby monitoring. Infant care has been an important concern for every family. At present, most families mainly depend on families to watch children at all times, which causes inconvenience for work, rest and the like of parents of the infants, and therefore, the infant monitoring system is applied to the infants. Infant monitoring systems are very popular in developed countries abroad and have gradually risen in China in recent years. The infant monitoring system can provide a safer protection measure for families, and the safety of infants is ensured.
The existing infant monitoring technology usually collects images of an infant in real time, and transmits the images to corresponding electronic equipment for display so as to facilitate the monitoring personnel to check the images, and the monitoring personnel judge whether the infant is in a sleep-wake state or not by checking the monitoring images.
Disclosure of Invention
Therefore, in order to solve the technical defects and shortcomings of the prior art, the invention provides a baby monitoring system.
specifically, an embodiment of the present invention provides a baby monitoring system, including: the device comprises a video acquisition device, a sensor, an embedded device, a first memory and a display terminal; wherein the content of the first and second substances,
The video acquisition device is used for acquiring a baby video in real time;
The sensor is used for acquiring environmental data around the infant in real time;
The embedded device is connected with the video acquisition device and is used for receiving the baby video acquired by the video acquisition device and the environmental data around the baby acquired by the sensor and analyzing and processing the data;
the first memory is connected with the embedded device and used for storing the baby video received by the embedded device;
And the display terminal is used for displaying the analysis processing result of the embedded device.
In one embodiment of the invention, the sensors include a temperature sensor and a humidity sensor.
in one embodiment of the invention, the temperature sensor comprises an ambient temperature sensor and a human body infrared temperature sensor; wherein the content of the first and second substances,
The ambient temperature sensor is used for measuring the ambient temperature around the baby;
The human body infrared temperature sensor is used for measuring the body temperature of the infant.
In one embodiment of the invention, a method according to an embedded device includes: the device comprises a video input interface, a sensor input interface, a processor, a video input/output interface and a data output interface; wherein the content of the first and second substances,
The video input interface is used for receiving the baby video acquired by the video acquisition device;
The sensor input interface is used for receiving the ambient temperature, the body temperature of the baby and the ambient humidity of the baby collected by the humidity sensor;
the processor is respectively connected with the video input interface and the sensor input interface and is used for compressing the received infant video and analyzing and processing the received environmental temperature, the received infant body temperature and the received environmental humidity to form first analysis data;
the video input/output interface is connected with the processor and is used for outputting the compressed baby video to the first memory;
the data output interface is connected with the processor and used for outputting the first analysis data to the display terminal.
in one embodiment of the present invention, the embedded device further comprises a second memory, connected to the processor, for storing local audio.
in an embodiment of the present invention, the embedded device further includes an audio output interface, where the audio output interface is connected to the processor, and is used for the processor to send the local audio read from the second memory to the audio output interface for playing.
in one embodiment of the invention, the processor is further configured to analyze the received baby video to form second analysis data; wherein the second analysis data comprises an infant sleeping state and an infant face shielding state.
in one embodiment of the invention, the second analysis data further comprises alarm information determined according to the sleep state of the infant and the facial occlusion state of the infant.
In an embodiment of the present invention, the data output interface is further configured to output the alarm information to the display terminal.
In an embodiment of the present invention, the display terminal is a mobile phone, a tablet, or a computer.
Based on this, the invention has the following advantages:
1) the infant monitoring system provided by the invention extracts whether the infant is awake or not or whether the infant is shielded by foreign matters and bedding or not according to the real-time image data of the infant, and informs a guardian of the dangerous scene in time.
2) the baby monitoring system provided by the invention can monitor the environmental parameters such as temperature and humidity around the baby in time, and is beneficial to a guardian to adjust the environmental parameters at any time.
other aspects and features of the present invention will become apparent from the following detailed description, which proceeds with reference to the accompanying drawings. It is to be understood, however, that the drawings are designed solely for purposes of illustration and not as a definition of the limits of the invention, for which reference should be made to the appended claims. It should be further understood that the drawings are not necessarily drawn to scale and that, unless otherwise indicated, they are merely intended to conceptually illustrate the structures and procedures described herein.
drawings
The following detailed description of embodiments of the invention will be made with reference to the accompanying drawings.
FIG. 1 is a schematic view of an infant monitoring system according to an embodiment of the present invention;
Fig. 2 is a schematic diagram of an embedded device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of image recognition of the eyes and nose areas in an infant face image according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of coordinate sampling points of eyes and nose in an infant face image according to an embodiment of the present invention;
FIG. 5 is a schematic view of an image of a head of an infant in a lying position according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an image of a head of an infant with a side 45-degree lying posture according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an image of a head of an infant in a side-lying posture according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of an image of a head in a climbing posture according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a 2-valued image of a facial region of an infant according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of the position coordinates of the five sense organs of a facial region of an infant according to an embodiment of the present invention;
fig. 11 is a schematic diagram of a triangle graph constructed by position coordinates of five sense organs of an infant according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
example one
Referring to fig. 1 and fig. 2, fig. 1 is a schematic diagram of a baby monitoring system according to an embodiment of the present invention, and fig. 2 is a schematic diagram of an embedded device according to an embodiment of the present invention. The system 10 includes: the system comprises a video acquisition device 11, a sensor 12, an embedded device 13, a first memory 14 and a display terminal 15; wherein the content of the first and second substances,
the video acquisition device 11 is used for acquiring a baby video in real time;
the sensor 12 is used for acquiring environmental data around the infant in real time;
The embedded device 13 is connected to the video acquisition device 11, and is configured to receive the infant video acquired by the video acquisition device 11 and the environmental data around the infant acquired by the sensor 12, and perform analysis processing;
the first memory 14 is connected to the embedded device 13 and is used for storing the baby video received by the embedded device 13;
The display terminal 15 is used for displaying the analysis processing result of the embedded device 13.
Further, the sensor 12 includes a temperature sensor and a humidity sensor.
further, the temperature sensor comprises an environment temperature sensor and a human body infrared temperature sensor; wherein the content of the first and second substances,
The ambient temperature sensor is used for measuring the ambient temperature around the baby;
the human body infrared temperature sensor is used for measuring the body temperature of the infant.
Further, the embedded device 13 includes: a video input interface 131, a sensor input interface 132, a processor 134, a video input output interface 136, and a data output interface 137; the video input interface 131 is configured to receive the baby video acquired by the video acquisition device 11; the sensor input interface 132 is used for receiving the ambient temperature, the body temperature of the infant and the humidity around the infant collected by the humidity sensor; the processor 134 is respectively connected to the video input interface 131 and the sensor input interface 132, and configured to compress the received infant video, and analyze and process the received ambient temperature, the received infant body temperature, and the received ambient humidity to form first analysis data; the video input/output interface 136 is connected to the processor 134, and is configured to output the compressed baby video to the first memory 14; the data output interface 137 is connected to the processor 134, and is configured to output the first analysis data to the display terminal 15.
Further, the embedded device 13 further comprises a second memory, which is connected to the processor 134 for storing local audio.
Further, the embedded device 13 further includes an audio output interface 135, and the audio output interface 135 is connected to the processor 134, so that the processor 134 sends the local audio read from the second memory to the audio output interface 135 for playing.
Further, the processor 134 is further configured to analyze the received baby video to form second analysis data; wherein the second analysis data comprises an infant sleeping state and an infant face shielding state.
further, the second analysis data further comprises alarm information determined according to the sleep state of the infant and the facial shielding state of the infant.
further, the data output interface 137 is also configured to output alarm information to the display terminal 15.
further, the display terminal 15 includes a mobile phone, a tablet, and a computer.
in the embodiment, the information of the baby can be monitored in real time by acquiring the baby monitoring video, the temperature and the humidity of the surrounding environment of the baby and the body temperature of the baby in real time; in addition, the baby sleeping state and the baby face shielding state are extracted by analyzing the baby monitoring video, the problem that a guardian stares the monitoring video in real time for preventing a baby dangerous scene is solved, and the effect that the guardian can work safely during baby monitoring is achieved.
example two
Referring to fig. 1 again, the present embodiment further illustrates the baby monitoring system based on the above embodiments. The system comprises: the device comprises a video acquisition device 11, a sensor 12, an embedded device 13, a first memory 14 and a display terminal 15.
the video acquisition device 11 is a camera which can rotate 360 degrees for shooting and is arranged above the crib for monitoring baby images in real time; or three cameras are respectively arranged above the crib and at two sides of the crib to monitor baby videos in real time; or two 180-degree cameras are respectively arranged at two sides of the crib to monitor baby images in real time.
The sensor 12 is an ambient temperature sensor, a human body infrared temperature sensor and an ambient humidity sensor. The environment temperature sensor and the environment humidity sensor can be selected in a plurality of manners, are respectively arranged around the crib, can be selected and set according to the requirements of a user, and can acquire the temperature value and the humidity value of the environment around the baby in real time. The human body infrared temperature sensor is used for measuring the body temperature of the infant and monitoring the body temperature of the infant in real time.
referring to fig. 2 again, the baby video collected by the video collecting device 11 is input to the processor 134 through the video input interface 131; the temperature and humidity around the infant and the body temperature of the infant, which are acquired by the sensor 12, are input to the processor 134 through the sensor input interface 132; the processor 134 performs compression processing after receiving the infant video, and outputs the compressed infant video through the video input/output interface 136; the processor 134 receives the temperature and humidity around the infant and the body temperature of the infant, and then determines to form first analysis data. The first analysis data is a high temperature alarm formed when the temperature around the infant is too high (the user can manually set the temperature around the infant, or a default value can be selected, preferably the default value can be selected as 27 degrees centigrade), a low temperature alarm formed when the temperature around the infant is too low (the user can manually set the temperature around the infant, or a default value can be selected, preferably the default value can be selected as 25 degrees centigrade), a high humidity alarm formed when the humidity around the infant is too high (the user can manually set the temperature around the infant, or a default value can be selected as 60%), a low humidity alarm formed when the humidity around the infant is too low (the user can manually set the temperature around the infant, or a default value can be selected as 30%), and an infant fever alarm formed when the body temperature of the infant is too high. Since the body temperature of the baby can be increased due to the fact that the quilt is often too thick when the baby sleeps, the heating alarm can be formed when the body temperature of the baby exceeds 37.5 degrees.
the processor 134 is further configured to analyze the received baby video to form second analysis data, where the second analysis data is a baby sleeping state, a baby facial occlusion state, and alarm information.
wherein, the process of judging the sleep state of the infant is as follows:
Step 1, extracting a baby face image from a baby video;
Step 2, preprocessing the face image of the baby;
21) Carrying out gray processing on the infant face image;
Graying of an image is a process of equalizing RGB component values of colors. Since the value range of RGB is 0-255, the gray level is 256 levels, that is, the gray image can express 256 colors.
The gray stretching is carried out after the gray processing of the infant face image, namely, the mapping method is used for separating the original compressed histogram into a plurality of parts, namely, the gray stretching is carried out, and the clearer infant face image is obtained.
22) Performing median filtering on the infant face image;
The median filtering method is a non-linear image smoothing method, and is characterized by that the gray levels of all pixels in a sliding window are sorted, and the central pixel of the window is substituted by its intermediate value, and if there are even number of pixels in the window, the average of two intermediate values is taken.
23) carrying out histogram equalization on the infant face image;
Let f (i, j), g (i, j) (i is 1, 2 … M; j is 1, 2 … N) be the original infant face image and the processed infant face image, respectively, the gray scale range of the infant face image is [0, 255], and the histogram equalization method is specifically as follows:
(231) obtaining a gray level histogram of the original image [ f (i, j) ] M×N, and representing the gray level histogram by a 256-dimensional vector h f;
(232) the gray level distribution probability of the original baby face image is obtained from h f and is recorded as p f
where N F is M × N (M, N are the length and width of the image, respectively) which is the total number of pixels of the image;
(233) Calculating the cumulative distribution probability of each gray value of the face image, and recording as p a
where p a (0) is made 0.
(231) Performing histogram equalization calculation, wherein the pixel values of the processed image are as follows:
g(i,j)＝255·pa(k) (3)
24) Binaryzation is carried out on the face image of the baby
the method adopts a maximum between-class variance threshold segmentation method to carry out binarization on the face image of the baby.
Step 3, determining the characteristics of eyes and a nose in the face image of the baby, and positioning the areas of the eyes and the nose;
referring to fig. 3, fig. 3 is a schematic diagram illustrating image recognition of the eyes and nose areas in an infant face image according to an embodiment of the present invention.
the projection method is adopted to reduce the face image of the baby to a small area with only eyes and nose, and the area with the eyes and the nose is roughly positioned.
And denoising and enhancing the regional images of the eyes and the nose. From a vertical distribution, with the nose under the eyes, searching from top to bottom, the area of the eyes and nose can be located.
the areas of the eyes and nose are accurately located using a template matching method.
The traditional template matching method is used for matching in the whole image, and not only is the operation amount large, but also the interference factors are large. In the invention, because the areas of the eyes and the nose are roughly positioned and the influence of organs such as eyebrows, mouths and the like is avoided, the images are continuously projected horizontally and vertically, and the intersection points of the images are positioned as the positions of the eyes and the nose, thereby improving the accuracy.
Referring to fig. 4, fig. 4 is a schematic diagram of coordinate sampling points of eyes and nose in a baby face image according to an embodiment of the present invention.
Step 4, calculating a first relative distance;
selecting N points on the upper eyelid edge of the eye area, and respectively calculating the upper eyelid coordinate average value of the N points;
selecting X points in the nose area, and respectively calculating the average value of the nose coordinates of the X points;
and subtracting the average value of the nose coordinates from the average value of the upper eyelid coordinates to obtain a first relative distance.
Step 5, calculating a second relative distance;
selecting M points at the lower eyelid edge of the eye area, and respectively calculating the lower eyelid coordinate average value of the M points;
and subtracting the average value of the nose coordinates from the average value of the lower eyelid coordinates to obtain a second relative distance.
step 6, calculating an absolute distance;
Respectively taking P points at the upper eyelid edge and the lower eyelid edge;
Respectively calculating a first average value of P points of the upper eyelid edge and a second average value of P points of the lower eyelid edge;
and subtracting the second average value from the first average value to obtain the absolute distance.
Step 7, judging the eye state;
the eye state formula is as follows:
wherein, T 1 is the second relative distance, T 2 is the absolute distance, T 3 is the first relative distance, OFFSET 1 and OFFSET 2 are the error compensation of gathering the human face image, and the error compensation needs manual setting because of the difference of machine.
and (4) substituting the first relative distance, the second relative distance, the absolute distance and the preset error compensation obtained in the step (4-6) into the eye state formula to obtain the value of theta.
when theta is smaller and is closer to 0, the eyes are closed, and the theoretical minimum value of theta is 0 under an ideal condition;
Conversely, the larger θ is, the closer to 1, the more open the eye is.
Since the value θ with which the eyes are open varies from person to person due to individual differences among infants, a threshold value may be set in advance for each individual infant, and θ may be detected by comparing the threshold value with θ.
so far, the eyes of the baby can be judged to be in an open state or a closed state through the value of theta.
if the eye state is the eye opening state and lasts for 5-10 seconds, determining that the infant is in the waking state; because the eyes of the infant can be opened temporarily during the sleeping process, but the eyes can be closed quickly to continue sleeping, the eyes can be opened for 5 seconds, 6 seconds, 7 seconds, 8 seconds and 9 seconds to judge whether the infant is awake, the short time easily causes misjudgment, the long time easily fails to detect the awake state of the infant, and the infant can turn over or climb after waking, and easily falls off the bed to cause irreparable injury.
If the eye state is the eye closing state and lasts for 60-300 seconds, determining that the infant is in the sleeping state; because each infant does not sleep for the same time, the duration may be defined manually based on the characteristics of the infant.
Wherein, the judgment process of the facial shielding state of the infant is as follows:
please refer to fig. 5 to 11 together, wherein fig. 5 is a schematic diagram of a head image of a lying-down infant according to an embodiment of the present invention; FIG. 6 is a schematic diagram of an image of a head of an infant with a side 45-degree lying posture according to an embodiment of the present invention; FIG. 7 is a schematic diagram of an image of a head of an infant in a side-lying posture according to an embodiment of the present invention; FIG. 8 is a schematic diagram of an image of a head in a climbing posture according to an embodiment of the present invention; FIG. 9 is a schematic diagram of a 2-valued image of a facial region of an infant according to an embodiment of the present invention; FIG. 10 is a schematic diagram of the position coordinates of the five sense organs of a facial region of an infant according to an embodiment of the present invention; fig. 11 is a schematic diagram of a triangle graph constructed by the position coordinates of the five sense organs of the infant according to an embodiment of the present invention; the specific execution steps are as follows:
step 1, identifying five sense organs.
the video of the baby collected by the video collecting device 11 forms three baby images, which are respectively a front top view, a left side view and a right side view. Among them, the lying posture is shown in fig. 5, the side 45-degree lying posture is shown in fig. 6, the side lying posture is shown in fig. 7, and the climbing posture is shown in fig. 8.
the method comprises the steps of determining an infant head image by adopting a face recognition algorithm (the algorithm is a general algorithm and is not described herein any more), and extracting the infant face image by adopting the face recognition algorithm (the algorithm is a general algorithm and is not described herein any more).
the facial image of the infant distinguishes the area of the five sense organs of the infant through color comparison of the five sense organs and the surrounding area. And performing region 2-valued operation on the infant face image by utilizing the difference of colors of the infant five sense organ region and the area around the infant to obtain a 2-valued image of the infant face region, and extracting the infant face five sense organs. The method specifically comprises the following steps: for the eye region of the infant, a gray level image is collected according to the face image, and as the complexion of the eye beads and the skin is different, a threshold value can be set according to the mean value of the gray level value, and 2-valued operation is performed, for example: the eye drop is black, the gray value is more than 200, and the skin is yellow, the gray value is less than 100. Thus setting 150 to a threshold, colors greater than 150 are labeled 1, and the remainder are labeled 0. Finally, 2-value speech images of the eye region of the infant can be obtained, so that the eyes can be respectively obtained. The method can be used in the nostril region, the ear-hole region and the mouth region. The final results are shown in fig. 9.
And step 32, judging occlusion.
and calibrating the position coordinates of the five sense organs according to the five sense organs of the face of the infant extracted in the step 31. Position coordinates of the eye region corner point 41, the nose region center point 42, the mouth region center point 43 and mouth corner 44, and the ear region center point 45 are calibrated, as shown in fig. 10.
And constructing a face triangular graph according to the position coordinates calibrated by the five sense organs. A first triangular graph 51 of the eye region and the nose region is formed by connecting two corner points of the eye region and the center of the nose region, a second triangular graph 52 of the nose region and the mouth region is formed by connecting two corner points of the nose region and the center of the mouth region, and a third triangular graph 53 of the ear region and the mouth region is formed by connecting two center points of the ear region and the center of the mouth region, as shown in fig. 11.
As shown in fig. 10, the facial occlusion determination is performed by the constructed triangle graph, and the specific method is as follows:
Step 321) judging the body posture;
And constructing a triangle graph in the three images of the front top view, the left side view and the right side view of the head image of the baby. The left and right side views are collectively referred to as side views.
if only the front top view has a triangle figure which can be constructed, the infant body is in the lying posture;
If the triangular graph which can be constructed exists in the front top view and the triangular graph which can be constructed exists in one of the side views, the infant body is in a 45-degree lying posture;
If only one side image has a triangle image which can be constructed, the infant body is in the lying-on-side posture;
if no triangle graph can be constructed, the baby body is in the prone posture.
step 322), judging the shielding and shielding position
and judging the occlusion of the face of the infant and the occlusion position according to the body lying posture of the infant in the step 321 through the triangular graph in the head image of the infant.
if the baby is in the prone posture, the face of the baby is completely shielded;
If the infant is in a lying posture, identifying and judging the facial occlusion of the infant by adopting a front top view;
a) If the first triangle graph 51 can not be constructed, the occlusion of the eyes or the nose of the baby is illustrated;
b) If there is no second triangular graphic 52 that can be constructed, this indicates occlusion of the baby's mouth or nose;
c) if there is no third triangular graphic 53 that can be constructed, it indicates that the infant is occluded from the ear or mouth;
if the lying posture is the side 45 degrees, identifying by adopting a side view and a top view image of the constructed triangular graph;
d) If neither the side view nor the top view has the first triangular pattern 51 that can be constructed, it is illustrated that the eyes or the nose of the infant are blocked;
e) If neither the side view nor the top view has a second triangular graphic 52 that can be constructed, this illustrates occlusion of the baby's mouth or nose;
f) If neither the side view nor the top view has a third triangular pattern 53 that can be constructed, this illustrates occlusion of the infant's ear or mouth;
If the lying posture is the side lying posture, the side images are adopted for identifying and judging the facial occlusion
g) if the first triangle graph 51 can not be constructed, the occlusion of the eyes or the nose of the baby is illustrated;
h) If there is no second triangular graphic 52 that can be constructed, this indicates occlusion of the baby's mouth or nose;
i) without a third triangular graphic 53 that could be constructed, this would indicate occlusion of the infant's ear or mouth.
So far, the shielding state of the baby face can be judged.
the processor 134 determines whether to form alarm information according to the determined sleep state and facial occlusion state of the infant. If the baby is in the waking state, forming a baby waking alarm; if the baby face is in a shielding state, a baby face shielding alarm is formed. Because the face of the baby is blocked, the baby is easily suffocated, if the duration is too long, the brain hypoxia is caused to the baby, the life threat is brought to the baby, and therefore the infant face blocking alarm can be formed by continuing for 5-10 seconds after judging that the face of the baby is blocked.
Preferably, specific information of the infant face shielding state may be formed; i.e. an alert can be sent whether the infant is eye or nose occluded, mouth or nose occluded or ear or mouth occluded.
a second memory is connected to the processor 134 for storing local audio. After the infant wake-up alarm is formed in the processor 134, the processor 134 reads the local audio in the second memory and plays the local audio through the audio output interface, so as to sooth the emotion of the infant. Whether to play music can be set in advance by a user.
the first memory 14 is connected to the video input/output interface 136, and receives and stores the baby video compressed by the processor 134 through the video input/output interface 136.
the data output interface 137 is connected to the processor 134, and receives and outputs the temperature and humidity around the infant, the body temperature of the infant, the first analysis data, and the second analysis data.
The display terminal 15 may be a mobile phone, a tablet, and a computer. The display terminal 15 is connected to the data output interface 137, and the user can view the temperature and humidity around the infant, the body temperature of the infant, the first analysis data and the second analysis data at the display terminal 15. When an alarm occurs, the alarm may include a high temperature alarm, a low temperature alarm, a high humidity alarm, a low humidity alarm, a heating alarm, a waking alarm, a facial occlusion alarm, and the like, and the alarm information is actively sent to the display terminal 15, so that the user can be reminded of performing processing operations. The user can bind the alarm information to the display terminals 15, so that when one guardian does not receive or ignore the alarm information in time, other guardians can find the alarm in time and take measures in time to ensure the safety of the baby.
the user can monitor the video of the baby in real time through the display terminal 15, and can also call the video monitored by the baby. The processor 134 retrieves and decompresses the baby video in the second memory through the video input/output interface 136, and transmits the decompressed baby video to the display terminal 15 through the data output interface. When an alarm occurs, the video of the baby within the alarm time period is actively transmitted to the display terminal 15. The display terminal 15 can select to automatically receive the baby video in real time or can select to automatically receive the baby video before and after the alarm forming time, so that the memory is saved; the display terminal 15 may also select to view the baby image manually.
in summary, the present invention is explained based on a baby monitoring system by using specific examples, and the above description of the embodiments is only used to help understanding the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention, and the scope of the present invention should be subject to the appended claims.
Claims (8)
1. An infant monitoring system, comprising: the device comprises a video acquisition device, a sensor, an embedded device, a first memory and a display terminal; wherein the content of the first and second substances,
the video acquisition device is used for acquiring a baby video in real time;
The sensor is used for acquiring environmental data around the infant in real time;
the embedded device is connected with the video acquisition device and the sensor and is used for receiving the baby video acquired by the video acquisition device and the environmental data around the baby acquired by the sensor and analyzing and processing the data;
the first memory is connected with the embedded device and used for storing the baby video received by the embedded device;
The display terminal is used for displaying the analysis processing result of the embedded device,
the embedded device includes: the device comprises a video input interface, a sensor input interface, a processor, a video input/output interface and a data output interface; wherein the content of the first and second substances,
the video input interface is used for receiving the baby video acquired by the video acquisition device;
The sensor input interface is used for receiving the ambient temperature, the body temperature of the infant and the ambient humidity of the infant acquired by the sensor;
The processor is respectively connected with the video input interface and the sensor input interface and is used for compressing the received infant video and analyzing and processing the received environmental temperature, the received infant body temperature and the received environmental humidity to form first analysis data;
The video input/output interface is connected with the processor and is used for outputting the compressed baby video to the first memory;
the data output interface is connected with the processor and used for outputting the first analysis data to the display terminal; the processor is further used for analyzing and processing the received baby video to form second analysis data; wherein the second analysis data comprises an infant sleeping state and an infant face shielding state;
the process for judging the sleep state of the infant comprises the following steps:
Step 1, extracting a baby face image from a baby video;
step 2, preprocessing the face image of the baby;
step 3, determining the characteristics of eyes and a nose in the face image of the baby, and positioning the areas of the eyes and the nose;
Step 4, calculating a first relative distance:
Selecting N points on the upper eyelid edge of the eye area, respectively calculating the upper eyelid coordinate average value of the N points, selecting X points in the nose area, respectively calculating the nose coordinate average value of the X points, and subtracting the nose coordinate average value from the upper eyelid coordinate average value to obtain a first relative distance;
step 5, calculating a second relative distance:
Selecting M points at the lower eyelid edge of the eye area, respectively calculating the lower eyelid coordinate average value of the M points, and subtracting the nose coordinate average value from the lower eyelid coordinate average value to obtain a second relative distance;
step 6, calculating the absolute distance:
Respectively taking P points at the upper eyelid edge and the lower eyelid edge, respectively calculating a first average value of the P points at the upper eyelid edge and a second average value of the P points at the lower eyelid edge, and subtracting the second average value from the first average value to obtain an absolute distance;
Step 7, judging the eye state;
the calculation formula of the eye state is as follows:
Wherein T 1 represents the second relative distance, T 2 represents the absolute distance, T 3 represents the first relative distance, OFFSET 1 and OFFSET 2 represent error compensation of collected face images, and for manual setting, θ represents the eye opening and closing degree, and the smaller θ is, the more closed the eyes are;
wherein, the infant face shelters from the state judgement process and includes:
Step a: identifying five sense organs:
Three infant images are formed through the infant video collected by the video collecting device, and are respectively a front top view, a left side view and a right side view; determining an infant head image by adopting a face recognition algorithm, and extracting an infant face image by adopting the face recognition algorithm; distinguishing the facial image of the infant from the facial image of the infant by comparing the color of the five sense organs with that of the surrounding area;
Step b: and (3) shielding judgment:
Calibrating the position coordinates of the five sense organs; constructing triangular graphs in three images of a front top view, a left side view and a right side view of the head image of the baby; and judging the occlusion and occlusion position of the infant face through a triangular graph in the infant head image.
2. the system of claim 1, wherein the sensor comprises a temperature sensor and a humidity sensor.
3. the system of claim 2, wherein the temperature sensor comprises an ambient temperature sensor and a human infrared temperature sensor; wherein the content of the first and second substances,
the ambient temperature sensor is used for measuring the ambient temperature around the baby;
The human body infrared temperature sensor is used for measuring the body temperature of the infant.
4. The system of claim 3, wherein the embedded appliance further comprises a second memory coupled to the processor for storing local audio.
5. the system of claim 4, wherein the embedded device further comprises an audio output interface, and the audio output interface is connected to the processor and is configured to enable the processor to send the local audio read from the second memory to the audio output interface for playing.
6. the system of claim 5, wherein the second analysis data further comprises alarm information determined according to the sleep state of the infant and the facial occlusion state of the infant.
7. the system of claim 6, wherein the data output interface is further configured to output the alarm information to the display terminal.
8. the system of claim 1, wherein the display terminal is a cell phone, a tablet, or a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711241516.5A CN107958572B (en) | 2017-11-30 | 2017-11-30 | Baby monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711241516.5A CN107958572B (en) | 2017-11-30 | 2017-11-30 | Baby monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107958572A CN107958572A (en) | 2018-04-24 |
| CN107958572B true CN107958572B (en) | 2019-12-10 |
Family
ID=61962054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711241516.5A Active CN107958572B (en) | 2017-11-30 | 2017-11-30 | Baby monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107958572B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108615333A (en) * | 2018-05-25 | 2018-10-02 | 朱利 | Infant asphyxia early warning system based on artificial intelligence and method |
| CN109567820A (en) * | 2018-11-27 | 2019-04-05 | 广州绿桦环保科技有限公司 | A kind of dormancy management method, apparatus and system |
| CN111023355A (en) * | 2019-11-04 | 2020-04-17 | 佛山市云米电器科技有限公司 | Multifunctional fan |
| JP7489248B2 (en) | 2020-02-06 | 2024-05-23 | 新東ホールディングス株式会社 | Information processing system, information processing method, and information processing program |
| 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 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306304A (en) * | 2011-03-25 | 2012-01-04 | 杜利利 | Face occluder identification method and device |
| CN104091408A (en) * | 2014-05-09 | 2014-10-08 | 郑州轻工业学院 | Infant sleeping posture intelligent identification method and device based on thermal infrared imaging |
| CN104217529A (en) * | 2014-08-27 | 2014-12-17 | 东北大学 | Intelligent infant monitoring system and method based on temperature, humidity and images |
| CN105844245A (en) * | 2016-03-25 | 2016-08-10 | 广州市浩云安防科技股份有限公司 | Fake face detecting method and system for realizing same |
| CN106056079A (en) * | 2016-05-31 | 2016-10-26 | 中国科学院自动化研究所 | Image acquisition device and facial feature occlusion detection method |
| CN106230959A (en) * | 2016-08-09 | 2016-12-14 | 西安科技大学 | A kind of intelligence baby monitoring system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH033080A (en) * | 1989-05-31 | 1991-01-09 | Fujitsu Ltd | Corresponding preprocessing system based upon image construction |
-
2017
- 2017-11-30 CN CN201711241516.5A patent/CN107958572B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306304A (en) * | 2011-03-25 | 2012-01-04 | 杜利利 | Face occluder identification method and device |
| CN104091408A (en) * | 2014-05-09 | 2014-10-08 | 郑州轻工业学院 | Infant sleeping posture intelligent identification method and device based on thermal infrared imaging |
| CN104217529A (en) * | 2014-08-27 | 2014-12-17 | 东北大学 | Intelligent infant monitoring system and method based on temperature, humidity and images |
| CN105844245A (en) * | 2016-03-25 | 2016-08-10 | 广州市浩云安防科技股份有限公司 | Fake face detecting method and system for realizing same |
| CN106056079A (en) * | 2016-05-31 | 2016-10-26 | 中国科学院自动化研究所 | Image acquisition device and facial feature occlusion detection method |
| CN106230959A (en) * | 2016-08-09 | 2016-12-14 | 西安科技大学 | A kind of intelligence baby monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 基于多视频窗口的疲劳驾驶监测***研究;王万军;《中国优秀硕士学位论文全文数据库 信息科技辑》;20120731;I138-1893 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107958572A (en) | 2018-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958572B (en) | Baby monitoring system | |
| US9338409B2 (en) | System and method for home health care monitoring | |
| CN104091408B (en) | Infant sleeping posture intelligent identification method and device based on thermal infrared imaging | |
| CN106022209A (en) | Distance estimation and processing method based on face detection and device based on face detection | |
| CN111931733B (en) | Human body posture detection method based on depth camera | |
| CN107832744A (en) | A kind of baby sleep monitoring system and its method | |
| CN112712020B (en) | Sleep monitoring method, device and system | |
| WO2017098265A1 (en) | Method and apparatus for monitoring | |
| CN114926957B (en) | Infant monitoring system and method based on intelligent home | |
| CN108711452A (en) | The health state analysis method and system of view-based access control model | |
| CN110870771A (en) | Image detection method and image detection device for determining posture of user | |
| CN108010579A (en) | Health monitoring system | |
| CN114937242A (en) | Sleep detection early warning method and device | |
| WO2023040577A1 (en) | Method and system for intelligent management and control of use of screen terminal by child | |
| KR101741904B1 (en) | Image-processing-based heartrate measuring method and, newborn baby image providing system | |
| CN108717872A (en) | Health analysis method and system based on face, hard recognition and big data | |
| CN208092911U (en) | A kind of baby monitoring systems | |
| CN113963424B (en) | Infant asphyxia or sudden death early warning method based on single-order face positioning algorithm | |
| CN117690159B (en) | Infant groveling and sleeping monitoring method, device and equipment based on multi-mode data fusion | |
| KR20150077846A (en) | Safety monitoring system for a infant | |
| CN114120214A (en) | Quilt kicking detection method, air conditioner control method and detection device | |
| WO2020118882A1 (en) | Method, apparatus and smart device for monitoring study status | |
| CN113392715A (en) | Chef cap wearing detection method | |
| WO2018235628A1 (en) | Monitoring assistance system, control method therefor, and program | |
| Choe et al. | Sleep analysis using motion and head 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191112 Address after: 518108 2F, building 2, Yuanling Industrial Zone, Shangwu community, Shiyan street, Bao'an District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Baichuan Security Technology Co., Ltd Address before: 710065 No. 86 Leading Times Square (Block B), No. 2, Building No. 1, Unit 22, Room 12202, No. 51, High-tech Road, Xi'an High-tech Zone, Shaanxi Province Applicant before: Xi'an CREE Sheng Creative Technology Limited |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 518000 2nd floor, building 2, Yuanling Industrial Zone, Shangwu community, Shiyan street, Bao'an District, Shenzhen City, Guangdong Province Patentee after: Shenzhen Ruilian Technology Co.,Ltd. Address before: 518108 2nd floor, building 2, Yuanling Industrial Zone, Shangwu community, Shiyan street, Bao'an District, Shenzhen City, Guangdong Province Patentee before: Shenzhen Baichuan Security Technology Co.,Ltd. |