CN113974933A - Infant quilt kicking detection method and device, electronic equipment and medium - Google Patents
Infant quilt kicking detection method and device, electronic equipment and medium Download PDFInfo
- Publication number
- CN113974933A CN113974933A CN202111264485.1A CN202111264485A CN113974933A CN 113974933 A CN113974933 A CN 113974933A CN 202111264485 A CN202111264485 A CN 202111264485A CN 113974933 A CN113974933 A CN 113974933A
- Authority
- CN
- China
- Prior art keywords
- marker
- infant
- head
- area
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims description 65
- 239000003550 marker Substances 0.000 claims abstract description 237
- 238000000034 method Methods 0.000 claims abstract description 43
- 230000007958 sleep Effects 0.000 claims description 21
- 238000010276 construction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 239000011358 absorbing material Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 18
- 230000008569 process Effects 0.000 description 13
- 239000000463 material Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000010365 information processing Effects 0.000 description 4
- 230000000474 nursing effect Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000031700 light absorption Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F5/00—Orthopaedic methods or devices for non-surgical treatment of bones or joints; Nursing devices; Anti-rape devices
Landscapes
- Health & Medical Sciences (AREA)
- Nursing (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Vascular Medicine (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the technical field of video monitoring, solves the technical problem that in the prior art, the quilt kicking of an infant is difficult to detect in the video monitoring process, and provides a method, a device, electronic equipment and a medium for detecting the quilt kicking of the infant. The method comprises the steps of acquiring an effective identification area for detecting the infant kicking; acquiring the current distance between the head of the infant and the marker in a sleeping state and the current effective area of the marker in real time, wherein the current effective area is the area of the marker in the effective identification area; according to the initial effective mark area and the current effective mark area; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
Description
The application is a divisional application of an invention patent application with application number 202110945621.7, which is filed at 18.8.2021 and has the invention name of an intelligent infant kicking detection method, device, electronic equipment and medium.
Technical Field
The invention relates to the technical field of video monitoring, in particular to a method and a device for detecting infant kicking, electronic equipment and a medium.
Background
In an intelligent home system, a video monitoring system is a relatively important component and plays an important role in lightening the visual field of the intelligent home system. In the application of the intelligent home system, the video monitoring system can be used for remotely monitoring infants to prevent safety accidents.
In the application scene of remotely monitoring infants through the video monitoring system, the common monitoring in the day can still meet the requirements, but once the infants enter the night, the visual field definition of the video monitoring system is reduced to some extent, so that the monitoring difficulty is improved, and the monitoring effect is unsatisfactory at the moment. However, the infant often moves with hands and feet during sleeping at night, so that the problem of cold caused by quilt kicking is caused. The infant is weak in physique and cannot arrive in position in the monitoring process, so that the problem that the infant catches a cold due to quilt kicking off sometimes occurs, but a better detection method is not provided for the phenomenon, and the technical problem to be solved in the industry is urgently solved.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, an electronic device and a medium for detecting infant kicking, so as to solve the technical problem in the prior art that it is difficult to detect that an infant kicks off a quilt in a video monitoring process.
The technical scheme adopted by the invention is as follows:
the invention provides a method for detecting infant kicking quilt, which comprises the following steps:
acquiring an effective identification area for detecting the infant kicking;
acquiring the current distance between the head of the infant and the marker in a sleeping state and the current effective area of the marker in real time, wherein the current effective area is the area of the marker in the effective identification area;
according to the initial effective mark area and the current effective mark area; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
Preferably, the acquiring of the valid identification area for infant kicking detection includes:
acquiring initial position information of the head of an infant in a sleeping state and initial position information of the marker, wherein the initial position information comprises a center coordinate and size data of a detection frame representing a detection target;
determining a width value and a height value of the effective identification area according to the initial position information of the infant head and the respective size data of the initial position information of the marker;
and establishing the effective identification area according to the central coordinate of the head of the infant and the combination of the width value and the height value.
Preferably, the acquiring, in real time, a current distance between the head of the infant and the marker in the sleep state and a current effective area of the marker, where the current effective area is an area of the marker located in the effective identification area includes:
acquiring a current head image of the head of an infant and a current marker image of a marker in a sleep state in real time;
obtaining the current distance according to the head center coordinate information of the detection frame for representing and detecting the current head image and the marker center coordinate information of the detection frame for representing and detecting the current marker image;
and obtaining the current effective mark area of the mark according to the mutual position relation between the mark area information of the detection frame for representing and detecting the current mark image and the effective identification area.
Preferably, the establishing the effective identification area according to the center coordinates of the infant's head in combination with the width value and the height value comprises:
according to the coordinate value of the head initial center coordinate information, the size data of the head initial range and the size information of the marker initial range, the formula
Obtaining a vertex P1 of the construction rectangle by formula
Obtaining a vertex P2 of the construction rectangle by formula
Obtaining a vertex P3 of the construction rectangle by formula
Obtaining a vertex P4 of the construction rectangle;
constructing the effective recognition region with vertices P1, P2, P3, and P4;
wherein x is the abscissa of the head center point, y is the ordinate of the head center point, a, b, c and m are constants, a is greater than 0 and less than m, b is greater than or equal to 0 and less than or equal to 1, c is greater than 0 and less than or equal to 1, W1 is the width value of the head range corresponding to the head identification area, and H2 is the height value of the marker range corresponding to the marker identification area.
Preferably, the acquiring of initial position information of the head of the infant in the sleeping state and initial position information of the marker, wherein the initial position information includes center coordinates and size data of a detection frame representing a detection target:
acquiring a target image and a preset feature image imaged by a marker in a sleeping state of an infant;
detecting the face contour of the infant on the target image to obtain initial position information of the head of the infant corresponding to the face contour of the infant;
and carrying out marker contour detection on the target image according to the characteristic image of the marker to obtain initial position information of the marker.
Preferably, the acquiring, in real time, a current distance between the head of the infant and the marker in the sleep state and a current effective area of the marker, where the current effective area is an area of the marker located in the effective identification area includes:
acquiring a current head image of the head of an infant and a current marker image of a marker in a sleep state in real time;
obtaining the current distance according to the head center coordinate information of the detection frame for representing and detecting the current head image and the marker center coordinate information of the detection frame for representing and detecting the current marker image;
and obtaining the current effective mark area of the mark according to the mutual position relation between the mark area information of the detection frame for representing and detecting the current mark image and the effective identification area.
Preferably, the method further comprises the step of determining the current valid flag area according to the initial valid flag area; and/or, according to the initial distance and the current distance, outputting information whether the infant kicks off a quilt or not comprises:
acquiring an area threshold value used for kicking the effective area of the identified marker and a distance threshold value of the distance between the marker and the head of the infant;
if the ratio of the current effective mark area to the initial effective mark area is less than or equal to the area threshold value; and/or;
and if the current distance is greater than the distance threshold value, outputting the information of the infant quilt kicking.
Preferably, the marker is made of light absorption material capable of absorbing 940nm infrared light source.
The invention also provides an infant quilt kicking detection device for executing the infant quilt kicking intelligent detection method, which comprises the following steps:
an identification area acquisition module: the method comprises the steps of obtaining a valid identification area for detecting infant kicking;
a data acquisition module: the system is used for acquiring the current distance between the head of the infant and the marker in a sleeping state and the current effective area of the marker in real time, wherein the current effective area is the area of the marker in the effective identification area;
a data processing module: the system is used for judging whether the current effective mark area is larger than the initial effective mark area or not; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
The present invention also provides an electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of any of the above.
The invention also provides a medium having stored thereon computer program instructions which, when executed by a processor, implement the method of any of the above.
In conclusion, the beneficial effects of the invention are as follows:
according to the infant kicking detection method, the infant kicking detection device, the electronic equipment and the medium, whether the infant kicks or not is determined according to the relation between the initial distance and the actual distance between the head position of the infant and the marker in the sleeping state of the infant and/or according to the initial effective identification area and the real-time effective identification area of the marker in the effective identification area, and if the infant kicks or not, prompt information is sent to a nursing person.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, without any creative effort, other drawings may be obtained according to the drawings, and these drawings are all within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of an intelligent detection method for infant kicking quilt in embodiment 1 of the present invention;
fig. 1-1 is a schematic structural diagram of an effective detection area in an example of the first embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating acquisition of initial position information of a head and initial position information of a marker in embodiment 1 of the present invention;
fig. 3 is a schematic flow chart of acquiring an initial effective identification area of a marker in embodiment 1 of the present invention;
fig. 4 is a schematic flowchart of a process of acquiring current position information of a head and current position information of a marker in embodiment 1 of the present invention;
fig. 5 is a schematic flow chart of acquiring a current effective identification area of a marker in embodiment 1 of the present invention;
fig. 6 is a schematic flow chart illustrating the determination of infant kicking quilt in embodiment 1 of the present invention;
fig. 7 is a block diagram of an infant quilt kicking intelligent detection device in embodiment 2 of the present invention;
fig. 8 is a schematic structural diagram of an electronic device in embodiment 3 of the present invention.
Reference numerals of fig. 1 to 8:
1. an active identification area; 11. a first identification area; 12. a second identification area; 2. a head recognition area; 21. a head region; 3. a marker recognition zone; 31. a marker.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. In the description of the present invention, it is to be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. In case of conflict, the various features of the embodiments of the present invention may be combined with each other and are within the scope of the present invention.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of an infant kicking quilt intelligent detection method in embodiment 1 of the present invention. The intelligent detection method for the quilt kicked by the infant in the embodiment 1 of the invention comprises the following steps:
s1: acquiring initial position information of the head of an infant in a sleeping state and initial position information of a marker used for the infant to kick off the detected object;
specifically, the infant nursing machine (camera) nurses the infant in real time, judge whether the infant gets into the sleep state according to infant activity information, after the infant gets into the sleep, open the sleep monitoring mode, simultaneously, the very first time acquires the infant and carries out the initial position information of infant's head position after the sleep state, and be used for judging whether the infant plays the initial position information of the marker that is monitored, this marker is the article that can absorb specific wavelength, preferably the material preparation that can absorb infrared light source forms, thereby can utilize infrared camera to carry out real time monitoring to the infant at night, the marker can form specific pattern at the control picture, be convenient for detect, improve and detect the accuracy.
S2: determining an effective identification area for detecting the infant kicking, an initial distance between the infant head and the marker and an initial effective marker area of the marker according to the initial position information of the infant head and the initial position information of the marker;
specifically, at night after the infant falls asleep, under the condition that the infant just falls asleep and the cover is in a normal state, the user sends a request instruction for kicking the infant through the terminal, the device detects an initial head contour and an initial marker contour immediately after acquiring the request instruction, determines initial head position information and initial marker position information, sets an effective identification area according to the two information, and further determines the effective marker area of the marker in the effective identification area in the initial state.
Specifically, referring to fig. 1-1, in the initialization process, a marker 31 is previously disposed on a quilt used by an infant, where the marker 31 and the quilt may also be detachable structures, or the marker 31 is a pattern on the quilt, where the marker is a material that can absorb a certain specific wavelength, preferably a light-absorbing material that can absorb an infrared light source of 780nm to 1100nm, for example a material that can absorb an infrared light source of 940nm, so that when an infrared image of the infant is taken at night, the marker 31 presents a characteristic image; when an infant enters a sleep state, a camera of a nursing infant receives a request instruction for kicking a detected infant, the camera shoots an infrared image of the infant in an initial state in the sleep state, a head region 21 of the infant is detected by using an infant head detection model, a marker 31 is detected by using a marker detection model, the marker 31 and a minimum circumscribed rectangular frame of the head of the infant are extracted by using a minimum contour method, and a marker identification region 3 and a head identification region 2 are obtained; determining an effective identification area 1 according to the marker identification area 3 and the head identification area 2, wherein the effective identification area 1 comprises a first identification area 11 and a second identification area 12; specific determination methods of the effective identification area 1 include, but are not limited to, infrared images including head outline images and marks of infants and young children when the infants and young children sleep at night in an initial state photographed by a deviceA marker profile image, wherein the sizes of the head area 21 and the marker 31 are represented by the length and the width corresponding to the head identification area 2 and the marker identification area 3 in the infrared image respectively; obtaining an effective identification area 1 according to a preset generation rule of the effective identification area 1, and utilizing a formula
Obtaining the coordinates of the vertex P1 of the effective identification area 1, and using the formula
Obtaining the coordinates of the vertex P2 of the effective identification area 1 by using a formula
Obtaining the coordinates of the vertex P3 of the effective identification area 1 by using a formula
Obtaining the coordinates of a vertex P4 of the effective identification area 1, wherein x is the abscissa of the head central point C, y is the ordinate of the head central point C, a, b, C and m are constants, a is more than 0 and less than m, b is more than 0 and less than or equal to 1, C is more than 0 and less than or equal to 1, W1 is the width value of the head identification area 2, and H2 is the height value of the marker identification area 3; thereby obtaining a rectangular effective identification area consisting of vertices P1, P2, P3 and P4; such as: the width of the effective identification area 1 is 4 times the width of the head area 21 of the baby, the height of the effective identification area is determined to be 0.8 times the height of the marker, and the Y coordinates of P1 and P2 are symmetrical with respect to the Y coordinate of the center point of the baby head, then m is 4, b is 0.5, and c is 0.8; the width of the effective identification area 1 was 4 × W1, and the height of the effective identification area 1 was 0.8 × H2.
It should be noted that the determined effective identification area 1 is actually a data-fitting virtual fence, and the position information of the head area 21 of the infant and the position information of the marker 31 in the initially established virtual fence are acquired through the initially established virtual fence, and then whether the infant kicks off a quilt or not is monitored through the position information of the head area 21 of the infant and the position information of the marker 31 acquired in real time, and the area change condition of the marker 31 in the effective identification area.
S3: acquiring the current position information of the head and the current position information of the marker in real time;
s4: determining the current distance between the head of the infant and the marker and the current effective marker area of the marker according to the current position information of the head and the current position information of the marker;
specifically, with the kick detection function of the device being started, after the device initialization detection process is completed, the device continuously acquires the sleep state of the infant with reference to the initially detected parameters, detects current parameter information, specifically includes current head position information and current marker position information, and determines the relative relationship between the current head position information and the current marker position information and the area ratio of the marker in the effective identification area in the current state according to the current head position information and the current marker position information; thereby obtaining the parameter characteristics in two different states, namely an initial state and a current state.
S5: according to the initial effective mark area and the current effective mark area; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
Specifically, the relative position relationship between the initial head contour and the contour of the marker is determined by detecting the initial head contour and the contour of the marker, the effective identification area is determined by the initial head contour and the contour of the marker, the area ratio of the marker in the effective identification area in the initial state is determined, after initialization is completed, the current head contour and the contour of the marker of the infant are acquired in real time, the current position relationship between the head contour and the marker and the area ratio of the marker in the effective identification area in the current state are determined, and whether the infant kicks a quilt or not is determined by comparing the head position information and the marker position information in the two states; or the change of the area ratio of the markers in the two states in the effective identification area is compared to determine whether the infant kicks the quilt or not, and the two judgment indexes can be fused together, so that the detection precision of the detection of the infant kicking the quilt is improved through multi-dimensional index parameter acquisition. It should be further noted that, for how to specifically determine whether the infant lifts off the quilt by using the parameters, the detection sensitivity may be set according to the actual situation, in this embodiment, if a single distance index is adopted, it is determined that the infant has kicked off the quilt when the current distance is more than twice of the initial distance; it should be noted that, if the detection sensitivity is to be improved, the restriction condition may be lowered, for example, when the current distance is more than 1.5 times of the initial distance, it may be determined that the infant kicks off the quilt, otherwise, if the detection sensitivity is to be improved and lowered, the restriction condition may be raised, and when the current distance is more than 2.5 times of the initial distance, it may be determined that the infant kicks off the quilt, and the specific parameter setting may be determined in combination with the physical quality of the infant, the local air temperature condition, and the infant monitoring condition; more specifically, if the initial distance between the head of the infant and the marker is 20cm, and if the current distance between the head of the infant and the marker in the detected current state is 38cm, and the current distance 38cm is 1.9 times of the initial distance 20cm, it is determined that the infant has kicked off the quilt at the moment when the set condition is that the current distance is more than 1.5 times of the initial distance; if the set condition is that the current distance is more than twice of the initial distance, determining that the infant does not kick off the quilt temporarily; setting the condition to be more than 2.5 times of the initial distance, and judging that the infant does not kick off the quilt temporarily; moreover, a single marker area index can be adopted to determine whether the infant lifts off the quilt, and when the current effective marker area is less than 30% of the initial effective marker area, the infant can be judged to kick off the quilt; in this case, the sensitivity of the detection can be flexibly adjusted according to actual needs, and will not be described herein.
In addition to the above-mentioned determination of whether the infant kicks off the quilt or not by a single parameter index, a fusion of two determination indexes can be adopted to comprehensively determine whether the infant kicks off the quilt or not, and a simple fusion or a complex fusion can be adopted in the fusion process, so as to further improve the detection accuracyJudging that the infant has kicked off the quilt only when the accumulation is less than 30% of the initial effective mark area, for example, when the current distance is 45cm, the initial distance is 20cm, and the current distance is more than twice the initial distance, further detecting that the current effective mark area is 5cm2Initial effective mark area of 20cm2If the current effective mark area is less than 30% of the initial effective mark area, judging that the infant kicks off the quilt; the method integrates two judgment modes, and can effectively improve the detection accuracy. In addition, a complex fusion method can be adopted, and details are not repeated here.
Furthermore, under the condition that the quilt is judged to be kicked off by the infant, the device sends early warning information that the quilt is kicked off by the infant to the terminal of the user, so that the user is reminded to take care of the infant in time, the quilt is covered for the infant in time, and cold caused by catching a cold at night is avoided.
It should be noted that: in the image shot by the camera, the resolution is determined and the total size of the image is determined, that is, the pixel points included in the distance from the point to the point are not changed, even if the image is subjected to stretching deformation and other processing in the later period, the actual distance from the point to the point may be changed, but the number of the pixel points from the point to the point is not changed.
In one embodiment, referring to fig. 2, the S1 includes:
s11: acquiring an initial head image of the head and an initial marker image of the marker;
specifically, under the condition that the infant just falls asleep and the comforter is in a normal state, the user sends a request instruction for kicking the detected infant through the terminal, or the device generates the request instruction for kicking the detected infant according to the current detection state (sleep monitoring state), and the device enters an initialization detection process, specifically, the device acquires and acquires an initial infant head image and an initial marker image.
S12: obtaining initial position information of the head according to the initial head image, wherein the initial position information of the head comprises: head region information representing an initial range of the head and head initial center coordinate information representing a geometric center of the head;
s13: obtaining initial position information of the marker according to the initial position information of the marker, wherein the initial position information of the marker comprises: marker region information characterizing an initial range of the marker and marker initial center coordinate information characterizing geometric center coordinates of the marker.
Specifically, after an initial infant head image and an initial marker image are obtained, if the density distribution of an object is assumed to be uniform, the gravity center of the object is the geometric center of the object according to the fact that the geometric center of a planar object is a representative point; for this reason, in the present embodiment, an initial head center coordinate value is determined from an initial head image; and determining the central coordinate value of the initial marker according to the initial marker image, and respectively representing the initial head position information and the initial marker position information by the initial head central coordinate value and the initial marker central coordinate value. It should be further noted that, in the technical solution provided by the present invention, the position information may not be represented only by using the central coordinate value, and on the basis of not deviating from the substantial content of the present invention, a specific point location having a larger reference meaning in the infant head image and the initial marker image, such as a point location where the infant nose is located or an edge point location of the marker, may be selected to represent the position information of the infant head and the initial position information of the marker.
In one embodiment, referring to fig. 3, the S2 includes:
s21: determining the initial distance according to the coordinate value of the head initial center coordinate information and the coordinate value of the marker initial center coordinate information;
specifically, the initial distance is determined by calculating the distance formula between two points using the initial head center coordinate value and the initial marker center coordinate value, for example, the initial head center coordinate value is (8,12), the initial marker center coordinate value is (20,16), and the initial distance between the two points is 12.65 cm.
S22: obtaining the width value of the effective identification area detected by the infant kicking according to the coordinate value of the head initial center coordinate information and the size data representing the head initial range;
s23: obtaining the height value of the effective identification area detected by the infant kicking according to the size information representing the initial range of the marker and the initial central coordinate information of the marker of the geometric center of the marker;
s24: constructing a rectangle on the basis of the width value of the effective identification area and the height value of the effective identification area, wherein the width value and the height value respectively correspond to the length and the width of the rectangle, and the effective identification area is represented by the rectangle;
specifically, according to the infrared image of the infant in the initial state, which is shot by the device when the infant sleeps at night, including the head contour image and the marker contour image of the infant, the width and the height of the head identification area 2 corresponding to the head area 21 of the infant at that time are identified, and according to the initial marker image 31 at that time, the width (the direction of X in fig. 1-1) and the height (the direction of Y in fig. 1-1) of the marker identification area 3 corresponding to the marker 31 are obtained, and according to the information, the effective identification area and the initial effective marker area of the marker in the effective identification area are further determined.
In one embodiment, the S24 includes:
s241: according to the coordinate value of the head initial center coordinate information, the size data of the head initial range and the size information of the marker initial range, the formula
Obtaining a vertex P1 of the construction rectangle by formula
Obtaining a vertex P2 of the construction rectangle by formula
Obtaining a vertex P3 of the construction rectangle by formula
Obtaining a vertex P4 of the construction rectangle;
s242: constructing the effective recognition region with vertices P1, P2, P3, and P4;
wherein x is the abscissa of the head center point, y is the ordinate of the head center point, a, b, c and m are constants, a is greater than 0 and less than m, b is greater than or equal to 0 and less than or equal to 1, c is greater than 0 and less than or equal to 1, W1 is the width value of the head range corresponding to the head identification area, and H2 is the height value of the marker range corresponding to the marker identification area.
Specifically, referring to fig. 1-1, in the initialization process, a marker 31 is previously disposed on a quilt used by an infant, where the marker 31 and the quilt may also be detachable structures, or the marker 31 is a pattern on the quilt, where the marker is a material that can absorb a certain specific wavelength, preferably a light-absorbing material that can absorb an infrared light source of 780nm to 1100nm, for example a material that can absorb an infrared light source of 940nm, so that when an infrared image of the infant is taken at night, the marker 31 presents a characteristic image; when an infant enters a sleep state, a camera of a nursing infant receives a request instruction for kicking a detected infant, the camera shoots an infrared image of the infant in an initial state in the sleep state, a head region 21 of the infant is detected by using an infant head detection model, a marker 31 is detected by using a marker detection model, the marker 31 and a minimum circumscribed rectangular frame of the head of the infant are extracted by using a minimum contour method, and a marker identification region 3 and a head identification region 2 are obtained; determining an effective identification area 1 according to the marker identification area 3 and the head identification area 2, wherein the effective identification area 1 comprises a first identification area 11 and a second identification area 12; specific determination methods of the effective identification area 1 include, but are not limited to, according to an infrared image of an infant sleeping at night in an initial state, which is shot by a device and includes an infant head contour image and a marker contour image, and the sizes of the head area 21 and the marker 31 are represented by the length and the width respectively corresponding to the head identification area 2 and the marker identification area 3 in the infrared image; root of herbaceous plantObtaining an effective identification area 1 according to a preset generation rule of the effective identification area 1, and utilizing a formula
Obtaining the coordinates of the vertex P1 of the effective identification area 1, and using the formula
Obtaining the coordinates of the vertex P2 of the effective identification area 1 by using a formula
Obtaining the coordinates of the vertex P3 of the effective identification area 1 by using a formula
Obtaining the coordinates of a vertex P4 of the effective identification area 1, wherein x is the abscissa of the head central point C, y is the ordinate of the head central point C, a, b and C are constants, a is more than 0 and less than m, b is more than 0 and less than or equal to 1, C is more than 0 and less than or equal to 1, W1 is the width value of the head identification area 2, and H2 is the height value of the marker identification area 3; thereby obtaining a rectangular effective identification area consisting of vertices P1, P2, P3 and P4; such as: the width of the effective identification area 1 is 4 times the width of the head area 21 of the baby, the height of the effective identification area is determined to be 0.8 times the height of the marker, and the Y coordinates of P1 and P2 are symmetrical with respect to the Y coordinate of the center point of the baby head, then m is 4, b is 0.5, and c is 0.8; the width of the effective identification area 1 is 4W 1, and the height of the effective identification area 1 is 0.8H 2, so that the head of the baby and the marker are positioned in the middle of the effective identification area 1, interference caused by other targets in the environment is avoided, and the detection accuracy is improved.
S25: and obtaining the initial effective mark area of the mark according to the mutual position relation between the effective identification area and the mark area corresponding to the initial range of the mark.
Specifically, the width of the effective identification area is determined to be 4 times of the pixel width of the infant head, the height of the effective identification area is determined to be 0.8 times of the pixel height of the marker, and therefore the effective identification area is determined according to the image parameters of the infant head and the marker on the basis of the image shot by the equipment; and calculating an initial effective recognition area of the marker falling within the effective recognition area.
In one embodiment, referring to fig. 4, the S3 includes:
s31: acquiring a current head image of the head and a current marker image of the marker in real time;
specifically, after the kick is detected, the camera acquires current parameter information in real time to identify the position change of the infant and the situation of the quilt covering the infant in the sleeping process of the infant, specifically, according to an infrared image shot by the device in the current state when the infant sleeps, the infrared image comprises an infant head outline image and a marker outline image.
S32: obtaining current position information of the head according to the current head image, wherein the current position information of the head comprises: head region information representing the current range of the head and head center coordinate information representing the geometric center of the head;
s33: obtaining current position information of the marker according to the current marker image, wherein the current position information of the marker comprises: marker region information characterizing the current range of the marker and marker center coordinate information characterizing the geometric center coordinates of the marker.
Specifically, according to the real-time contour information of the current head image and the marker image of the infant, the geometric center corresponding to the contour image is determined as the center position of the head and the marker of the infant, so as to obtain the current head center coordinate value and the current marker center coordinate value.
In one embodiment, referring to fig. 5, the S4 includes:
s41: determining the current distance according to the coordinate value of the head center coordinate information and the coordinate value of the marker center coordinate information;
s42: and obtaining the current effective mark area of the mark according to the mutual position relation between the effective identification area and the mark area corresponding to the current range of the mark.
Specifically, the determination of the current distance is obtained by calculating a distance formula between two points by using a current head center coordinate value and a current center coordinate value of the marker, for example, the current head center coordinate value is (10,13), the current marker center coordinate value is (28,12), and the current distance between the two points is 18.01cm, and the effective identification area of the current marker in the effective identification area can be determined according to the outline of the identified marker, the effective identification area and the center coordinate value of the marker; in this case, since the virtual fence of the valid recognition area has already been set, the current valid recognition area of the marker located in the valid recognition area in the current state can be calculated.
After the current distance and the current effective identification area are determined, the initial data can be compared according to the current data, so that whether the infant kicks off a quilt or not is further judged; to this end, in an embodiment, referring to fig. 6, the S5 includes:
s51: acquiring an area threshold value used for kicking the effective area of the identified marker and a distance threshold value of the distance between the marker and the head of the infant;
s52: if the ratio of the current effective mark area to the initial effective mark area is less than or equal to the area threshold value; and/or;
s53: and if the current distance is greater than the distance threshold value, outputting the information of the infant quilt kicking.
Specifically, in this embodiment, a kick-quilt detection threshold is set, and as long as the current detection data exceeds or is lower than the kick-quilt detection threshold, the device will have a corresponding determination conclusion as to whether the infant kicks the quilt or not; the set kicking detection threshold value can be comprehensively determined by referring to various factors, and the purpose is to better take care of the infants sleeping at night and avoid cold caused by kicking the quilt.
By adopting the intelligent detection method for infant kicking quilt of the embodiment, according to the initial infant head image and the marker image in the infant sleeping state, the initial position of the infant head and the initial position of the marker are determined, and the initial distance between the infant head position and the marker is obtained; establishing an effective identification area according to the outline corresponding to the head image of the infant and the outline corresponding to the marker image, so as to determine the effective identification area of the marker; in the process of detecting the sleep state of the infant in real time, whether the infant kicks the quilt or not is determined according to the relationship between the initial distance and the actual distance between the head position of the infant and the marker and/or the initial effective identification area and the real-time effective identification area of the marker, and if the infant kicks the quilt, prompt information is sent to a caregiver.
Example 2
An embodiment of the present invention further provides an apparatus, as shown in fig. 7, including:
an initial information acquisition module: the system comprises a detection device, a control device and a control module, wherein the detection device is used for acquiring initial position information of the head of an infant in a sleeping state and initial position information of a marker used for the infant to kick off the detected infant;
an initial information processing module: the system comprises a mark, a detection area and a marking area, wherein the mark is used for detecting the initial position information of the head of the infant and the initial position information of the marking;
the current information acquisition module: the system is used for acquiring the current position information of the head and the current position information of the marker in real time;
the current information processing module: the system comprises a mark, a current position information acquisition unit, a current distance acquisition unit and a current effective mark area acquisition unit, wherein the mark is used for acquiring the current position information of the head of the infant;
the kicking detection module: the system is used for judging whether the current effective mark area is larger than the initial effective mark area or not; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
By adopting the device of the embodiment, the initial position of the head of the infant and the initial position of the marker are determined according to the initial head image and the initial marker image of the infant in the sleeping state, so that the initial distance between the head position of the infant and the marker is obtained; establishing an effective identification area according to the outline corresponding to the head image of the infant and the outline corresponding to the marker image, so as to determine the effective identification area of the marker; in the process of detecting the sleep state of the infant in real time, whether the infant kicks the quilt or not is determined according to the relationship between the initial distance and the actual distance between the head position of the infant and the marker and/or the initial effective identification area and the real-time effective identification area of the marker, and if the infant kicks the quilt, prompt information is sent to a caregiver.
In one embodiment, the initial information obtaining module includes:
an initial image acquisition unit: acquiring an initial head image of the head and an initial marker image of the marker;
a head first position unit: obtaining initial position information of the head according to the initial head image, wherein the initial position information of the head comprises: head region information representing an initial range of the head and head initial center coordinate information representing a geometric center of the head;
marker first position unit: obtaining initial position information of the marker according to the initial position information of the marker, wherein the initial position information of the marker comprises: marker region information characterizing an initial range of the marker and marker initial center coordinate information characterizing geometric center coordinates of the marker.
In one embodiment, the initial information processing module includes:
initial distance unit: determining the initial distance according to the coordinate value of the head initial center coordinate information and the coordinate value of the marker initial center coordinate information;
width unit: obtaining the width value of the effective identification area detected by the infant kicking according to the coordinate value of the head initial center coordinate information and the size data in the head area information representing the head initial range;
height unit: obtaining the height value of the effective identification area detected by the infant kicking according to the marker area information representing the initial range of the marker and the size data of the marker initial center coordinate information of the geometric center coordinate of the marker;
valid identification area unit: constructing a rectangle on the basis of the width value of the effective identification area and the height value of the effective identification area, wherein the width value and the height value respectively correspond to the length and the width of the rectangle, and the effective identification area is represented by the rectangle;
effective area identification unit: and obtaining the initial effective mark area of the mark according to the mutual position relation between the effective identification area and the mark area corresponding to the initial range of the mark.
In one embodiment, the current information obtaining module includes:
a real-time image acquisition unit: acquiring a current head image of the head and a current marker image of the marker in real time;
head real-time position unit: obtaining current position information of the head according to the current head image, wherein the current position information of the head comprises: head region information representing the current range of the head and head center coordinate information representing the geometric center of the head;
marker real-time location unit: obtaining current position information of the marker according to the current marker image, wherein the current position information of the marker comprises: marker region information characterizing the current range of the marker and marker center coordinate information characterizing the geometric center coordinates of the marker.
In one embodiment, the current information processing module includes:
a real-time distance calculation unit: determining the current distance according to the coordinate value of the head center coordinate information and the coordinate value of the marker center coordinate information;
real-time effective area unit: and obtaining the current effective mark area of the mark according to the mutual position relation between the effective identification area and the mark area corresponding to the current range of the mark.
In one embodiment, the kick detection module includes:
distance threshold unit: acquiring an area threshold value used for kicking the effective area of the identified marker and a distance threshold value of the distance between the marker and the head of the infant;
an area identification unit: if the ratio of the current effective mark area to the initial effective mark area is less than or equal to the area threshold value; and/or;
a distance recognition unit: and if the current distance is greater than the distance threshold value, outputting the information of the infant quilt kicking.
In one embodiment, the marker is made of light absorption material capable of absorbing 780 nm-1100 nm infrared light source.
The device provided by the embodiment determines the initial position of the head of the infant and the initial position of the marker according to the initial head image and the initial marker image of the infant in the sleeping state, so as to obtain the initial distance between the head position of the infant and the marker; establishing an effective identification area according to the outline corresponding to the head image of the infant and the outline corresponding to the marker image, so as to determine the effective identification area of the marker; in the process of detecting the sleep state of the infant in real time, whether the infant kicks the quilt or not is determined according to the relationship between the initial distance and the actual distance between the head position of the infant and the marker and/or the initial effective identification area and the real-time effective identification area of the marker, and if the infant kicks the quilt, prompt information is sent to a caregiver.
Example 3
The present invention provides an electronic device and storage medium, as shown in fig. 8, comprising at least one processor, at least one memory, and computer program instructions stored in the memory.
Specifically, the processor may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present invention, and the electronic device includes at least one of the following: the wearing equipment that has intelligent camera, the mobile device that has intelligent camera.
The memory may include mass storage for data or instructions. By way of example, and not limitation, memory may include a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or Universal Serial Bus (USB) Drive or a combination of two or more of these. The memory may include removable or non-removable (or fixed) media, where appropriate. The memory may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory is non-volatile solid-state memory. In a particular embodiment, the memory includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.
The processor reads and executes the computer program instructions stored in the memory to realize the intelligent infant kicking quilt detection method in any one of the above embodiment modes.
In one example, the electronic device may also include a communication interface and a bus. The processor, the memory and the communication interface are connected through a bus and complete mutual communication.
The communication interface is mainly used for realizing communication among modules, devices, units and/or equipment in the embodiment of the invention.
A bus comprises hardware, software, or both that couple components of an electronic device to one another. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. A bus may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.
In summary, embodiments of the present invention provide an infant quilt kicking intelligent detection method, apparatus, device and storage medium.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of detecting kicking of an infant, the method comprising:
acquiring an effective identification area for detecting the infant kicking;
acquiring the current distance between the head of the infant and the marker in a sleeping state and the current effective area of the marker in real time, wherein the current effective area is the area of the marker in the effective identification area;
according to the initial effective mark area and the current effective mark area; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
2. The method according to claim 1, wherein the obtaining of the valid identification area for detecting infant kicking comprises:
acquiring initial position information of the head of an infant in a sleeping state and initial position information of the marker, wherein the initial position information comprises a center coordinate and size data of a detection frame representing a detection target;
determining a width value and a height value of the effective identification area according to the initial position information of the infant head and the respective size data of the initial position information of the marker;
and establishing the effective identification area according to the central coordinate of the head of the infant and the combination of the width value and the height value.
3. The method according to claim 2, wherein the establishing the effective identification area according to the center coordinates of the head of the infant in combination with the width value and the height value comprises:
according to the coordinate value of the head initial center coordinate information, the size data of the head initial range and the size information of the marker initial range, the formula
Obtaining a vertex P1 of the construction rectangle by formula
Obtaining a vertex P2 of the construction rectangle by formula
Obtaining a vertex P3 of the construction rectangle by formula
Obtaining a vertex P4 of the construction rectangle;
constructing the effective recognition region with vertices P1, P2, P3, and P4;
wherein x is the abscissa of the head center point, y is the ordinate of the head center point, a, b, c and m are constants, a is greater than 0 and less than m, b is greater than or equal to 0 and less than or equal to 1, c is greater than 0 and less than or equal to 1, W1 is the width value of the head range corresponding to the head identification area, and H2 is the height value of the marker range corresponding to the marker identification area.
4. The method according to claim 2, wherein the acquiring initial position information of the head of the infant in the sleeping state and the initial position information of the marker includes center coordinates and size data of a detection frame representing a detection target:
acquiring a target image and a preset feature image imaged by a marker in a sleeping state of an infant;
detecting the face contour of the infant on the target image to obtain initial position information of the head of the infant corresponding to the face contour of the infant;
and carrying out marker contour detection on the target image according to the characteristic image of the marker to obtain initial position information of the marker.
5. The method for detecting infant kicking according to any one of claims 1 to 4, wherein the obtaining, in real time, a current distance between the infant's head and a marker in a sleeping state and a current effective area of the marker, the current effective area being an area of the marker located within the effective identification area includes:
acquiring a current head image of the head of an infant and a current marker image of a marker in a sleep state in real time;
obtaining the current distance according to the head center coordinate information of the detection frame for representing and detecting the current head image and the marker center coordinate information of the detection frame for representing and detecting the current marker image;
and obtaining the current effective mark area of the mark according to the mutual position relation between the mark area information of the detection frame for representing and detecting the current mark image and the effective identification area.
6. The method according to claim 5, wherein the step of detecting kicks of the infant is performed according to the initial valid flag area and the current valid flag area; and/or, according to the initial distance and the current distance, outputting information whether the infant kicks off a quilt or not comprises:
acquiring an area threshold value used for kicking the effective area of the identified marker and a distance threshold value of the distance between the marker and the head of the infant;
if the ratio of the current effective mark area to the initial effective mark area is less than or equal to the area threshold value; and/or;
and if the current distance is greater than the distance threshold value, outputting the information of the infant quilt kicking.
7. The method for detecting kicking of an infant or young child according to claim 5, wherein the marker is made of a light-absorbing material capable of absorbing 940nm infrared light.
8. An infant kicking detection device for performing the intelligent infant kicking detection method according to any one of claims 1 to 7, the infant kicking detection device comprising:
an identification area acquisition module: the method comprises the steps of obtaining a valid identification area for detecting infant kicking;
a data acquisition module: the system is used for acquiring the current distance between the head of the infant and the marker in a sleeping state and the current effective area of the marker in real time, wherein the current effective area is the area of the marker in the effective identification area;
a data processing module: the system is used for judging whether the current effective mark area is larger than the initial effective mark area or not; and/or outputting information whether the infant kicks off a quilt or not according to the initial distance and the current distance.
9. An electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory that, when executed by the processor, implement the method of any of claims 1-7.
10. A medium having stored thereon computer program instructions, which, when executed by a processor, implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111264485.1A CN113974933B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking detection method and device, electronic equipment and medium |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111264485.1A CN113974933B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking detection method and device, electronic equipment and medium |
| CN202110945621.7A CN113384386B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking intelligent detection method and device, electronic equipment and medium |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110945621.7A Division CN113384386B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking intelligent detection method and device, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113974933A true CN113974933A (en) | 2022-01-28 |
| CN113974933B CN113974933B (en) | 2024-03-12 |
Family
ID=77622763
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110945621.7A Active CN113384386B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking intelligent detection method and device, electronic equipment and medium |
| CN202111264485.1A Active CN113974933B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking detection method and device, electronic equipment and medium |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110945621.7A Active CN113384386B (en) | 2021-08-18 | 2021-08-18 | Infant quilt kicking intelligent detection method and device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN113384386B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116386106A (en) * | 2023-03-16 | 2023-07-04 | 宁波星巡智能科技有限公司 | Intelligent infant head recognition method, device and equipment during sleep-accompanying infant |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107424208A (en) * | 2017-08-11 | 2017-12-01 | 衢州熊妮妮计算机科技有限公司 | A kind of baby bed and monitoring method of smart home |
| CN107545221A (en) * | 2016-06-28 | 2018-01-05 | 北京京东尚科信息技术有限公司 | Baby kicks quilt recognition methods, system and device |
| CN110008816A (en) * | 2019-01-28 | 2019-07-12 | 温州大学 | A kind of method that real-time detection baby kicks quilt son |
| CN110580466A (en) * | 2019-09-05 | 2019-12-17 | 深圳市赛为智能股份有限公司 | infant quilt kicking behavior recognition method and device, computer equipment and storage medium |
| CN111262760A (en) * | 2020-01-16 | 2020-06-09 | 珠海格力电器股份有限公司 | Household control method and device, computer equipment and storage medium |
| WO2021023106A1 (en) * | 2019-08-02 | 2021-02-11 | 杭州海康威视数字技术股份有限公司 | Target recognition method and apparatus, and camera |
-
2021
- 2021-08-18 CN CN202110945621.7A patent/CN113384386B/en active Active
- 2021-08-18 CN CN202111264485.1A patent/CN113974933B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545221A (en) * | 2016-06-28 | 2018-01-05 | 北京京东尚科信息技术有限公司 | Baby kicks quilt recognition methods, system and device |
| CN107424208A (en) * | 2017-08-11 | 2017-12-01 | 衢州熊妮妮计算机科技有限公司 | A kind of baby bed and monitoring method of smart home |
| CN110008816A (en) * | 2019-01-28 | 2019-07-12 | 温州大学 | A kind of method that real-time detection baby kicks quilt son |
| WO2021023106A1 (en) * | 2019-08-02 | 2021-02-11 | 杭州海康威视数字技术股份有限公司 | Target recognition method and apparatus, and camera |
| CN110580466A (en) * | 2019-09-05 | 2019-12-17 | 深圳市赛为智能股份有限公司 | infant quilt kicking behavior recognition method and device, computer equipment and storage medium |
| CN111262760A (en) * | 2020-01-16 | 2020-06-09 | 珠海格力电器股份有限公司 | Household control method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 丘柳东 等: "Python深度学习 逻辑、算法与编程实战", 西南交通大学出版, pages: 145 - 151 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116386106A (en) * | 2023-03-16 | 2023-07-04 | 宁波星巡智能科技有限公司 | Intelligent infant head recognition method, device and equipment during sleep-accompanying infant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113384386A (en) | 2021-09-14 |
| CN113384386B (en) | 2021-11-23 |
| CN113974933B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8503727B2 (en) | Monitoring camera terminal | |
| CN108209871B (en) | Sleep monitoring method, device and system and electronic equipment | |
| CN113384386B (en) | Infant quilt kicking intelligent detection method and device, electronic equipment and medium | |
| CN104169968B (en) | Site estimation device, and site estimation method | |
| JP2009055139A (en) | Person tracking system, apparatus, and program | |
| CN113298062B (en) | Infant sleep activity state detection method, device, equipment and medium | |
| CN103366505B (en) | A kind of sleeping position recognition methods and device | |
| JP5868426B2 (en) | How to estimate the orientation of a stationary person | |
| CN109637086A (en) | Alarm method and system | |
| CN117690159A (en) | Infant groveling and sleeping monitoring method, device and equipment based on multi-mode data fusion | |
| CN113963424B (en) | Infant asphyxia or sudden death early warning method based on single-order face positioning algorithm | |
| CN107958572A (en) | A kind of baby monitoring systems | |
| CN116612532A (en) | Infant target nursing behavior recognition method, device, equipment and storage medium | |
| CN108549838A (en) | A kind of back-up surveillance method of view-based access control model system | |
| CN114120354A (en) | Human body detection and positioning method and device applied to air conditioner and intelligent sensing system | |
| CN113919627A (en) | Intelligent monitoring method applied to hydro-junction engineering | |
| JP2000137790A (en) | Method and device for monitoring image of man conveyor | |
| CN115880643B (en) | Social distance monitoring method and device based on target detection algorithm | |
| CN111595460A (en) | High-precision infrared temperature measurement method and device based on face recognition | |
| CN208092911U (en) | A kind of baby monitoring systems | |
| CN115862115A (en) | Infant respiration detection area positioning method, device and equipment based on vision | |
| CN115601699A (en) | Safety helmet wearing detection method, electronic equipment and computer readable medium | |
| CN113378762B (en) | Sitting posture intelligent monitoring method, device, equipment and storage medium | |
| CN113762164A (en) | Fire fighting access barrier identification method and system | |
| JP2008191785A (en) | Eye closure detection apparatus, doze detection apparatus, eye closure detection method, and program for eye closure detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |