CN112001286A - Neck pillow height adjusting method and device for sleep posture recognition processing based on pressure image - Google Patents

Neck pillow height adjusting method and device for sleep posture recognition processing based on pressure image Download PDF

Info

Publication number
CN112001286A
CN112001286A CN202010820060.3A CN202010820060A CN112001286A CN 112001286 A CN112001286 A CN 112001286A CN 202010820060 A CN202010820060 A CN 202010820060A CN 112001286 A CN112001286 A CN 112001286A
Authority
CN
China
Prior art keywords
pressure
human body
height
lying
pillow
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010820060.3A
Other languages
Chinese (zh)
Other versions
CN112001286B (en
Inventor
张立国
马子荐
金梅
刘强
李媛媛
李福昆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yanshan University
Original Assignee
Yanshan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yanshan University filed Critical Yanshan University
Priority to CN202010820060.3A priority Critical patent/CN112001286B/en
Publication of CN112001286A publication Critical patent/CN112001286A/en
Application granted granted Critical
Publication of CN112001286B publication Critical patent/CN112001286B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47G—HOUSEHOLD OR TABLE EQUIPMENT
    • A47G9/00—Bed-covers; Counterpanes; Travelling rugs; Sleeping rugs; Sleeping bags; Pillows
    • A47G9/10—Pillows
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C9/00—Measuring inclination, e.g. by clinometers, by levels
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
    • G01L5/0028—Force sensors associated with force applying means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Analytical Chemistry (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Otolaryngology (AREA)
  • Pulmonology (AREA)
  • Chemical & Material Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Image Processing (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention provides a neck pillow height adjusting method and a neck pillow height adjusting device for sleep posture identification based on pressure images, wherein the height adjusting method comprises the steps of preliminarily judging human body postures, identifying the prone and supine lying of a human body and establishing a model of head and neck height changing along with the postures; the height adjusting device comprises a pillow outer skin, a pressure sensor, a transverse plate, a side plate, an electric push rod, a fixed column, a rotating shaft, a control unit, a down filling layer, a power module and a pressure sensor array, wherein the power module provides a sensor and a controller power supply, the pressure sensor array collects human body pressure images, the pressure sensor array receives head pressure data, the control unit comprehensively analyzes human body pressure image information and the head pressure data, and the side plate is rotated by controlling the electric push rod to change the height of the neck pillow. The device and the method simplify characteristic calculation, improve the speed and the precision of identifying the lying down and lying up, and realize the purpose of adjusting the height of the neck pillow and protecting the human body by identifying the sleeping posture through the pressure image.

Description

Neck pillow height adjusting method and device for sleep posture recognition processing based on pressure image
Technical Field
The invention relates to a sleeping posture identification technology, in particular to a neck pillow height adjusting method and device for carrying out sleeping posture identification processing based on a pressure image.
Background
More and more researches show that the supine pillow height and the lateral pillow height are positively correlated with the generation of cervical spondylosis of patients. Improper pillow height can increase spinal burden and affect quality of rest. In the products for adjusting the pillow height according to the body posture and protecting the cervical vertebra, the existing sleeping posture identification technology mainly comprises image identification acquired by a camera and pressure identification of a pressure sensor. The images collected by the camera are identified, so that the influence of objects such as quilts and the like and the influence of weak noctilucent light rays in actual conditions are difficult to ignore, and the product installation difficulty is high, and the house attractiveness is influenced. The problems of quilt shading and darkness at night are solved through a pressure sensor identification method, but the existing algorithm has the defects of many identification modes, low precision, low operation speed and the like.
Disclosure of Invention
Therefore, in order to further improve the effect and the efficiency, the invention provides a simplified sleeping posture identification method. In the sleeping posture identification method, aiming at the inclination degrees of pitching lying and different side lying in sleeping, the sleeping posture identification method based on pressure image processing is provided by calculating the pressure density change of a pressure sensor and combining the pressure distribution information and the optimal pillow height information of a human body under different postures, and the relationship between the optimal pillow height and different sleeping postures is obtained.
A neck pillow height adjusting method for sleep posture recognition processing based on pressure images comprises the following steps:
step S1: determining the optimal pillow height and an adjusting mode;
establishing an optimal pillow height prediction function Y:
Figure BDA0002634136740000021
wherein, Y1The optimum pillow height and Y for no cervical spondylosis2The optimum pillow height and Y for cervical spondylosis3For lying on back and pillowing high, Y4The height of the pillow is laid on the side, C is whether cervical spondylosis exists, C is 0 and represents no cervical spondylosis, C is 1 and represents cervical spondylosis, lambda is the adjustment degree of the height of the neck pillow, and F is an adjustment mode function;
the user can adjust the time t by changingsAnd power γ selection adjustment mode function F:
Figure BDA0002634136740000022
x is the time taken to reach the current height in the height adjustment process, tsThe total time taken for height adjustment is constant;
step S2: preliminarily judging the lying down and the lying sideways of the human body;
s21, collecting the pressure information of the human body on the bed by a pressure detection array consisting of M × W pressure sensors, converting the obtained pressure value into a gray value of 0-255, and converting the expression into:
Figure BDA0002634136740000023
wherein N is the pressure value of the pressure sensor, NmaxIs the maximum value of pressure, NminIs the minimum value of pressure, P is the grey scale value;
s22, calculating pressure density rho:
Figure BDA0002634136740000024
wherein N isiIs a pressure value, PijThe number of pressure points;
introduction of double threshold K1、K2When the pressure density ρ of the pressure image is greater than K1When the human body is lying in a pitching way, if the pressure density rho of the pressure image is less than K2When in use, the human body lies on the side;
step S3: identifying the lying down and lying back of the human body;
positioning a pressure dense region by a pressure dense region positioning method based on local symmetry and gray scale statistical characteristics, performing central symmetry transformation on a region with high pressure density, performing weighted average on the transformed region and an original image to obtain a transformed image, and obtaining a standard deviation C1：
Figure BDA0002634136740000031
In the formula, MiFor each statistical point in the detection window, each point is marked as 1, NijThe point pressure value;
traversing the position information of each area to obtain the center position information, marking the condition of the maximum standard deviation of the upper standard deviation and the lower standard deviation to obtain two positioning ranges, and comparing the positioning ranges, namely:
Figure BDA0002634136740000032
in the formula, SOn the upper part、SLower partRespectively a detection window area nearest to the head center Z and a detection window area farthest to the head center Z, wherein a is the area ratio of the upper part to the lower part, and when a is larger than K6And SOn the upper partAnd SLower partIs less than K7The human body is lying on the back, the rest is lying on the top, wherein d is SOn the upper partAnd SLower partDistance between central positions, K6Is 0.6, K7Equal to the upper body length H2;
step S4: and establishing a model of the head and neck height changing along with the posture, and adjusting the optimal pillow height according to the human body posture detected in the step.
Preferably, in the S2:
when the pressure density rho of the pressure image is between K1And K2In the meantime, the human body can not be accurately distinguished to lie in a pitching manner or lie in a side manner, at the moment, the human body lies in a pitching manner, incompletely lies in a side manner or already lies in a side manner, and the state of the human body posture is judged by introducing the balance degree standard of the pressure image;
setting a threshold K3、K4Performing bottom-cap transformation on the pressure image to remove noise influence, and simultaneously selecting a plurality of gray values larger than K5Selecting n x n points near the pressure gray level graph position point to calculate the average difference, and calculating the average difference C3Is composed of
Figure BDA0002634136740000033
In the formula, PpIs the average of n x n dot gray values, PijIs the gray value at position (i, j) when C3Initially above the gradient threshold K3And then, taking the point value as a contour point, counting the positions of all the contour points, wherein the balance degree B of the pressure image is as follows:
B＝|∑Li-∑Ri| (8)
in the formula, LiIs the contour point on the left side of the center line, RiIs a contour point on the right side of the central line;
constructing an influence function r:
Figure BDA0002634136740000041
when r is between 0 and K3When lying on the back, when r is at K4When the value is 0, the human body is in a side lying state, and when the value is r, the human body is in an incomplete side lying state.
Preferably, the height of the pillow is Y when the human body is lying on the back and the pressure density changes slowly in time t1(ii) a When the human body is in a lying posture and the pressure density is rapidly reduced, detecting whether the human body is lying on the side or not, and if the human body is still lying on the side within the time t and the pressure density changes slowly, raising the pillowAdjusted to Y2If the human body lies down and the pressure density changes slowly within the time t, the pillow height is adjusted to the minimum value Y3(ii) a When the human body is in a lying posture and the pressure density changes slowly within a time t, the height of the pillow part is Y2(ii) a When the human body is in a side lying posture and the pressure density is rapidly increased, detecting whether the human body lies on the back, if the human body still lies on the back within the time t and the pressure density changes slowly, adjusting the pillow height to Y1If the human body lies down and the pressure density changes slowly within the time t, the pillow height is adjusted to the minimum value Y3。
A neck pillow height adjusting device of a neck pillow height adjusting method based on pressure image recognition processing comprises a pillow outer skin, a pressure sensor, a transverse plate, a side plate, an electric push rod, a fixed column, a rotating shaft, a control unit, a down feather filling layer, a power supply module, a Bluetooth module and a pressure sensor array, wherein the electric push rod is connected with the fixed column and the side plate, the fixed column is connected with the transverse plate, the control unit is connected with the electric push rod, the pressure sensor and the pressure sensor array, the power supply module supplies power to the sensor and a controller, the pressure sensor array collects human body pressure images to recognize human body sleeping postures, the pressure sensor receives head pressure data to recognize head positions, the control unit comprehensively analyzes human body pressure image information and the head pressure data and controls the electric push rod to enable the side plate to rotate, the height of the neck pillow is changed.
Preferably, the control unit determines the head center position according to the pressure of different pressure sensors, the device height L is in negative correlation with the pressure of the pressure sensor N, the device height is in positive correlation with the length L of the electric push rod, and the function formula is as follows:
l＝αN+βL (12)
wherein, alpha and beta are correlation coefficients, and alpha is positive and beta is negative.
Compared with the prior art, the invention has the following advantages:
(1) the method for identifying the sleeping posture by analyzing the pressure distribution of different postures of the human body solves the problems that the sleeping posture identification is influenced by quilt shielding and dark light at night;
(2) in the range of the relative fuzziness of the pressure density to the sleep gesture recognition, a construction function comprising the balance degree is introduced for accurate recognition;
(3) standard deviation judgment is introduced through the condition that the upper pressure and the lower pressure of the lying face down are different in distribution range, and feature calculation is simplified;
(4) and finally, the cervical vertebra protection of recognizing the sleeping posture through the pressure image is realized through the optimal pillow height model of the sleeping posture and the existence of cervical spondylosis.
Drawings
FIG. 1 is a diagram of a pressure sensing array of the present invention;
FIG. 2a is a schematic view of the profile points of the balance of the present invention;
FIG. 2b is a schematic diagram of the value range of the constructor of the present invention;
FIG. 3 is a schematic illustration of an apparatus according to an embodiment of the present invention;
FIG. 4 is a flow chart of the present invention;
FIG. 5 is an exemplary process diagram of the present invention for performing sleep posture recognition; and
fig. 6a, 6b and 6c are schematic diagrams of three lying postures according to the invention.
Reference numerals:
the pillow comprises a pillow outer skin 10, a pressure sensor 20, a transverse plate 21, side plates 22, an electric push rod 23, a fixed column 24, a rotating shaft 25, a control unit 26, a down filling layer 27, a power supply module 28, a Bluetooth module 29 and a pressure sensor array 30.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
In order to realize the idea of intelligently adjusting the head and neck bearing height, the invention provides a cervical vertebra protection method and device for recognizing sleeping postures based on pressure images. The flow is shown in figure 4.
Step S1: determining the optimal pillow height and an adjusting mode;
specifically, in step S1, the information includes the presence or absence of cervical spondylosis C, right hand width R, and cheekbone distance S according to the user input1Height H1, upper half length H2, shoulder width S2Determining the optimal pillow height and the optimal adjusting mode according to the adjustment degree lambda of the neck pillow height, the adjusting mode F, the lying pressure information N and the like. In the process of establishing and determining the optimal pillow height, the pillow height model is determined according to the conclusion that the width of the right palm, the distance between the shoulders and the cheekbones, the height and the weight of the human body are all in certain relation with the optimal pillow height and the corresponding correlation coefficients are 0.607, 0.603, 0.345 and 0.378 respectively, which are provided in the southeast university paper 'study on the correlation between the pillow height, the individual data and the cervical spondylosis'. The data of the best pillow height of the normal person without cervical spondylosis, which is improved in the application conclusion, of the 'same body size' is the width of the right palm, and can be obtained according to a regression equation:
Y1＝1.558+0.807R (1)
the data of the 'same body inch' of the optimal pillow height of the patient with cervical spondylosis is the distance between the shoulders and the cheeks, and can be obtained according to a regression equation:
Y2＝2.001+0.726S1 (2)
wherein, Y1The optimum pillow height without cervical spondylosis, Y2The optimum pillow height for cervical spondylosis. Therefore, the individual predicted value of the optimal pillow height of the patient with cervical spondylosis and the patient without cervical spondylosis is obtained.
Further, a lambda value and an adjustment mode function F suitable for the person are set according to whether the cervical spondylosis exists in the human body. Establishing a function by combining the individual predicted value of the optimal pillow height with an adjusting mode function:
Figure BDA0002634136740000061
wherein, Y3For lying on back and pillowing high, Y4The height of the pillow is laid on the side, C is whether cervical spondylosis exists, C is 0 and represents no cervical spondylosis, C is 1 and represents cervical spondylosis, lambda is the adjustment degree of the height of the neck pillow, and F is an adjustment mode function.
Setting different adjustment mode functions F may provide different adjustment modes. Optionally, F is set as a power function, and the user can adjust the time t by changingsAnd power gamma selects a comfortable adjustment mode:
Figure BDA0002634136740000071
x is the time taken to reach the current height in the height adjustment process, tsThe total time taken for height adjustment is constant;
step S2: preliminarily judging the posture of the human body;
s21, as shown in fig. 1, the pressure detection array composed of M × W pressure sensors collects the pressure information of the human body on the bed, and converts the pressure information into a pressure image and a grayscale image. Converting the obtained pressure value into a gray value of 0-255, and converting the expression into:
the specific method comprises the following steps:
Figure BDA0002634136740000072
wherein N is the pressure value of the pressure sensor, NmaxIs the maximum value of pressure, NminIs the pressure minimum and P is the grey scale value.
S22, calculating pressure density and introducing double threshold values K1、K2The calculation method of the pressure density rho comprises the following steps:
Figure BDA0002634136740000073
wherein N isiIs a pressure value, PijThe number of pressure points.
Further, fig. 6 is a schematic diagram of three lying posture pressures, fig. 6a is a side lying posture, fig. 6b is a back lying posture, fig. 6c is a top lying posture, the diagram illustrates the stress condition of the pressure sensor, wherein the deeper the color is, the larger the pressure is, the larger the stress area of the human body in the top lying posture or the back lying posture is, and the larger the stress area of the human body side isThe force bearing area of lying, but the human quality is unchangeable, therefore the human pressure density of lying down or lying on back is less than the pressure density of lying on one's side. When the pressure density rho of the pressure image is larger than K1At this time, the human body is in pitch and lies, and if the pressure density rho of the pressure image is less than K2When in use, the human body lies on the side; when the pressure density rho of the pressure image is between K1And K2In between, the human body is in the prone lying state, the incomplete lying state or the lying state. Wherein K1And K2The value of (A) is determined by the lying pressure information S, the S value is obtained by recording the pressure distribution information of the human body when lying, namely the pressure density of the user when lying in a standard way, and the pressure density is calculated by the information. Alternatively, K1Less than 1.2 times S, K2Between 1.5 times S and 2 times S.
Further, in order to judge the state of the human body posture more accurately, a balance degree standard of the pressure image is introduced.
S23, specifically, first, the upper half length H2 and the shoulder width S2Determining a gray scale image symmetry axis. Taking the maximum force position of the pressure sensor 20 as the center Z and the upper body length H2 as the distance, when there is pressure information at the position with the distance H2 from the Z, recording the position and calculating the distance of each position, and when the distance between two points and the shoulder width S in all the recorded positions2When the two points are closest to each other, marking two points, wherein the line from the centers of the two points to Z is the symmetry axis.
Setting a threshold K3、K4Performing bottom-cap transformation on the pressure image to remove certain noise influence, and selecting a plurality of gray values larger than K5Selecting n x n points near the pressure gray level graph position point to calculate the average difference, and calculating the average difference C3Is composed of
Figure BDA0002634136740000081
In the formula, PpIs the average of n x n dot gray values, PijIs the gray value at position (i, j) when C3Initially above the gradient threshold K3Then, the point value is the contour point. The position of each contour point is counted,the balance B of the pressure image at this time is:
B＝|∑Li-∑Ri| (8)
in the formula, LiIs the contour point on the left side of the center line, RiIs the centerline right contour point.
The balance degree B contains data information of lying on the back, not fully lying on the side or lying on the side, as shown in the diagram of the profile points of the balance degree in fig. 2a, which illustrates the profile points under stress on both sides of the centerline when the human body is not fully lying on the side. The impact function r is further constructed:
Figure BDA0002634136740000082
when r is between 0 and K, as shown in FIG. 2b3When lying on the back, when r is at K4Lying on one side when r is at 0, lying on one side when r is at other value, and lying on one side when r is at other value3And K4The values are related to B, K5Value of and K1And K2And (4) correlating.
Further, the human body posture, i.e., lying on the back and on the side, can be preliminarily judged through the above process.
Step S3: identifying the lying down and lying back of the human body;
specifically, in step S3, after the human body posture is preliminarily determined in step S2, the obtained lying posture is determined and analyzed to obtain lying posture information, and the process is as shown in fig. 5, a sleeping posture recognition diagram.
Specifically, in the process of judging the pitch and lie information of the human body, the pressure-dense region is positioned by a pressure-dense region positioning method based on local symmetry and gray statistical characteristics. First, the gray value change is large in the area where the pressure density is large, and therefore the standard deviation is large in this area. In the lying down pressure information and lying up pressure information, two areas with large pressure density are arranged up and down, the areas have better up and down symmetry, so the areas are transformed up and down symmetrically, then the transformed images are obtained by weighted averaging with the original images, the standard deviation is calculated for the transformed images, and the areas with the peak standard deviation are the areas with large pressure density to be identified. It should be noted that, before calculating the standard deviation, the position without pressure information needs to be averaged, specifically, the head position Z, the height H1 and the shoulder width S are referred to2And an axis of symmetry centered on the axis of symmetry to establish a dimension of H1S2The area average is calculated and the locations with pressure less than 10 are averaged. Standard deviation C1The calculation process of (2) is as follows:
Figure BDA0002634136740000091
in the formula, MiFor each statistical point in the detection window, each point is marked as 1, NijFor this point pressure value, the statistical window size becomes the shoulder width S2The square area of (a). Several regions with the largest standard deviation were screened as candidate regions.
And traversing the position information of each region to obtain the center position information, and marking the condition that each peak is positioned at the maximum standard deviation. And (3) combining the distance of each mark position to obtain two positioning ranges, and comparing the positioning ranges and the distances respectively to obtain lying down or lying back information, namely:
Figure BDA0002634136740000092
in the formula, SOn the upper part、SLower partThe detection window area closest to the head center Z and the detection window area farthest therefrom, respectively. As shown in fig. 6c, the schematic diagrams of lying down and lying down pressure in fig. 6b, the upper square in the schematic diagrams of lying down and lying down is SOn the upper partThe lower square frame is SLower partAnd a is the ratio of the area of the upper part to the area of the upper part and the area of the lower part. When a is greater than K6And SOn the upper partAnd SLower partIs less than K7The human body is lying on the back, and the rest is lying on the top. d is SOn the upper partAnd SLower partDistance between central positions, K6Value of (A) and K7The value of (A) is related to the body weight distribution of the human body, where K is taken6Is 0.6, take K7The upper body length is H2.
In the identification of peopleIn the embodiments of lying prone and lying supine positions, the number of pixels of the pressure image is equal to the number of pressure sensors, and the number of pixels is 500 × 280. Please refer to fig. 6b, wherein fig. 6b contains three standard deviations at the peak, which are denoted as C11、C12And C1326.49, 33.37 and 37.11 respectively, and the maximum distance is C11And C13The distance d is 158. C11Is SOn the upper part，C13Is SLower part，SOn the upper partIs 24002, SLower partHas a range of 12907, a is 0.65 and the upper body length H2 is 244, thus giving the posture of lying on the back.
FIG. 6C contains two standard deviations at the peak, denoted C21And C2233.98 and 35.06, respectively, and a maximum distance C21And C22The distance d is 274. C21Is SOn the upper part，C22Is SLower part，SOn the upper partIn the range of 19317, SLower partIs 22172, a is 0.47, and the upper half H2 is 244, whereby the posture is recumbent.
SOn the upper partAnd SLower partAs shown in fig. 6b and 6 c.
S4: establishing a model of head and neck height changing along with posture;
specifically, in step S4, the optimal pillow height is adjusted according to the human body posture, i.e., lying on its side, lying on its top, and lying on its back, detected in the above steps.
When the human body is lying on the back and the pressure density changes slowly within the time t, the height of the pillow part is Y1When the human body is in a lying posture and the pressure density is rapidly reduced, detecting whether the human body is lying on the side or not, and if the human body is still lying on the side and the pressure density changes slowly within the time t, adjusting the pillow height to Y2If the human body lies down and the pressure density changes slowly within the time t, the pillow height is adjusted to the minimum value Y3. When the human body is in a lying posture and the pressure density changes slowly within a time t, the height of the pillow part is Y2When the human body is in a side lying posture and the pressure density is rapidly increased, detecting whether the human body is lying on the back, if the human body is still lying on the back within the time t and the pressure density changes slowly, adjusting the pillow height to Y1If the human body lies down and the pressure density changes slowly within the time t, the pillow height is adjusted to the minimum value Y3。
Further, an embodiment of the device for adjusting the height of the head and neck is shown in fig. 3, and the structure comprises a pillow outer skin 10, a pressure sensor 20, a transverse plate 21, a side plate 22, an electric push rod 23, a fixing column 24, a rotating shaft 25, a control unit 26, a down filling layer 27, a power supply module 28, a bluetooth module 29, a pressure sensor array 30 and the like.
In the device for adjusting the height of the head and the neck, a power module 28 is connected with a pressure sensor 20, an electric push rod 23, a control unit 26, a Bluetooth module 29, a pressure sensor array 30 and the like, the power module 28 provides power for a sensor and a controller, the pressure sensor array 30 collects pressure images of a human body, the pressure sensor 20 receives head pressure data, the Bluetooth module 29 transmits Bluetooth data to interact with terminals such as a mobile phone, and the control unit 26 comprehensively analyzes information of the pressure sensor 26 and the pressure image information. The electric push rod 23 is connected with the fixed column 24 and the side plate 22, and the fixed column 24 is connected with the transverse plate 21. The control unit 26 is connected with the electric push rod 23, the pressure sensor 20 and the pressure sensor array 30, and the pressure sensor array 30 receives the human body pressure information and transmits the information to the control unit 26 for human body sleeping posture identification. The pressure sensor 20 receives head pressure data and transmits it to the control unit 26 for head position recognition.
The control unit 26 causes the side plate 22 to rotate under the connection of the rotating shaft 25 by controlling the length of the electric push rod 23. The rotation of the side plates 22 changes the stress structure inside the device to change the height of the device under stress. When the height of the neck pillow needs to be increased, the electric push rod 23 near the center of the head is extended to cause the rotating shaft 25 to rotate and the side plates 22 to turn outwards, and the down feather filling layer 27 is lifted to enable the neck pillow to be lifted. Otherwise the neck pillow is lowered. The control unit 26 determines the center position of the head according to the pressures of different pressure sensors, the height of the device is in negative correlation with the pressure of the pressure sensors, and the height of the device is in positive correlation with the length of the electric push rod 23. Specifically, the following formula can be used:
l＝αN+βL (12)
wherein, L is the device height, N is the pressure value, L is electric putter length, alpha, beta are the correlation coefficient, and wherein alpha is positive beta is negative.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can 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 (5)

1. A neck pillow height adjusting method for sleep posture recognition processing based on pressure images is characterized by comprising the following steps:
step S1: determining the optimal pillow height and an adjusting mode;
establishing an optimal pillow height prediction function Y:
Figure FDA0002634136730000011
wherein, Y1The optimum pillow height and Y for no cervical spondylosis2The optimum pillow height and Y for cervical spondylosis3For lying on back and pillowing high, Y4The height of the pillow is laid on the side, C is whether cervical spondylosis exists, C is 0 and represents no cervical spondylosis, C is 1 and represents cervical spondylosis, lambda is the adjustment degree of the height of the neck pillow, and F is an adjustment mode function;
the user can adjust the time t by changingsAnd power γ selection adjustment mode function F:
Figure FDA0002634136730000012
x is the time taken to reach the current height in the height adjustment process, tsThe total time taken for height adjustment is constant;
step S2: preliminarily judging the lying down and the lying sideways of the human body;
s21, collecting the pressure information of the human body on the bed by a pressure detection array consisting of M × W pressure sensors, converting the obtained pressure value into a gray value of 0-255, and converting the expression into:
Figure FDA0002634136730000013
wherein P is a gray value, N is a pressure of the pressure sensor, and N ismaxIs the maximum value of pressure, NminIs the minimum value of pressure;
s22, calculating pressure density rho:
Figure FDA0002634136730000021
wherein N isiIs a pressure value, PijThe number of pressure points;
introduction of double threshold K1、K2When the pressure density ρ of the pressure image is greater than K1When the human body is lying in a pitching way, if the pressure density rho of the pressure image is less than K2When in use, the human body lies on the side;
step S3: identifying the lying down and lying back of the human body;
positioning a pressure dense region by a pressure dense region positioning method based on local symmetry and gray scale statistical characteristics, performing central symmetry transformation on a region with high pressure density, performing weighted average on the transformed region and an original image to obtain a transformed image, and obtaining a standard deviation C1：
Figure FDA0002634136730000022
In the formula, MiFor each statistical point in the detection window, each point is marked as 1, NijThe point pressure value;
traversing the position information of each area to obtain the center position information, marking the condition of the maximum standard deviation of the upper standard deviation and the lower standard deviation to obtain two positioning ranges, and comparing the positioning ranges, namely:
Figure FDA0002634136730000023
in the formula, SOn the upper part、SLower partRespectively a detection window area nearest to the head center Z and a detection window area farthest to the head center Z, wherein a is the area ratio of the upper part to the lower part, and when a is larger than K6And SOn the upper partAnd SLower partIs less than K7The human body is lying on the back, the rest is lying on the top, wherein d is SOn the upper partAnd SLower partDistance between central positions, K6Is 0.6, K7Equal to the upper body length H2;
step S4: and establishing a model of the head and neck height changing along with the posture, and adjusting the optimal pillow height according to the human body posture detected in the step.
2. The method for adjusting the height of a neck pillow for sleep posture recognition processing based on a pressure image according to claim 1, wherein in S2:
when the pressure density rho of the pressure image is between K1And K2In the meantime, the human body can not be accurately distinguished to lie in a pitching manner or lie in a side manner, at the moment, the human body lies in a pitching manner, incompletely lies in a side manner or already lies in a side manner, and the state of the human body posture is judged by introducing the balance degree standard of the pressure image;
setting a threshold K3、K4Performing bottom-cap transformation on the pressure image to remove noise influence, and simultaneously selecting a plurality of gray values larger than K5Selecting n x n points near the pressure gray level graph position point to calculate the average difference, and calculating the average difference C3Is composed of
Figure FDA0002634136730000031
In the formula, PpIs the average of n x n dot gray values, PijIs the gray value at position (i, j) when C3Initially above the gradient threshold K3At that pointAnd taking the values as contour points, and counting the positions of the contour points, wherein the balance degree B of the pressure image is as follows:
B＝|∑Li-∑Ri| (8)
in the formula, LiIs the contour point on the left side of the center line, RiIs a contour point on the right side of the central line;
constructing an influence function r:
Figure FDA0002634136730000032
when r is between 0 and K3When lying on the back, when r is at K4When the value is 0, the human body is in a side lying state, and when the value is r, the human body is in an incomplete side lying state.
3. The method for adjusting the height of a neck pillow based on a pressure image for sleep posture recognition processing according to claim 1, characterized in that:
when the human body is lying on the back and the pressure density changes slowly within the time t, the height of the pillow part is Y1；
When the human body is in a lying posture and the pressure density is rapidly reduced, detecting whether the human body is lying on the side or not, if the human body is still lying on the side within the time t and the pressure density changes slowly, adjusting the pillow height to Y2If the human body lies down and the pressure density changes slowly within the time t, the pillow height is adjusted to the minimum value Y3；
When the human body is in a lying posture and the pressure density changes slowly within a time t, the height of the pillow part is Y2；
When the human body is in a side lying posture and the pressure density is rapidly increased, detecting whether the human body lies on the back, if the human body still lies on the back within the time t and the pressure density changes slowly, adjusting the pillow height to Y1If the human body lies down and the pressure density changes slowly within the time t, the pillow height is adjusted to the minimum value Y3。
4. The utility model provides a neck pillow height-adjusting device of neck pillow height-adjusting method based on pressure image carries out appearance of sleeping discernment processing, its includes pillow crust, pressure sensor, diaphragm, curb plate, electric putter, fixed column, pivot, the control unit, eiderdown filling layer, power module, bluetooth module and pressure sensor array, its characterized in that: the electric neck pillow comprises an electric push rod, a side plate, a transverse plate, a control unit, a sensor module, a pressure sensor array, a sensor and a controller, wherein the electric push rod is connected with the fixed column and the side plate, the fixed column is connected with the transverse plate, the control unit is connected with the electric push rod, the pressure sensor array and the pressure sensor array, the power module provides power for the sensor and the controller, the pressure sensor array collects human body pressure images to identify the sleeping postures of a human body, the pressure sensor receives head pressure data to identify the position of the head, and the control unit comprehensively analyzes the human body pressure image information and.
5. The neck pillow height adjusting device for sleep posture recognition processing based on a pressure image according to claim 4, characterized in that: the control unit confirms head central point according to different pressure sensor pressure size, and device height L becomes the negative correlation with pressure sensor pressure N, and the device height becomes positive correlation with electric putter length L, and the functional formula is as follows:
l＝αN+βL (12)
wherein, alpha and beta are correlation coefficients, and alpha is positive and beta is negative.
CN202010820060.3A 2020-08-14 2020-08-14 Method and device for adjusting height of neck pillow based on pressure image for sleep posture recognition processing Active CN112001286B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010820060.3A CN112001286B (en) 2020-08-14 2020-08-14 Method and device for adjusting height of neck pillow based on pressure image for sleep posture recognition processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010820060.3A CN112001286B (en) 2020-08-14 2020-08-14 Method and device for adjusting height of neck pillow based on pressure image for sleep posture recognition processing

Publications (2)

Publication Number Publication Date
CN112001286A true CN112001286A (en) 2020-11-27
CN112001286B CN112001286B (en) 2022-07-08

Family

ID=73473745

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010820060.3A Active CN112001286B (en) 2020-08-14 2020-08-14 Method and device for adjusting height of neck pillow based on pressure image for sleep posture recognition processing

Country Status (1)

Country Link
CN (1) CN112001286B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114569118A (en) * 2022-05-06 2022-06-03 慕思健康睡眠股份有限公司 Sleeping posture detection system and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103689965A (en) * 2014-01-10 2014-04-02 林水龙 Pillow with adjustable height
CN203934951U (en) * 2014-05-06 2014-11-12 张紫娟 A kind of height-adjustable pillow
CN106056116A (en) * 2016-05-31 2016-10-26 河北工业大学 Fuzzy rough set-based sleeping posture pressure image recognition method
CN209595380U (en) * 2019-01-30 2019-11-08 深圳航伴科技有限责任公司 The pillow of automatic adjusument height
CN110432724A (en) * 2019-08-28 2019-11-12 南通金露智能设备有限公司 A kind of change with sleeping position and the pillow of automatic controlled height
KR20200073909A (en) * 2018-12-16 2020-06-24 박홍제 Height adjustable smart pillow

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103689965A (en) * 2014-01-10 2014-04-02 林水龙 Pillow with adjustable height
CN203934951U (en) * 2014-05-06 2014-11-12 张紫娟 A kind of height-adjustable pillow
CN106056116A (en) * 2016-05-31 2016-10-26 河北工业大学 Fuzzy rough set-based sleeping posture pressure image recognition method
KR20200073909A (en) * 2018-12-16 2020-06-24 박홍제 Height adjustable smart pillow
CN209595380U (en) * 2019-01-30 2019-11-08 深圳航伴科技有限责任公司 The pillow of automatic adjusument height
CN110432724A (en) * 2019-08-28 2019-11-12 南通金露智能设备有限公司 A kind of change with sleeping position and the pillow of automatic controlled height

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114569118A (en) * 2022-05-06 2022-06-03 慕思健康睡眠股份有限公司 Sleeping posture detection system and method

Also Published As

Publication number Publication date
CN112001286B (en) 2022-07-08

Similar Documents

Publication Publication Date Title
CN108618465B (en) Soft and hard adjustable mattress for realizing intelligent learning and hardness adjusting system and method thereof
WO2019179378A1 (en) Bedding and method for adjusting bedding
Huang et al. Multimodal sleeping posture classification
CN107169453B (en) Sitting posture detection method based on depth sensor
CN100550037C (en) Utilize and improve Hausdorff apart from the method for extracting the identification human ear characteristic
CN103870843B (en) Head posture estimation method based on multi-feature-point set active shape model (ASM)
CN110934591B (en) Sitting posture detection method and device
CN113269096B (en) Head pressure data deep learning processing method for sleeping gesture recognition
CN107330352A (en) Sleeping position pressure image-recognizing method based on HOG features and machine learning
CN112001286B (en) Method and device for adjusting height of neck pillow based on pressure image for sleep posture recognition processing
CN111291701B (en) Sight tracking method based on image gradient and ellipse fitting algorithm
CN113749467A (en) Sleep improvement method and intelligent mattress
CN109685025A (en) Shoulder feature and sitting posture Activity recognition method
CN105956512A (en) Air conditioner temperature automatic regulating system and air conditioner temperature automatic regulating method based on machine vision
CN108596087A (en) A kind of driving fatigue degree detecting regression model based on dual network result
CN109190458A (en) A kind of person of low position's head inspecting method based on deep learning
CN111481024B (en) Method for automatically adjusting intelligent pillow and intelligent pillow thereof
WO2024207712A1 (en) Sleep image data-based intelligent pressure-sensitive bedding adjusting method and device
CN109028237A (en) The kitchen ventilator of wind speed adjusting is carried out based on dual area Image Acquisition
CN117671739A (en) User identity recognition method and device
CN114627524A (en) Automatic face exposure method based on depth camera
CN111950492B (en) Hypertension risk prediction method based on traditional Chinese medicine theory and palm multi-feature extraction
CN117095443A (en) Face wrinkle detection method
CN208000731U (en) The eyeshield escope of automatic regulating lightness
TWI742696B (en) Multi-parameter physiological signal measuring method

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