CN116391987B - Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data - Google Patents

Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data

Info

Publication number
CN116391987B
CN116391987B CN202310373471.6A CN202310373471A CN116391987B CN 116391987 B CN116391987 B CN 116391987B CN 202310373471 A CN202310373471 A CN 202310373471A CN 116391987 B CN116391987 B CN 116391987B
Authority
CN
China
Prior art keywords
bedding
pressure
image
area
sensitive
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310373471.6A
Other languages
Chinese (zh)
Other versions
CN116391987A (en
Inventor
徐国芳
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.)
Li Shi
Original Assignee
Dongguan Coomo Furniture Co ltd
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 Dongguan Coomo Furniture Co ltd filed Critical Dongguan Coomo Furniture Co ltd
Priority to CN202310373471.6A priority Critical patent/CN116391987B/en
Publication of CN116391987A publication Critical patent/CN116391987A/en
Priority to PCT/CN2023/126217 priority patent/WO2024207712A1/en
Application granted granted Critical
Publication of CN116391987B publication Critical patent/CN116391987B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C17/00—Sofas; Couches; Beds
    • A47C17/86—Parts or details specially adapted for beds, sofas or couches not fully covered by any single one of groups A47C17/02 - A47C17/84
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C21/00—Attachments for beds, e.g. sheet holders or bed-cover holders; Ventilating, cooling or heating means in connection with bedsteads or mattresses
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C27/00—Spring, stuffed or fluid mattresses or cushions specially adapted for chairs, beds or sofas
    • A47C27/08—Fluid mattresses
    • A47C27/081—Fluid mattresses of pneumatic type
    • A47C27/082—Fluid mattresses of pneumatic type with non-manual inflation, e.g. with electric pumps
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C27/00—Spring, stuffed or fluid mattresses or cushions specially adapted for chairs, beds or sofas
    • A47C27/08—Fluid mattresses
    • A47C27/081—Fluid mattresses of pneumatic type
    • A47C27/083—Fluid mattresses of pneumatic type with pressure control, e.g. with pressure sensors
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C27/00—Spring, stuffed or fluid mattresses or cushions specially adapted for chairs, beds or sofas
    • A47C27/08—Fluid mattresses
    • A47C27/081—Fluid mattresses of pneumatic type
    • A47C27/084—Fluid mattresses of pneumatic type self inflating
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47C—CHAIRS; SOFAS; BEDS
    • A47C27/00—Spring, stuffed or fluid mattresses or cushions specially adapted for chairs, beds or sofas
    • A47C27/08—Fluid mattresses
    • A47C27/10—Fluid mattresses with two or more independently-fillable chambers
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Nursing (AREA)
  • Mattresses And Other Support Structures For Chairs And Beds (AREA)

Abstract

本发明公开了一种基于睡眠图像数据的智能压感卧具调节方法及设备，属于智能控制技术领域，用于解决现有的卧具调节方法中，依靠压力数据进行睡姿判断，容易出现误判，导致调节不合理或能耗浪费的技术问题。方法包括：将卧具全景图像与预存的卧具气囊分布图进行叠加，得到卧具叠加图像；将相同时刻的压力数据与卧具叠加图像中对应的折叠气囊位置相关联；根据压力数据，对卧具叠加图像进行分割，得到卧具受压区域图像；在卧具受压区域图像中确定出非人体区域，并将非人体区域中折叠气囊关联的压力数据清零；将处理后的压力数据转换为压力矩阵，并进行分析计算，确定使用者的睡姿信息；根据睡姿信息，对智能压感卧具中的气囊进行充气或抽气处理。

The present invention discloses an intelligent pressure-sensitive bedding adjustment method and device based on sleep image data, belonging to the field of intelligent control technology. The method is used to solve the technical problem that existing bedding adjustment methods rely on pressure data to judge sleeping posture, which is prone to misjudgment, resulting in unreasonable adjustment or energy waste. The method includes: superimposing a panoramic bedding image with a pre-stored bedding airbag distribution map to obtain a bedding superimposed image; associating pressure data at the same time with the corresponding folding airbag positions in the bedding superimposed image; segmenting the bedding superimposed image based on the pressure data to obtain a bedding pressure area image; determining non-human body areas in the bedding pressure area image, and clearing the pressure data associated with the folding airbags in the non-human body areas; converting the processed pressure data into a pressure matrix, and performing analysis and calculation to determine the user's sleeping posture information; and inflating or deflating the airbags in the intelligent pressure-sensitive bedding based on the sleeping posture information.

Description

Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data
Technical Field
The invention relates to the technical field of intelligent control, in particular to an intelligent pressure-sensitive bedding adjusting method and equipment based on sleep image data.
Background
In the sleeping process, the quality of sleeping is directly related to the sleeping posture. Sleep or bed rest is an effective way of relaxing the whole body, particularly the spine, because the body is in full contact with the bed, reducing the burden on the body when standing upright. However, if the sleeping posture is improper or the prone posture is improper, the spine and muscle are contracted seriously, or the local ligament is stretched excessively, so that the diseases such as stiff neck, lumbago and backache are caused, and meanwhile, the body comfort in the sleeping process is also affected.
At present, a plurality of beds or mattresses capable of intelligently adjusting the height are arranged, and different supporting forces are generated on all parts of a user's body by adjusting the heights of different parts of the beds or mattresses, so that the user can keep a normal physiological curve during sleeping. However, the existing intelligent adjustment method is mainly based on the principle that the gesture of a user is judged by collecting pressure data of the user on a mattress, or the gesture of the user is recognized by image collection, so that the user is supported in a corresponding gesture. However, the situation of misjudgment is very easy to occur only by the pressure data detected by the mattress, for example, a weight (such as a schoolbag, a quilt and the like) is placed on the mattress, and the weight is possibly recognized as a part of a human body, so that the posture of the human body is judged wrongly, the condition of unreasonable adjustment height is caused, and the normal use of the mattress is influenced. Or under the condition that the human body is not lying on the mattress, the weight is identified as the human body, and unnecessary automatic adjustment is carried out, so that articles can be possibly dropped, and unnecessary energy consumption is also caused.
Disclosure of Invention
The embodiment of the invention provides an intelligent pressure-sensitive bedding adjusting method and equipment based on sleep image data, which are used for solving the technical problems that in the existing bedding adjusting method, sleep posture judgment is carried out by means of pressure data, misjudgment is easy to occur, and adjustment is unreasonable or energy consumption is wasted.
The embodiment of the invention adopts the following technical scheme:
On one hand, the embodiment of the invention provides an intelligent pressure-sensitive bedding adjusting method based on sleep image data, which at least comprises an image collector, an intelligent air pump, a plurality of folding air bags vertically arranged on a bedding base in an array shape and a plurality of fiber sensors arranged on the surface of each folding air bag; the method comprises the steps of receiving a bedding panoramic image shot by an image collector, superposing the bedding panoramic image with a pre-stored bedding air bag distribution diagram to obtain a bedding superposed image, receiving pressure data transmitted by each fiber sensor, correlating the pressure data at the same moment with corresponding folded air bag positions in the bedding superposed image, dividing the bedding superposed image according to the pressure data to obtain a bedding pressed area image, identifying human body parts of the bedding pressed area image, determining non-human body areas, carrying out zero setting processing on pressure data values correlated with folded air bags in the non-human body areas, converting the pressure data subjected to zero setting processing into a pressure matrix, carrying out analysis and calculation on the pressure matrix to determine sleeping position information of a user, controlling the intelligent air pump according to the sleeping position information, and carrying out air inflation or air suction processing on the air bags in the intelligent pressure-sensitive bedding so as to enable the intelligent pressure-sensitive bedding to carry out intelligent adjustment according to the sleeping position of the user.
In a possible implementation mode, before receiving the bedding panoramic image shot by the image collector, the method further comprises drawing and storing a bedding air bag distribution map according to the picture proportion of the image collector and air bag position design data when the intelligent pressure-sensitive bedding is produced, wherein the bedding air bag distribution map is a black and white line drawing, four vertex coordinates of the intelligent pressure-sensitive bedding are extracted and stored in the bedding air bag distribution map, a shot picture of the image collector is received, whether a first bedding aspect ratio in the shot picture is identical to a second bedding aspect ratio in the bedding air bag distribution map or not is detected, if different, the image collector is controlled to move along a sliding rail until the first bedding aspect ratio is identical to the second bedding aspect ratio, the image collector is installed in the sliding rail right above the intelligent pressure-sensitive bedding and can move in a translational mode along the sliding rail, the sliding rail is parallel to the four vertex coordinates of the intelligent pressure-sensitive bedding, and the image collector is controlled to shoot images of the four vertices of the intelligent pressure-sensitive bedding in parallel to the four vertex coordinates.
In a possible implementation manner, the bedding panoramic image and a pre-stored bedding air bag distribution diagram are overlapped to obtain a bedding overlapped image, and the bedding panoramic image comprises the steps of adjusting black pixels in the bedding air bag distribution diagram to be in a semitransparent state, adjusting white pixels in the bedding air bag distribution diagram to be in a transparent state to obtain a bedding air bag distribution line diagram, aligning four vertexes of the intelligent pressure-sensitive bedding in the bedding air bag distribution line diagram to correspond to the four vertexes of the intelligent pressure-sensitive bedding in the bedding panoramic image, overlapping the bedding air bag distribution line diagram on the upper layer of the bedding panoramic image after alignment, and combining the two layers to obtain the bedding overlapped image.
In a possible implementation mode, the method for correlating the pressure data at the same moment with the positions of the corresponding folding air bags in the bedding superimposed image specifically comprises the steps of performing one-to-one correspondence between the position coordinates of each folding air bag in the bedding superimposed image and the position of each folding air bag in a pre-stored intelligent pressure-sensitive bedding, setting the same serial numbers for the folding air bags positioned at the same position in the bedding superimposed image and the intelligent pressure-sensitive bedding, assigning the serial numbers to fiber sensors corresponding to the surfaces of the folding air bags, and correlating the pressure data returned by each fiber sensor at the current moment with the corresponding folding air bag in the bedding superimposed image according to the serial numbers of each fiber sensor and the serial numbers of each folding air bag in the bedding superimposed image.
In a feasible implementation mode, the bedding superimposed image is segmented according to the numerical value of the pressure data to obtain a bedding pressed area image, and the method specifically comprises the steps of determining all pressed folding air bags with the numerical value of the pressure data not being 0 in the bedding superimposed image, determining pixels in a preset range around each pressed folding air bag, setting the pixel value of the rest pixels to 255, and completing segmentation of the bedding superimposed image to obtain the bedding pressed area image, wherein the preset range is a square circled range taking the circle center of a folded air bag section as a center point and taking two times of the diameter of the folded air bag section as the side length.
In a feasible implementation mode, human body parts of the bedding pressed area image are identified, and non-human body areas are determined, specifically, the method comprises the steps of determining a target area threshold according to gray value distribution of the bedding pressed area image, determining areas with gray values larger than the target area threshold in the bedding pressed area image as target areas, dividing the target area into a plurality of target blocks, calculating gradient histograms of different gradient orientations in each target block by using gradient values of pixel points in each target block as weight vectors, normalizing the gradient histograms of different gradient orientations in each target block to obtain gradient feature vectors of each target block, combining the gradient feature vectors of each target block into gradient feature vectors of the target area, inputting the gradient feature vectors into a classifier, classifying the target blocks as human body areas, communicating the target blocks with classification results as human body targets, determining the target areas except the human body areas in the bedding pressed area image, and determining the non-human body areas.
In a feasible implementation mode, a target area threshold is determined according to gray value distribution of the bedding pressed area image, and specifically comprises the steps of determining a gray value distribution interval in the bedding pressed area image, randomly selecting a plurality of gray values in the gray value distribution interval to serve as a plurality of initial clustering centers, carrying out k-means clustering on the bedding pressed area image, analyzing gray value change data of each clustering center in the clustering process after the clustering is completed, determining a clustering center with mutation of the gray value change data and a mutation point gray value of the clustering center, and determining the mutation point gray value as the target area threshold.
In one possible implementation, the pressure matrix is analyzed and calculated to determine the sleeping gesture of the user, and the method specifically comprises the steps of determining an area where matrix elements with the values larger than 0 are located as a pressed area in the pressure matrix, and counting the number of the matrix elements in the pressed area; according to the matrix element quantity and element scale of the pressed area, the intelligent pressure sensing bedding is used as the current pressed area of the intelligent pressure sensing bedding; the element scale is a proportional relation between a matrix element and the occupied area of a folding air bag in the intelligent pressure-sensitive bedding; the method comprises the steps of comparing a current compression area with preset compression area intervals of different gesture types, preliminarily determining gesture types of a user, wherein the gesture types comprise sitting postures, lying postures and side lying postures, the lying postures comprise lying postures and lying postures, the side lying postures comprise lying postures and lying postures specifically comprise lying postures on the left side and on the right side, acquiring peak values of a plurality of matrix element values in a compression area when the gesture types are lying postures on the side, fitting the peak values of the matrix element values into a straight line, determining the straight line as a stress axis, analyzing the number of matrix elements positioned on two sides of the stress axis in the compression area, determining one side with more matrix elements as the facing side of the user, calculating an element value average value in the compression area when the gesture types are lying postures, determining an area formed by elements smaller than the element value average value as a low stress area when at least one low stress area exists in a longitudinal middle area of the compression area, and determining the user as lying posture otherwise.
In a possible implementation manner, the intelligent air pump is controlled according to the sleeping gesture, and the air bag in the intelligent pressure-sensitive bedding is inflated or exhausted so that the intelligent pressure-sensitive bedding can be intelligently adjusted according to the sleeping gesture of the user, and the intelligent pressure-sensitive bedding specifically comprises the steps of judging the length of the user according to the gesture of the user; the method comprises the steps of determining the position of each body part of a user according to the body length and pressure data distribution condition of the user, dividing the compression area into at least a trunk area, a left upper limb area, a right upper limb area, a left lower limb area and a right lower limb area according to the position of each body part, respectively obtaining the minimum value and the maximum value of element values in each area, averaging to obtain a pressure balance value corresponding to each area, slowly pumping the folded air bags corresponding to elements larger than the pressure balance value in the intelligent pressure sensing bedding, slowly pumping the folded air bags corresponding to elements smaller than the pressure balance value, monitoring the pressure value born by each folded air bag in the compression area in real time, and stopping the air pumping or pumping treatment when the error of the pressure value born by the folded air bags and the corresponding pressure balance value enters an error allowance range or the real-time deformation value reaches the expansion range boundary value corresponding to the current adjusting gear, wherein different adjusting gears correspond to different expansion ranges of the folded air bags.
In another aspect, the embodiment of the invention also provides intelligent pressure-sensing bedding adjusting equipment based on sleep image data, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions capable of being executed by the at least one processor so that the at least one processor can execute the intelligent pressure-sensing bedding adjusting method based on the sleep image data according to any one of the embodiment.
Compared with the prior art, the intelligent pressure-sensitive bedding adjusting method and device based on the sleep image data have the following beneficial effects:
The intelligent pressure sensing adjusting bedding of the invention combines the pressure data collected by the bedding and the image data collected by the image collector to obtain an accurate human body pressure data matrix, thereby being capable of reducing the occurrence of misjudging the pressure data generated by a non-human body as the human body position. And the sleeping gesture of the user is analyzed through the pressure data matrix, the parts of the body of the user are adjusted in a partitioning mode according to the sleeping gesture, and each partitioning is used for adjusting the folding air bag based on different pressure balance values, so that balanced stress and balanced support of the parts of the body of the user are realized. The method can improve the accuracy of the intelligent pressure-sensitive bedding on the sleeping gesture detection result of the user, so that the intelligent pressure-sensitive bedding can be more attached to the body of each user, and a better supporting effect is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art. In the drawings:
FIG. 1 is a top view of an air bag layer structure of an intelligent pressure-sensitive bedding provided by an embodiment of the invention;
FIG. 2 is a top view of a base layer structure of an intelligent pressure-sensitive bedding provided by an embodiment of the invention;
FIG. 3 is a flowchart of an intelligent pressure-sensitive bedding adjusting method based on sleep image data according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an intelligent pressure-sensing bedding adjusting device based on sleep image data according to an embodiment of the present invention;
Reference numerals illustrate:
1. Folding air bag, head strip air bag, foot strip air bag, intelligent air pump, folding air bag mounting groove, head strip air bag mounting groove, and foot strip air bag mounting groove.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present invention.
Firstly, the embodiment of the invention provides an intelligent pressure-sensitive bedding adjusting method based on sleep image data, which is applied to intelligent pressure-sensitive bedding. The intelligent pressure-sensitive bedding of the invention is understood to be an intelligent mattress, which consists of an air bag layer and a base layer.
As a possible implementation manner, fig. 1 is a top view of an air bag layer structure of an intelligent pressure-sensing bedding provided by an embodiment of the present application, as shown in fig. 1, in the air bag layer, a plurality of folded air bags 1 are vertically installed in an array shape, and a fiber sensor (not shown in the figure) is installed on a surface of each folded air bag, so as to send a pressure value born by each folded air bag to a processor. The head and tail parts of the mattress are also provided with head strip-shaped air bags 2 and foot strip-shaped air bags 3 with different numbers. The arrangement mode of the folding air bags can be staggered arrangement as shown in fig. 1, or can be aligned in rows and columns.
Further, the airbag layer is mounted on the base layer, and fig. 2 is a top view of a base layer structure of the intelligent pressure-sensing bedding provided by the embodiment of the application, and as shown in fig. 2, the base layer comprises an intelligent air pump 4, a folding airbag mounting groove 5 for mounting a folding airbag 1, a head strip airbag mounting groove 6 for mounting a head strip airbag 2, and a foot strip airbag mounting groove 7 for mounting a foot strip airbag 3. All folding air bags and all strip air bags are connected with the intelligent air pump 4 through pipelines, and the intelligent air pump is connected with the processor and is used for inflating or exhausting air into the connected air bags according to instructions of the processor. The processor is connected with the fiber sensor on the surface of each air bag through a wire and is used for receiving pressure data transmitted back by the fiber sensor. The intelligent air pump and the processor are both arranged at the bed tail end of the mattress.
The intelligent pressure-sensitive bedding is characterized in that an image collector matched with the intelligent pressure-sensitive bedding and a sliding rail for installing the image collector are additionally arranged on the basis of the structure of the intelligent pressure-sensitive bedding. The slide rail is installed right above the perpendicular bisector of the two short sides of the intelligent pressure-sensitive bedding and is installed in parallel with the perpendicular bisector. So that the image collector can be always positioned on the central line of the intelligent pressure-sensitive bedding when moving on the sliding rail, and the symmetry of shooting vision is maintained. Preferably, the image collector may be an infrared camera or an infrared camera.
Based on the above-mentioned intelligent pressure-sensing bedding structure, fig. 3 is a flowchart of an intelligent pressure-sensing bedding adjusting method based on sleep image data according to an embodiment of the present invention, as shown in fig. 3, where the method specifically includes:
S301, the processor receives the bedding panoramic image shot by the image collector, and superimposes the bedding panoramic image and a pre-stored bedding air bag distribution map to obtain a bedding superimposed image.
Specifically, after the intelligent pressure-sensitive bedding is produced, firstly, according to the picture proportion of a matched image collector and the air bag position design data of the current type of intelligent pressure-sensitive bedding in production, drawing an air bag distribution diagram of the bedding and storing the air bag distribution diagram in a processor of the bedding. Wherein, the distribution diagram of the bedding air bag is a black-white line diagram, the line is black, and the bottom is white.
Further, in the bedding air bag distribution diagram, a plane rectangular coordinate system is established by taking the lower left vertex of the diagram as an original point and two sides connected with the original point as coordinate axes, and then the coordinates of the four vertices of the intelligent pressure-sensitive bedding in the bedding air bag distribution diagram are extracted and stored in a processor.
Further, after the intelligent pressure sensing bedding is installed and the power supply is started, the processor receives a shooting picture of the image collector and detects whether the aspect ratio of the first bedding in the shooting picture is the same as that of the second bedding in the bedding air bag distribution diagram.
If the first bedding aspect ratio and the second bedding aspect ratio are the same, the image collector is proved to be not to be at the right center of the intelligent pressure-sensitive bedding at the moment, so that the image collector is controlled to move along the sliding rail until the first bedding aspect ratio and the second bedding aspect ratio are the same.
Further, the image collector is controlled to zoom, and four vertexes of the intelligent pressure-sensitive bedding in the shot picture are respectively positioned at the stored four vertex coordinates so as to calibrate the image. The purpose of the image calibration is to ensure that the bedding picture shot by the image collector and the pre-stored bedding air bag distribution diagram can be completely overlapped so as to increase the accuracy of subsequent image superposition.
Further, in the bedding airbag distribution map, the transparency value of all pixels with the pixel value of 0 is set to 100, and the transparency value of all pixels with the pixel value of 255 is set to 0, so that the black pixels are adjusted to be in a semitransparent state, and the white pixels are adjusted to be in a transparent state, and the bedding airbag distribution line map is obtained.
As a possible embodiment, the value of the black pixel alpha channel with a pixel value of 0 in the bedding airbag distribution map is set to 100, and the black pixel is set to a semitransparent state. And the value of the alpha channel of the white pixel with the pixel value of 255 is set to be 0, the white pixel is set to be in a transparent state, so that the bedding air bag distribution diagram is converted into a line diagram, and other positions except the line diagram are transparent, so that the image details of the bedding panoramic image are not blocked after superposition.
And after alignment, the bedding air bag distribution line drawing is overlapped on the upper layer of the bedding panoramic image, and the two layers are combined to obtain a bedding overlapped image.
And S302, the processor receives the pressure data returned by each fiber sensor and correlates the pressure data at the same moment with the corresponding folded airbag position in the bedding superimposed image.
Specifically, the processor performs one-to-one correspondence between the position of each folding airbag in the bedding superimposed image and the position of each folding airbag in the intelligent pressure-sensitive bedding. And then, setting the same number for the folded air bags positioned at the same position in the bedding superimposed image and the intelligent pressure-sensitive bedding, and assigning the number to the fiber sensor corresponding to the surface of the folded air bag.
Further, according to the number of each fiber sensor and the number of each folding air bag in the bedding superimposed image, the pressure data returned by each fiber sensor at the current moment is associated with the corresponding folding air bag in the bedding superimposed image.
In one embodiment, the placement direction shown in fig. 1 is taken as the positive direction, the folded airbags at the upper left corner are numbered sequentially, the number of the first folded airbag is 1, the number of the first folded airbag increases sequentially to the right, and after one row is finished, the number is started from the leftmost side of the next row until the last folded airbag is finished in number. According to the mode, the folding air bags in the bedding superimposed image and the folding air bags in the intelligent pressure-sensitive bedding are numbered. And finally, according to the same number, associating the pressure data with the folded air bag in the bedding superimposed image.
S303, dividing the bedding superimposed image according to the numerical value of the pressure data to obtain a bedding pressed area image.
Specifically, in the bedding superimposed image, all the compressed folded airbags whose values of the pressure data are not 0 are determined. And determining pixels in a preset range around each pressed folding air bag, and setting the pixel values of the rest pixels to 255 so as to complete segmentation of the bedding superimposed image and obtain a bedding pressed area image. The preset range is a range circled by a square with the center of the cross section of the folded air bag as a center point and the diameter of the cross section of the folded air bag twice as the side length. The term "segmentation" as used herein is not a segmentation in the conventional sense, but rather, the pixels of the compressed area are kept and the remaining pixels are set to white, and the information contained in the resulting bedding compressed area image can be considered as part of the segmentation from the original image.
As a possible implementation manner, since the bedding superimposed image has both the folded airbag image and the bedding panoramic image, the area where the folded airbag with the pressure data value not being 0 (i.e. the folded airbag which is pressed) is reserved, the pixels of the area where the folded airbag with the pressure data value being 0 (i.e. the folded airbag which is not pressed) is changed to white or cut off directly, and the reserved area is the actual pressed area image of the bedding.
S304, human body part identification is carried out on the bedding pressed area image, a non-human body area is determined, and pressure data associated with the folding air bags in the non-human body area are processed by 0.
The method comprises the steps of determining a gray value distribution interval in a bedding pressed area image, randomly selecting a plurality of gray values in the gray value distribution interval to serve as a plurality of initial clustering centers, carrying out k-means clustering on the bedding pressed area image, analyzing gray value change data of each clustering center in the clustering process after clustering is completed, determining a clustering center with mutation of the gray value change data and a mutation point gray value thereof, and determining the mutation point gray value as a target area threshold.
As a possible implementation manner, since the gray values of the targets in the same class are not greatly different and the gray values of the targets in different classes are greatly different in the infrared image, after clustering is completed, the clustering centers of all subclasses belonging to the same class of target objects still approximately linearly change, and obvious turning is necessarily generated at the clustering centers of the subclasses at the critical positions of the different target objects, so that the threshold value of image segmentation can be determined by determining the gray values at the turning points. The processor records the gray value of the initial clustering center after each clustering in the clustering process, calculates the difference value between the gray value of the clustering center after each clustering and the gray value of the clustering center after the last clustering, and if the error between the difference values calculated each time is always smaller than a certain smaller threshold value until the error between the difference value of a certain time and the previous difference value is larger than the threshold value, the gray value corresponding to the mutation point is the needed target area threshold value.
The method comprises the steps of determining a region with gray values larger than a target region threshold in a bedding pressed region image as a target region, dividing the target region into a plurality of target blocks, calculating gradient histograms with different gradient orientations in each target block by using gradient values of pixel points in each target block as weight vectors, carrying out normalization processing on the gradient histograms with different gradient orientations in each target block to obtain gradient feature vectors of each target block, combining the gradient feature vectors of each target block into gradient feature vectors of the target region, inputting the gradient feature vectors into a classifier to classify the target blocks respectively, and communicating the target blocks with classification results of human targets to determine the human region. And determining the area except the human body area in the bedding compression area image as a non-human body area.
Further, the pressure data values associated with the folded air bags in the determined non-human body area are all set to zero, the processed pressure data are all human body areas if the pressure data are not 0, and the rest pressure data values are all 0 except the human body areas.
The operation eliminates some interference factors in the pressure data, and after the value of the pressure data generated by a non-human body is given 0, the subsequent sleeping gesture recognition is performed, so that the accuracy of sleeping gesture recognition can be greatly improved.
S305, converting the processed pressure data into a pressure matrix, analyzing and calculating the pressure matrix, and determining sleeping posture information of the user.
The processor stores the processed pressure data in a matrix form, namely marking a row number i and a column number j of each folding air bag in the top view of the intelligent pressure sensing bedding, and displaying a pressure value Aij corresponding to the folding air bag (i, j) on an ith row and a jth column of the pressure matrix to finally obtain the complete pressure matrix.
In the pressure matrix, determining the area where matrix elements with the value larger than 0 are located as a pressed area, counting the number of the matrix elements in the pressed area, and taking the area as the current pressed area of the intelligent pressure-sensing bedding according to the number of the matrix elements in the pressed area and an element scale, wherein the element scale is the proportional relation between one matrix element and the occupied area of one folding air bag in the intelligent pressure-sensing bedding. And comparing the current pressure area with preset pressure area intervals of different gesture types to preliminarily determine the gesture type of the user, wherein the gesture type comprises sitting, lying and side lying. Recumbent practice includes supine and prone, and lateral practice includes left lateral and right lateral.
In one embodiment, one element value in the pressure matrix corresponds to the pressure value sensed by one folded airbag, and because a certain gap exists between the folded airbags, the length of the connecting line of the circle centers of the cross sections of the two folded airbags is taken as a side length A, and the area of a square with the side length A is calculated and taken as the actual area occupied by the cross section of one folded airbag. If the actual area occupied by the section of one folded airbag is calculated to be 25cm2, the element ratio is 1:25. In the element scale, the value of the matrix element is constantly 1.
In one embodiment, the magnitude relation of the general pressure receiving areas is that the lying posture is more than the side lying posture, so that different pressure receiving area sections are set for different posture types, and the actual pressure receiving area is in which section, namely the corresponding posture type can be preliminarily determined, and the specific posture is further determined after the posture type is determined.
Further, under the condition that the posture type is lateral lying, peak values of a plurality of matrix element values in the pressed area are obtained, the peak values of the matrix element values are fitted into a straight line, and the straight line is determined as a stress axis. And analyzing the number of matrix elements positioned on two sides of the stress axis in the compression area, and determining the side with the larger number of elements as the facing side of the user. When lying on one side, the main stress area is on the trunk, the element peak value is fitted into a straight line which approximately coincides with the trunk, the number of elements on the left and right sides of the straight line is analyzed, and the side with more elements is the facing direction of a user.
Further, under the condition that the posture type is horizontal, calculating an element value average value in a pressed area, determining an area formed by elements smaller than the element value average value as a low stress area, if at least one low stress area exists in a longitudinal middle area of the pressed area, determining that the user is in a supine posture, otherwise, determining that the user is in a prone posture. The principle of the design is that when a human body is supine, the waist has a camber, the pressure between the waist and the mattress is small, and when the human body is prone, the pressure between the bellyband the mattress is large, so that a region with small pressure is selected by calculating the average value of the pressure of the whole body, and if the region with small pressure exists in the middle section of the pressed region, the user can be determined to lie on the back, otherwise, the user is prone.
S306, controlling the intelligent air pump according to the sleeping gesture, and performing air inflation or air suction treatment on the air bag in the intelligent pressure-sensitive bedding so as to enable the intelligent pressure-sensitive bedding to be intelligently adjusted according to the sleeping gesture of a user.
Specifically, the length of the user is determined according to the posture of the user. The position of each body part of the user is determined according to the length of the user and the distribution condition of the pressure data. Then dividing the compression area into at least a trunk area, a left upper limb area, a right upper limb area, a left lower limb area and a right lower limb area according to the positions of the body parts. And then respectively obtaining the minimum value and the maximum value of the element values in each partition, and averaging to obtain the pressure balance value corresponding to each partition.
In one embodiment, when the posture type of the user is recumbent or recumbent, the maximum span in the vertical direction of the pressed area is first determined as the body length of the user. And then determining the positions of the shoulders and the buttocks according to the region with the maximum pressure of the pressed region, and further determining the positions of other parts such as the neck, the waist, the limbs and the like according to the distribution proportion of the human body, thereby dividing the pressed region into a plurality of subareas.
The weight of different parts of the human body, such as the trunk part and the limbs, has a large difference, if the human body is regarded as a whole for adjustment, the weight difference of the different parts of the human body can be ignored, so that the parts of the human body are adjusted in a partitioning way, and the proper supporting force is obtained for the parts of the human body. When a human body lies on an unadjustable mattress, due to physiological radian, pressure imbalance caused by various parts on the mattress, such as a trunk part, is caused by buttocks, and the pressure caused by the waist on the mattress is relatively small, so that the waist cannot be effectively supported due to unbalanced stress, and meanwhile, discomfort can be caused when the buttocks are in an extrusion state. Therefore, the average value of the maximum value and the minimum value of the pressures in different subareas is calculated to obtain the pressure balance value in the subarea, and the expansion and contraction value of the folding air cushion at the corresponding position is regulated according to the current actual pressure value, so that the pressures between the body and the mattress in the same subarea are more balanced.
Further, in each subarea, the folded air bags corresponding to the elements larger than the pressure balance value are slowly pumped, the folded air bags corresponding to the elements smaller than the pressure balance value are slowly inflated, and the pressure value born by each folded air bag in the compression area is monitored in real time in the inflation or pumping process.
And stopping the air inflation or air extraction treatment when the error of the pressure value born by the folding air bag and the corresponding pressure balance value enters an error allowable range or the real-time deformation value reaches the boundary value of the telescopic interval corresponding to the current adjusting gear. Different adjusting gears correspond to different telescopic sections of the folding air bag.
As a possible implementation, the processor may set different adjustment gears for different weight ranges born by all the folded airbags, and the different adjustment gears correspond to different telescopic sections of the folded airbags. Firstly, adding element values with values larger than a minimum pressure threshold value in the obtained pressure matrix to obtain the total weight currently born by all the folding airbags, wherein the minimum pressure threshold value is used for setting the minimum pressure which can be generated by a human body on the intelligent pressure-sensitive adjusting bedding. And under the condition that the total weight is smaller than a preset weight threshold value, the folding air bag is not adjusted. And under the condition that the total weight is greater than or equal to a preset weight threshold value, determining a corresponding adjusting gear according to a weight range to which the total weight belongs.
In addition, the embodiment of the invention also provides an intelligent pressure-sensitive bedding adjusting device based on the sleep image data, as shown in fig. 4, the intelligent pressure-sensitive bedding adjusting device based on the sleep image data specifically comprises:
and a memory communicatively coupled to the at least one processor, wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform:
Receiving a bedding panoramic image shot by the image collector, and superposing the bedding panoramic image and a pre-stored bedding air bag distribution map to obtain a bedding superposition image;
receiving pressure data transmitted back by each fiber sensor, and correlating the pressure data at the same moment with the corresponding folded air bag position in the bedding superimposed image;
dividing the bedding superimposed image according to the numerical value of the pressure data to obtain a bedding pressed area image;
the image of the pressed area of the bedding is subjected to human body part identification, a non-human body area is determined, and pressure data related to a folding air bag in the non-human body area are processed by 0-degree;
converting the processed pressure data into a pressure matrix, analyzing and calculating the pressure matrix, and determining the sleeping gesture of the user;
And controlling the intelligent air pump according to the sleeping gesture to perform air inflation or air suction treatment on the air bag in the intelligent pressure-sensitive bedding so as to intelligently adjust the intelligent pressure-sensitive bedding according to the sleeping gesture of the user.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.
The foregoing describes certain embodiments of the present invention. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and changes may be made to the embodiments of the invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims (9)

1.一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，所述智能压感卧具至少包括：图像采集器、智能气泵、呈阵列状垂直安装在卧具基座上的若干折叠气囊以及安装于每个折叠气囊表面的若干纤维传感器；所述方法包括：1. A method for adjusting intelligent pressure-sensitive bedding based on sleep image data, characterized in that the intelligent pressure-sensitive bedding comprises at least: an image collector, an intelligent air pump, a plurality of foldable airbags vertically mounted in an array on a bedding base, and a plurality of fiber sensors mounted on the surface of each foldable airbag; the method comprises: 按照所述图像采集器的画面比例，以及智能压感卧具生产时的气囊位置设计数据，绘制卧具气囊分布图并保存；其中，所述卧具气囊分布图为黑白线条图；According to the screen ratio of the image collector and the airbag position design data during the production of the intelligent pressure-sensitive bedding, a bedding airbag distribution map is drawn and saved; wherein the bedding airbag distribution map is a black and white line drawing; 在所述卧具气囊分布图中，提取并保存所述智能压感卧具的四个顶点坐标；Extracting and saving the coordinates of four vertices of the intelligent pressure-sensitive bedding from the bedding airbag distribution map; 接收所述图像采集器的拍摄画面，并检测所述拍摄画面中的第一卧具长宽比例是否与所述卧具气囊分布图中的第二卧具长宽比例相同；receiving a captured image from the image collector, and detecting whether a first bedding length-to-width ratio in the captured image is the same as a second bedding length-to-width ratio in the bedding airbag distribution map; 若不同，则控制所述图像采集器沿滑轨移动，直至所述第一卧具长宽比例与所述第二卧具长宽比例相同；其中，所述图像采集器安装于所述智能压感卧具正上方的滑轨中，并可以沿所述滑轨进行平移移动；所述滑轨与所述智能压感卧具两条短边的中垂线平行；If they are different, controlling the image collector to move along the slide rail until the length-to-width ratio of the first bedding is the same as the length-to-width ratio of the second bedding; wherein the image collector is installed in the slide rail directly above the smart pressure-sensitive bedding and can move translationally along the slide rail; the slide rail is parallel to the perpendicular midline of the two short sides of the smart pressure-sensitive bedding; 控制所述图像采集器进行变焦，将拍摄画面中智能压感卧具的四个顶点分别定位到保存的所述四个顶点坐标处，以进行图像校准；Controlling the image collector to zoom, and positioning the four vertices of the intelligent pressure-sensitive bedding in the captured image to the four saved vertex coordinates, so as to perform image calibration; 接收所述图像采集器拍摄的卧具全景图像，并将所述卧具全景图像与预存的卧具气囊分布图进行叠加，得到卧具叠加图像；receiving a panoramic image of the bedding captured by the image collector, and superimposing the panoramic image of the bedding with a pre-stored bedding airbag distribution map to obtain a superimposed bedding image; 接收每个纤维传感器传回的压力数据，并将相同时刻的压力数据与所述卧具叠加图像中对应的折叠气囊位置相关联；receiving pressure data transmitted by each fiber sensor, and associating the pressure data at the same moment with the corresponding folded airbag position in the bedding overlay image; 根据所述压力数据，对所述卧具叠加图像进行分割，得到卧具受压区域图像；Segmenting the bedding superimposed image according to the pressure data to obtain an image of the bedding pressure area; 对所述卧具受压区域图像进行人体部位识别，确定出非人体区域，并将所述非人体区域中折叠气囊关联的压力数据值做置零处理；Performing human body part recognition on the image of the pressure area of the bedding to determine a non-human body area, and setting the pressure data value associated with the folded airbag in the non-human body area to zero; 将置零处理后的压力数据转换为压力矩阵，并对所述压力矩阵进行分析计算，确定使用者的睡姿信息；Converting the zeroed pressure data into a pressure matrix, and analyzing and calculating the pressure matrix to determine the user's sleeping posture information; 根据所述睡姿信息，控制所述智能气泵，对智能压感卧具中的气囊进行充气或抽气处理，以使所述智能压感卧具根据所述使用者的睡姿进行智能调节。According to the sleeping posture information, the intelligent air pump is controlled to inflate or deflat the airbags in the intelligent pressure-sensitive bedding, so that the intelligent pressure-sensitive bedding can be intelligently adjusted according to the sleeping posture of the user. 2.根据权利要求1所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，将所述卧具全景图像与预存的卧具气囊分布图进行叠加，得到卧具叠加图像，具体包括：2. The intelligent pressure-sensitive bedding adjustment method based on sleep image data according to claim 1, characterized in that the bedding panoramic image is superimposed with a pre-stored bedding airbag distribution map to obtain a bedding superimposed image, specifically comprising: 将所述卧具气囊分布图中，黑色像素调整为半透明状态，白色像素调整为透明状态，得到卧具气囊分布线条图；Adjusting the black pixels in the bedding airbag distribution map to a semi-transparent state and the white pixels to a transparent state to obtain a bedding airbag distribution line map; 将所述卧具气囊分布线条图中智能压感卧具的四个顶点，与所述卧具全景图像中智能压感卧具的四个顶点对应对齐；Aligning four vertices of the smart pressure-sensitive bedding in the bedding airbag distribution line diagram with four vertices of the smart pressure-sensitive bedding in the bedding panoramic image; 对齐之后，将所述卧具气囊分布线条图叠加在所述卧具全景图像的上层，并将两个图层进行合并，得到所述卧具叠加图像。After alignment, the bedding airbag distribution line diagram is superimposed on the upper layer of the bedding panoramic image, and the two layers are merged to obtain the bedding superimposed image. 3.根据权利要求1所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，将相同时刻的压力数据与卧具叠加图像中对应的折叠气囊位置相关联，具体包括：3. The intelligent pressure-sensitive bedding adjustment method based on sleep image data according to claim 1, characterized in that the pressure data at the same time is associated with the corresponding folding airbag position in the bedding superimposed image, specifically comprising: 将所述卧具叠加图像中每个折叠气囊的位置坐标，与预存的智能压感卧具中每个折叠气囊的位置进行一一对应；Matching the position coordinates of each folding airbag in the bedding overlay image with the position of each folding airbag in the pre-stored intelligent pressure-sensitive bedding; 对于所述卧具叠加图像与所述智能压感卧具中位于相同位置的折叠气囊，设置相同的编号，并将所述编号赋给折叠气囊表面对应的纤维传感器；For the folding airbags located at the same position in the bedding superimposed image and the intelligent pressure-sensitive bedding, the same number is set, and the number is assigned to the fiber sensor corresponding to the surface of the folding airbag; 根据每个纤维传感器的编号以及卧具叠加图像中每个折叠气囊的编号，将当前时刻每个纤维传感器传回的压力数据与所述卧具叠加图像中对应的折叠气囊相关联。According to the number of each fiber sensor and the number of each folded airbag in the bedding superimposed image, the pressure data returned by each fiber sensor at the current moment is associated with the corresponding folded airbag in the bedding superimposed image. 4.根据权利要求3所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，根据所述压力数据的数值，对所述卧具叠加图像进行分割，得到卧具受压区域图像，具体包括：4. The intelligent pressure-sensitive bedding adjustment method based on sleep image data according to claim 3, characterized in that the bedding superimposed image is segmented according to the value of the pressure data to obtain the bedding pressure area image, specifically comprising: 在所述卧具叠加图像中，确定出压力数据的数值不为0的所有受压折叠气囊；In the bedding superimposed image, determining all pressurized folded airbags whose pressure data values are not 0; 确定每个受压折叠气囊周围预设范围内的像素，将其余像素的像素值置为255，以完成对所述卧具叠加图像的分割，得到所述卧具受压区域图像；Determine the pixels within a preset range around each compressed folded airbag, and set the pixel values of the remaining pixels to 255 to complete the segmentation of the bedding superimposed image to obtain the compressed area image of the bedding; 其中，所述预设范围为以折叠气囊截面圆心为中心点，以折叠气囊截面直径的二倍为边长的正方形圈出的范围。The preset range is a range enclosed by a square with the center of the cross-section of the folded airbag as the center point and a side length of twice the diameter of the cross-section of the folded airbag as the side length. 5.根据权利要求1所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，对所述卧具受压区域图像进行人体部位识别，确定出非人体区域，具体包括：5. The intelligent pressure-sensitive bedding adjustment method based on sleep image data according to claim 1, characterized in that the method further comprises: performing human body part recognition on the pressure area image of the bedding to determine the non-human area; 根据所述卧具受压区域图像的灰度值分布，确定目标区域阈值；determining a target area threshold according to a grayscale value distribution of the image of the pressure area of the bedding; 将所述卧具受压区域图像中，灰度值大于所述目标区域阈值的区域确定为目标区域；Determining, in the image of the bedding pressure area, an area whose grayscale value is greater than the target area threshold as a target area; 将所述目标区域划分为若干个目标块，使用每个目标块内各像素点的梯度值作为权向量，计算每个目标块内不同梯度朝向的梯度直方图；Divide the target area into several target blocks, use the gradient value of each pixel in each target block as a weight vector, and calculate the gradient histogram of different gradient directions in each target block; 将每个目标块内不同梯度朝向的梯度直方图进行归一化处理，得到每个目标块的梯度特征向量；Normalize the gradient histograms of different gradient directions in each target block to obtain the gradient feature vector of each target block; 将每个目标块的梯度特征向量组合为所述目标区域的梯度特征向量，并输入分类器中，以对各目标块分别进行分类；Combining the gradient feature vectors of each target block into a gradient feature vector of the target region and inputting the gradient feature vectors into a classifier to classify each target block separately; 将分类结果为人体目标的目标块连通起来，确定为人体区域；并将所述卧具受压区域图像中，除所述人体区域之外的区域，确定为所述非人体区域。The target blocks classified as human targets are connected to determine them as human body areas; and the area other than the human body area in the bedding pressure area image is determined as the non-human body area. 6.根据权利要求5所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，根据所述卧具受压区域图像的灰度值分布，确定目标区域阈值，具体包括：6. The intelligent pressure-sensitive bedding adjustment method based on sleep image data according to claim 5, characterized in that determining the target area threshold according to the grayscale value distribution of the pressure area image of the bedding specifically comprises: 确定所述卧具受压区域图像中的灰度值分布区间；Determining a grayscale value distribution interval in the image of the bedding pressure area; 在所述灰度值分布区间中，随机选取多个灰度值，作为多个初始聚类中心，并对所述卧具受压区域图像进行k-均值聚类；In the grayscale value distribution interval, a plurality of grayscale values are randomly selected as a plurality of initial cluster centers, and k-means clustering is performed on the image of the bedding pressure area; 聚类完成后，对聚类过程中各个聚类中心的灰度值变化数据进行分析，确定灰度值变化数据出现突变的聚类中心及其突变点灰度值；After clustering is completed, the grayscale value change data of each cluster center during the clustering process is analyzed to determine the cluster center where the grayscale value change data has a mutation and the grayscale value of the mutation point; 将所述突变点灰度值确定为所述目标区域阈值。The grayscale value of the mutation point is determined as the target area threshold. 7.根据权利要求1所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，对所述压力矩阵进行分析计算，确定使用者的睡姿，具体包括：7. The intelligent pressure-sensitive bedding adjustment method based on sleep image data according to claim 1, wherein analyzing and calculating the pressure matrix to determine the user's sleeping posture specifically comprises: 在所述压力矩阵中，将数值大于0的矩阵元素所在区域确定为受压区域，并统计所述受压区域的矩阵元素数量；In the pressure matrix, the area where the matrix elements with values greater than 0 are located is determined as the pressure area, and the number of matrix elements in the pressure area is counted; 根据所述受压区域的矩阵元素数量以及元素比例尺，作为智能压感卧具的当前受压面积；其中，所述元素比例尺为一个矩阵元素与智能压感卧具中一个折叠气囊所占面积的比例关系；The number of matrix elements and the element scale of the pressure-sensitive area are used as the current pressure-sensitive area of the smart pressure-sensitive bedding; wherein the element scale is the ratio between one matrix element and the area occupied by one folding airbag in the smart pressure-sensitive bedding; 将所述当前受压面积与不同姿势类型的预设受压面积区间进行比对，初步确定所述使用者的姿势类型；其中，所述姿势类型包括坐姿、平卧、侧卧；所述平卧具体包括仰卧以及俯卧，所述侧卧具体包括左侧卧以及右侧卧；Comparing the current pressure area with preset pressure area intervals for different posture types to preliminarily determine the posture type of the user; wherein the posture types include sitting, lying flat, and lying on the side; lying flat specifically includes lying on the back and lying on the stomach, and lying on the side specifically includes lying on the left side and lying on the right side; 在所述姿势类型为侧卧的情况下，获取所述受压区域中的若干个矩阵元素值的峰值，并将所述若干个矩阵元素值的峰值拟合为一条直线，确定为受力轴线；When the posture type is side-lying, obtaining peak values of several matrix element values in the pressure area, and fitting the peak values of the several matrix element values into a straight line to determine it as the force axis; 分析所述受压区域中位于所述受力轴线两侧的矩阵元素数量，将矩阵元素数量多的一侧确定为所述使用者的面向侧；Analyzing the number of matrix elements on both sides of the force axis in the pressure area, and determining the side with more matrix elements as the user facing side; 在所述姿势类型为平卧的情况下，计算所述受压区域中的元素值平均值，并将小于所述元素值平均值的元素形成的区域确定为低受力区；若所述受压区域的纵向中段区域中存在至少一个所述低受力区，则确定所述使用者为仰卧姿势，否则确定所述使用者为俯卧姿势。When the posture type is lying flat, the average value of the element values in the pressure area is calculated, and the area formed by elements smaller than the average value of the element values is determined as a low-force area; if there is at least one low-force area in the longitudinal middle area of the pressure area, the user is determined to be in a supine posture, otherwise the user is determined to be in a prone posture. 8.根据权利要求1所述的一种基于睡眠图像数据的智能压感卧具调节方法，其特征在于，根据所述睡姿，控制所述智能气泵，对所述智能压感卧具中的气囊进行充气或抽气处理，以使所述智能压感卧具根据所述使用者的睡姿进行智能调节，具体包括：8. The method for adjusting intelligent pressure-sensitive bedding based on sleep image data according to claim 1, characterized in that the intelligent air pump is controlled according to the sleeping posture to inflate or deflat the airbags in the intelligent pressure-sensitive bedding, so that the intelligent pressure-sensitive bedding is intelligently adjusted according to the user's sleeping posture, specifically comprising: 根据所述使用者的姿势，判断所述使用者的身长；Determining the height of the user according to the user's posture; 根据所述使用者的身长以及压力数据分布情况，确定所述使用者各个身体部位的位置；Determining the position of each body part of the user according to the user's height and pressure data distribution; 根据所述各个身体部位的位置，将所述受压区域至少划分为躯干分区、左上肢分区、右上肢分区、左下肢分区以及右下肢分区；According to the positions of the various body parts, the compressed area is divided into at least a trunk area, a left upper limb area, a right upper limb area, a left lower limb area, and a right lower limb area; 分别获取每个分区中元素值的最小值以及最大值，并求平均值，得到所述每个分区对应的压力平衡值；Obtain the minimum and maximum values of the elements in each partition respectively, and calculate the average value to obtain the pressure balance value corresponding to each partition; 对智能压感卧具中，大于所述压力平衡值的元素对应的折叠气囊进行缓慢抽气，对小于所述压力平衡值的元素对应的折叠气囊进行缓慢充气；Slowly deflating the folding airbags corresponding to the elements with a pressure greater than the pressure balance value in the intelligent pressure-sensitive bedding, and slowly inflating the folding airbags corresponding to the elements with a pressure less than the pressure balance value; 实时监测充气或抽气过程中，受压区域中每个折叠气囊承受的压力值；Real-time monitoring of the pressure value of each folded airbag in the pressurized area during inflation or deflating; 在所述折叠气囊承受的压力值与对应的压力平衡值的误差进入误差允许范围，或者实时形变值达到当前调节档位对应的伸缩区间边界值时，停止充气或抽气处理；其中，不同的调节档位对应所述折叠气囊的不同伸缩区间。When the error between the pressure value borne by the folding airbag and the corresponding pressure balance value enters the allowable error range, or the real-time deformation value reaches the boundary value of the expansion and contraction range corresponding to the current adjustment gear, the inflation or exhaust process is stopped; wherein different adjustment gears correspond to different expansion and contraction ranges of the folding airbag. 9.一种基于睡眠图像数据的智能压感卧具调节设备，其特征在于，所述设备包括：9. An intelligent pressure-sensitive bedding adjustment device based on sleep image data, characterized in that the device comprises: 至少一个处理器；以及，at least one processor; and, 与所述至少一个处理器通信连接的存储器；其中，a memory communicatively connected to the at least one processor; wherein, 所述存储器存储有能够被所述至少一个处理器执行的指令，以使所述至少一个处理器能够执行根据权利要求1-8任一项所述的一种基于睡眠图像数据的智能压感卧具调节方法。The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute the intelligent pressure-sensitive bedding adjustment method based on sleep image data according to any one of claims 1 to 8.
CN202310373471.6A 2023-04-07 2023-04-07 Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data Active CN116391987B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202310373471.6A CN116391987B (en) 2023-04-07 2023-04-07 Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data
PCT/CN2023/126217 WO2024207712A1 (en) 2023-04-07 2023-10-24 Sleep image data-based intelligent pressure-sensitive bedding adjusting method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310373471.6A CN116391987B (en) 2023-04-07 2023-04-07 Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data

Publications (2)

Publication Number Publication Date
CN116391987A CN116391987A (en) 2023-07-07
CN116391987B true CN116391987B (en) 2025-08-08

Family

ID=87009898

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310373471.6A Active CN116391987B (en) 2023-04-07 2023-04-07 Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data

Country Status (2)

Country Link
CN (1) CN116391987B (en)
WO (1) WO2024207712A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116391987B (en) * 2023-04-07 2025-08-08 李拾 Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108618465A (en) * 2018-04-18 2018-10-09 浙江想能云软件股份有限公司 A kind of soft or hard adjustable bed mattess that realizing intelligence learning and its hardness regulating system and method
CN113749467A (en) * 2021-09-29 2021-12-07 慕思健康睡眠股份有限公司 Sleep improvement method and intelligent mattress

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2255293B1 (en) * 2008-02-14 2012-10-31 Kingsdown, Inc. Apparatuses and methods for evaluating a person for a sleep system
KR101586908B1 (en) * 2014-05-21 2016-01-20 김창효 Apparatus for adjusting hight of pillow
CN105705091A (en) * 2014-06-02 2016-06-22 住友理工株式会社 Orientation determination device and orientation determination method
CN105877713B (en) * 2016-06-19 2019-03-26 河北工业大学 A method of fusion multiple information adjust automatically sleeping position
CN108175219A (en) * 2017-12-11 2018-06-19 绵眠（上海）智能科技有限公司 A kind of air bag sleep method for supporting and system based on pressure distribution
CN109124166A (en) * 2018-07-24 2019-01-04 深圳市赛亿科技开发有限公司 Intelligent mattress and its management-control method, electronic equipment and storage medium
TW202034882A (en) * 2019-03-20 2020-10-01 醫博科技股份有限公司 Method for human body support device and system thereof
CN111000528B (en) * 2019-12-23 2021-01-12 西南交通大学 Method for detecting sleeping posture of human body
CN113688720B (en) * 2021-08-23 2024-05-31 安徽农业大学 A method for predicting sleeping posture based on neural network recognition
CN115211692A (en) * 2022-08-16 2022-10-21 浙江世矩科技股份有限公司 Electric bed capable of being automatically adjusted and control method thereof
CN116391987B (en) * 2023-04-07 2025-08-08 李拾 Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108618465A (en) * 2018-04-18 2018-10-09 浙江想能云软件股份有限公司 A kind of soft or hard adjustable bed mattess that realizing intelligence learning and its hardness regulating system and method
CN113749467A (en) * 2021-09-29 2021-12-07 慕思健康睡眠股份有限公司 Sleep improvement method and intelligent mattress

Also Published As

Publication number Publication date
CN116391987A (en) 2023-07-07
WO2024207712A1 (en) 2024-10-10

Similar Documents

Publication Publication Date Title
CN109919132B (en) A pedestrian fall recognition method based on skeleton detection
CN108618465B (en) Soft and hard adjustable mattress for realizing intelligent learning and hardness adjusting system and method thereof
US9033901B2 (en) System for determining individual user anthropometric characteristics related to mattress preference
EP4147637B1 (en) Gait analysis system and method
CN110532850B (en) A Fall Detection Method Based on Video Joints and Hybrid Classifiers
CN116391987B (en) Intelligent pressure-sensitive bedding adjusting method and device based on sleep image data
CN107169453B (en) Sitting posture detection method based on depth sensor
CN108244874B (en) Automatic adjusting bed
CN105877713A (en) Method for automatically adjusting sleeping postures by fusing multivariate information
TW202034882A (en) Method for human body support device and system thereof
CN113269096A (en) Head pressure data deep learning processing method for sleeping posture recognition
CN116458744B (en) A method and device for adjusting intelligent pressure-sensitive bedding based on sleep state
CN117502858A (en) Intelligent mattress, sleep fit degree adjusting system and method
CN114601454A (en) A kind of monitoring method of patient's bed position
CN109271918A (en) The method for distinguishing balanced capacity obstacle crowd based on centre-of gravity shift model
CN120147238A (en) A metal powder packaging quality inspection system based on machine vision
CN215304706U (en) Height-adjustable pillow
CN117338285B (en) Scoliosis detection device and method
CN114550099A (en) Comprehensive health management system based on digital twins
CN104970640B (en) Pillow with automatic pillow height adjustment and using method thereof
CN111012360B (en) Device and method for collecting nervous system data of drug addiction stopping personnel
CN113749651B (en) Pressure evaluation method and pressure evaluation system based on human body gesture recognition
CN119006607A (en) Footprint calibration and feature extraction method, system, medium and equipment based on pressure
JPH08145825A (en) Animal attribute identification device
CN115429066A (en) A method and system for recognizing the intention to get out of bed of an array airbag mattress

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20230803

Address after: 523560 Room 5-1001, Tianlongwan, Lidi Yuhuayuan Community, Nancheng District, Dongguan City, Guangdong Province

Applicant after: Li Shi

Address before: Building 2, No. 316 Kangle South Road, Houjie Town, Dongguan City, Guangdong Province, 523282

Applicant before: DONGGUAN COOMO FURNITURE Co.,Ltd.

GR01 Patent grant
GR01 Patent grant