CN115272588B - Human body spine fitting method and system based on depth image and electronic equipment - Google Patents
Human body spine fitting method and system based on depth image and electronic equipment Download PDFInfo
- Publication number
- CN115272588B CN115272588B CN202211177644.9A CN202211177644A CN115272588B CN 115272588 B CN115272588 B CN 115272588B CN 202211177644 A CN202211177644 A CN 202211177644A CN 115272588 B CN115272588 B CN 115272588B
- Authority
- CN
- China
- Prior art keywords
- value
- plane
- plane function
- connecting line
- spine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000006870 function Effects 0.000 claims description 81
- 238000005070 sampling Methods 0.000 claims description 54
- 238000012545 processing Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 210000001015 abdomen Anatomy 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims 1
- 206010039722 scoliosis Diseases 0.000 abstract description 8
- 238000003325 tomography Methods 0.000 description 7
- 238000012935 Averaging Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000000691 measurement method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002612 cardiopulmonary effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 210000000115 thoracic cavity Anatomy 0.000 description 2
- 230000037237 body shape Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
- G06T2207/30012—Spine; Backbone
Abstract
The disclosure relates to a depth image-based human spine fitting method, a depth image-based human spine fitting system and electronic equipment, wherein the method comprises the following steps: acquiring a depth image of the back of a human body; acquiring depth data of a depth image; intercepting back data in the depth data; calculating to obtain a first discrete set and a second discrete set; respectively obtaining the total number of the first connecting line, the second connecting line and the first inflection pointAnd a second total number of inflection points(ii) a Calculating to obtain a first plane function about a spinal coronal plane and constructing a first spinal fitting curve; and calculating to obtain a second plane function about the sagittal plane of the spine and constructing a second spine fitting curve. The system and the electronic equipment are used for executing the method. The method has the advantages of high accuracy of fitting results, capability of realizing spinal fitting in two directions of the human body coronal plane and the sagittal plane, capability of meeting the requirement of scoliosis examination, and better applicability and data containment.
Description
Technical Field
The disclosure relates to the technical field of image processing, in particular to a human body spine fitting method and system based on a depth image and an electronic device.
Background
The spine is the central axis of a human body, and not only can abnormal body appearance and movement dysfunction be caused when the spine is seriously bent laterally, but also cardiopulmonary dysfunction can be caused due to thoracic deformity, the life quality is reduced, and the physical and mental health development of teenagers is seriously influenced. If the disease is discovered and actively treated in short time, the disease not only affects the body shape and appearance of the sick children, but also can cause abnormal cardio-pulmonary function, leads the spine to be degenerated early, causes pain and causes unbalanced trunk.
There are many methods for examining scoliosis, and these methods can be roughly classified into physical measurement and image measurement. The physical measurement refers to measuring scoliosis by directly contacting with the back of a human body; the image measurement is an inspection method that does not directly contact the back of the human body, and mainly includes a moire image measurement method, an X-ray film measurement method, a structured light measurement method, a laser scanner measurement method, and the like.
With the development of image processing technology, an image measuring method is a main trend of scoliosis detection in the future because the image measuring method has the advantages of high measuring efficiency, high precision and small subjective influence, wherein an X-ray film measuring method needs to directly obtain a tomography two-dimensional image sequence of a spine from a patient when three-dimensional reconstruction is carried out on human tissues and organs, the number of the final tomography two-dimensional image sequences is about 600 in the tomography two-dimensional image sequence with complete thoracic vertebra and lumbar vertebra, the quantity of the final tomography two-dimensional image sequences is influenced by the sizes of spines of different ages and the size of the tomography two-dimensional image sequence, and long-time tomography scanning is needed to be carried out on a human body to obtain the quantity of the tomography two-dimensional image sequences.
The other image measuring method is to acquire the back image of the human body through a digital camera, further acquire the back contour data of the human body, and calculate the position of the fitting spine through processing and analyzing the two-dimensional image data. Although the method does not need X-ray scanning, the fitting accuracy is influenced by data dimension because the method is based on two-dimensional image data, interference and deviation are easy to occur, and the accuracy of the fitting result is influenced.
Disclosure of Invention
In order to solve the problems in the prior art, the present disclosure aims to provide a method and a system for fitting a spine of a human body based on a depth image, and an electronic device. The method carries out human spine fitting based on the depth image, has high accuracy of fitting results, can realize spine fitting in two directions of a human coronal plane and a sagittal plane, can meet the requirement of scoliosis examination, and has better applicability and data containment.
The human body spine fitting method based on the depth image comprises the following steps:
s01, acquiring a depth image of the back of a human body;
s02, obtaining depth data of the obtained depth image;
s03, intercepting back data about a spine part in the depth data;
s04, calculating and obtaining a first discrete set consisting of numerical values of two dimensions of a coronal plane and a second discrete set consisting of numerical values of two dimensions of a sagittal plane according to the back data;
s05, processing the first discrete set and the second discrete set to respectively obtain a first connecting line for representing the numerical distribution trend of the first discrete set and a second connecting line for representing the numerical distribution trend of the second discrete set;
s06, analyzing the first connecting line and the second connecting line to obtain the total number of first inflection points of the first connecting lineAnd a second total number of inflection points for the second line;
S07, combining the first discrete set and the first total number of inflection pointsCalculating to obtain a first plane function about a coronal plane of the spine, and constructing a first spine fitting curve about the coronal plane based on the first plane function;
combining the second discrete set and the second total number of inflection pointsAnd calculating to obtain a second plane function about the sagittal plane of the spine, and constructing a second spine fitting curve about the sagittal plane based on the second plane function.
Preferably, the step S03 includes:
s031, process the said depth data, discern the human body outline and label the bony landmark point in the said depth picture;
s032, two bony marking points at two ends of a spine part are selected, and depth data between the two selected bony marking points are intercepted and used as the back data.
Preferably, in step S04, a horizontal plane is defined as an x-z plane, a coronal plane is defined as a y-x plane, a sagittal plane is defined as a y-z plane, a left side to a right side of the human body is a positive x-axis direction, a foot side to a head side is a positive y-axis direction, and a back side to an abdomen side is a positive z-axis direction.
Preferably, the step S04 is specifically:
traversing the back data, obtaining all x values corresponding to each y value independently, recording as an x value set corresponding to the y value, calculating the average value and variance of each x value set, carrying out numerical judgment on the obtained variance, if the obtained variance is more than 5, taking the median of the x value set as the x value corresponding to the y value, otherwise, taking the average of the x value set as the x value corresponding to the y value, and forming the first discrete set according to each y value and the corresponding x value thereof;
traversing the back data, obtaining all z values corresponding to all y values, recording the z values as z value sets corresponding to all y values, calculating the average value and variance of all the z value sets, carrying out numerical judgment on the obtained variance, taking the median of the z value set as the z value corresponding to the y value if the obtained variance is more than 5, otherwise, taking the average of the z value set as the z value corresponding to the y value, and forming the second discrete set according to all the y values and the z values corresponding to the y values.
Preferably, in the step S05, the processing the first discrete set and the second discrete set specifically includes:
and carrying out smoothing processing and noise point elimination on the first discrete set and the second discrete set.
Preferably, in the step S06, the first connection line and the second connection line are processed through a sliding window algorithm, a numerical variation trend of each sampling point in a window is analyzed, and whether an inflection point exists in the window is determined, which is specifically as follows:
setting the number of sampling points in the window asWhen the front in the windowEach sampling point has the same variation trend, and thenOne sampling point is another variation trend, and the most value of the first connection line/the second connection line in the window appears at the secondA sampling point or the secondA sampling point orA sampling point and the secondWhen sampling points are arranged among the sampling points, judging that an inflection point exists in a section of the first connecting line/the second connecting line in the window; wherein the content of the first and second substances,;
performing segment-by-segment analysis on the first connecting line and the second connecting line through a sliding window algorithm, and performing accumulated counting on the number of inflection points to obtain the total number of the first inflection pointsAnd a second total number of inflection points。
Preferably, in the step S07, the first discrete set and the first total number of inflection points are combinedThe first plane function obtained by calculation with respect to the coronal plane of the spine is specifically:
comparing the first discrete set and the first total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the first plane function:
obtaining a first plane function according to the plane function coefficient of the obtained first plane function, wherein the first plane function is obtained by:
combining the second discrete set and the second total number of inflection pointsThe second plane function obtained by calculation with respect to the sagittal plane of the spine is specifically:
combining the second discrete set and the second total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the second plane function:
according to the plane function coefficient of the obtained second plane function, obtaining the second plane function as:
the utility model discloses a human backbone fitting system based on depth image includes:
the image acquisition module is used for acquiring a depth image of the back of a human body;
a depth data acquisition module for acquiring depth data of the obtained depth image;
the intercepting module is used for processing the depth data, identifying a human body contour in the depth image and marking bony mark points; selecting two bony mark points at two ends of a spine part, and intercepting depth data between the two selected bony mark points as back data;
the discrete set calculation module is used for defining that the horizontal plane is an x-z plane, the coronal plane is a y-x plane, the sagittal plane is a y-z plane, the left side to the right side of the human body is the positive direction of an x axis, the feet are the positive directions of a y axis towards the head, and the back is the positive direction of a z axis towards the abdomen;
traversing the back data, obtaining all x values corresponding to each y value independently, recording as an x value set corresponding to the y value, calculating the average value and variance of each x value set, carrying out numerical judgment on the obtained variance, if the obtained variance is more than 5, taking the median of the x value set as the x value corresponding to the y value, otherwise, taking the average of the x value set as the x value corresponding to the y value, and forming a first discrete set according to each y value and the corresponding x value thereof;
traversing the back data, acquiring all z values corresponding to all y values, recording the z values as z value sets corresponding to all y values, calculating the average value and variance of each z value set, carrying out numerical judgment on the obtained variance, taking the median of the z value set as the z value corresponding to the y value if the obtained variance is more than 5, otherwise, taking the average of the z value set as the z value corresponding to the y value, and forming a second discrete set according to all y values and the z values corresponding to the y values;
the connecting line construction module is used for performing smoothing processing and noise point elimination on the first discrete set and the second discrete set to respectively obtain a first connecting line for representing the numerical value distribution trend of the first discrete set and a second connecting line for representing the numerical value distribution trend of the second discrete set;
the inflection point calculation module is used for processing the first connecting line and the second connecting line through a sliding window algorithm, analyzing the numerical value variation trend of each sampling point in a window and judging whether an inflection point exists in the window, and specifically comprises the following steps:
setting the number of sampling points in the window asWhen the front in the windowEach sampling point has the same variation trend, and thenOne sampling point is another variation trend, and the most value of the first line/the second line in the window appears at the firstA sampling point orA sampling point orA sampling point and the secondWhen sampling points are arranged among the sampling points, judging that an inflection point exists in a section of the first connecting line/the second connecting line in the window; wherein the content of the first and second substances,;
performing segment-by-segment analysis on the first connecting line and the second connecting line through a sliding window algorithm, and performing accumulated counting on the number of inflection points to obtain the total number of the first inflection pointsAnd a second total number of inflection points;
A fitting curve construction module to combine the first discrete set and the first total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the first plane function:
obtaining a first plane function according to the plane function coefficient of the obtained first plane function, wherein the first plane function is obtained by:
constructing a first spine fit curve about a coronal plane based on the first planar function;
combining the second discrete set and the second total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the second plane function:
according to the plane function coefficient of the obtained second plane function, obtaining the second plane function as:
constructing a second spine-fitting curve about the sagittal plane based on the second plane function.
A computer device of the present disclosure comprises a processor and a memory in signal connection, wherein the memory has stored therein at least one instruction or at least one program which, when loaded by the processor, performs the method of human spine fitting based on depth images as described above.
A computer readable storage medium of the present disclosure has stored thereon at least one instruction or at least one program which, when loaded by a processor, performs a depth image based human spine fitting method as described above.
The human body spine fitting method, the human body spine fitting system and the electronic equipment based on the depth image have the advantages that depth data with three-dimensional attributes can be obtained based on the depth image of the back of a human body, a first discrete set related to dimension values of a coronal plane and a second discrete set related to dimension values of a sagittal plane can be obtained based on the depth data, the first discrete set and the second discrete set are respectively converted into a first connecting line and a second connecting line, and the first connecting line and the second connecting line are analyzed to obtain the total number of first inflection pointsAnd a second total number of inflection pointsCombining the first discrete set and the first total number of inflection pointsA first spine fit curve for characterizing the spine backprojection may be obtained, combining the second discrete set and the second total number of inflection pointsCan be obtained for characterizing the spineAnd the second spine fitting curve projected from the side surface can be used for checking and analyzing the scoliosis condition according to the first spine fitting curve and the second spine fitting curve.
The spine curve fitting method based on the depth data with the three-dimensional attributes can avoid the influence of data dimensions on fitting accuracy, reduce interference and deviation, avoid the influence of factors such as skin color on fitting results, and remarkably improve the accuracy of the fitting results. And the fitting of the spine in two directions of the coronal plane and the sagittal plane of the human body can be realized, and the requirement of scoliosis examination can be met. Meanwhile, the spine curve fitting method is not limited to the shape of the spine curve, can effectively fit various abnormal spine curves, and is better in applicability and data containment.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for fitting a spine of a human body based on depth images according to an embodiment;
fig. 2 is a schematic view of the depth image obtained in step S01 in this embodiment;
fig. 3 is a schematic diagram of marking bony landmark points in the depth image in step S03 in this embodiment;
fig. 4 is a schematic diagram of intercepting the back data in step S03 in this embodiment;
FIG. 5 is a schematic illustration of a first spine fit curve and a second spine fit curve obtained in accordance with the present embodiment;
fig. 6 is a schematic structural diagram of the computer device according to this embodiment.
Description of the reference numerals: 101-processor, 102-memory.
Detailed Description
As shown in fig. 1, a depth image-based human spine fitting method according to the present disclosure includes the following steps:
s01, acquiring a depth image of the back of a human body; specifically, the back of the human body is imaged by using a depth camera, and a depth image of the back of the human body as shown in fig. 2 is acquired and obtained.
S02, obtaining depth data of the obtained depth image; specifically, the acquired depth image is read, and the related depth data in the depth image as shown in fig. 3 is acquired.
S03, intercepting back data related to a spine part in the depth data; specifically, step S03 includes:
s031, the depth data obtained in step S02 is mainly subjected to denoising, filtering and smoothing treatment on the human body surface distance values in sequence, as shown in FIG. 3, the human body contour in the depth data is identified, and the bony mark points C1, C7, T12, S5 and L5 about the human body spine are marked according to the human body medical theory;
s032, selecting two bony landmark points at two ends of the spinal column, and capturing depth data between the two selected bony landmark points as back data, in this embodiment, as shown in fig. 4, capturing depth data in a range from C1 to S5 as back data.
S04, calculating and obtaining a first discrete set consisting of numerical values of two dimensions of a coronal plane and a second discrete set consisting of numerical values of two dimensions of a sagittal plane according to the back data;
specifically, in order to facilitate calculation of specific numerical values, a human body horizontal plane is taken as an x-z plane, a coronal plane is taken as a y-x plane, a sagittal plane is taken as a y-z plane to construct a space rectangular coordinate system, and the left side to the right side of the human body is defined as the positive direction of an x axis, the feet to the head is defined as the positive direction of a y axis, and the back to the abdomen is defined as the positive direction of a z axis. There are a y-value (y-axis coordinate point) and an x-value (x-axis coordinate point) on the coronal plane for the spine curve and a y-value and a z-value (z-axis coordinate point) on the sagittal plane for the spine curve.
Based on the above defined spatial rectangular coordinate system, step S04 specifically includes:
traversing the obtained back data, wherein the back data is on a y-x plane, each y value can correspond to a plurality of different x values, all the x values corresponding to each y value are obtained as a number set and are recorded as the x value sets corresponding to the y values, the average difference and variance of each x value set are calculated, the obtained variance is subjected to numerical judgment, if the obtained variance is more than 5, the discrete degree of the x value set is represented to be larger, the median of the x value set is taken as the x value corresponding to the y value, otherwise, the average of the x value set is taken as the x value corresponding to the y value, and through the steps, each y value and the corresponding x value are determined to form a first discrete set related to the y value and the x value.
The second discrete set is constructed in the same manner as the first discrete set, specifically as follows:
traversing the obtained back data, wherein the back data is on a y-z plane, each y value can correspond to a plurality of different z values, all the z values corresponding to each y value are obtained as a number set and are recorded as the z value set corresponding to the y value, the average difference and variance of each z value set are calculated, the obtained variance is subjected to numerical judgment, if the obtained variance is larger than 5, the discrete degree of the z value set is represented to be larger, the median of the z value set is taken as the z value corresponding to the y value, otherwise, the average of the z value set is taken as the z value corresponding to the y value, and through the steps, each y value and the corresponding z value are determined to form a second discrete set related to the y value and the z value.
Through the above steps, a first discrete set of values for y and x and a second discrete set of values for y and z are obtained.
S05, smoothing the first discrete set and the second discrete set and eliminating noise points to improve the smoothness and accuracy of data, respectively marking each numerical value of the first discrete set and the second discrete set on a coordinate system and then connecting the numerical values to obtain a first connecting line for representing the numerical value distribution trend of the first discrete set and a second connecting line for representing the numerical value distribution trend of the second discrete set;
s06, analyzing the first connecting line and the second connecting line to obtain the total number of first inflection points of the first connecting lineAnd a second total number of inflection points for the second line(ii) a The method comprises the following specific steps: the sliding window algorithm is used for processing the first connecting line and the second connecting line, analyzing the numerical value change trend of each sampling point in the window and judging whether an inflection point exists in the window, wherein the method specifically comprises the following steps:
with sampling points in the windowIn an amount ofWhen the front in the windowEach sampling point has the same variation trend, and thenOne sampling point is another variation trend, and the most value of the first connection line/the second connection line in the window appears at the secondA sampling point or the secondA sampling point or the secondA sampling point and the secondWhen sampling points are arranged among the sampling points, judging that an inflection point exists in a section of the first connecting line/the second connecting line in the window; wherein, the first and second connecting parts are connected with each other;
the method for judging whether a plurality of sampling points are in the same change trend is as follows:
sequentially averaging every two adjacent sampling points in the window, e.g. averaging the 1 st and 2 nd sampling points, averaging the 2 nd and 3 rd sampling points, and so on, averaging the 3 rd sampling pointA sampling point and aTaking the average value of each sampling point to obtainAverage value, in sequence、...If, if,,,Then the connection is determined to have the same upward trend in the first 4 sampling points and another trend, i.e., a downward trend, in the 5 th and 6 th sampling points.
Performing segment-by-segment analysis on the first connecting line and the second connecting line through a sliding window algorithm, and performing accumulation counting on the number of inflection points to obtain the total number of the first inflection pointsAnd a second total number of inflection points。
S07, combining the first discrete set and the first total number of inflection pointsAnd calculating to obtain a first plane function about a coronal plane of the spine, and constructing a first spine fitting curve about the coronal plane based on the first plane function, specifically as follows:
summing the first discrete set and the first total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the first plane function:
obtaining a first plane function according to the plane function coefficient of the obtained first plane function, wherein the first plane function is obtained by:
based on the resulting first plane function, a first spine fit curve with respect to the coronal plane as shown on the right side of FIG. 5 is constructed.
Combining the second discrete set and the second total number of inflection pointsAnd calculating to obtain a second plane function related to the sagittal plane of the spine, and constructing a second spine fitting curve related to the sagittal plane based on the second plane function, wherein the method specifically comprises the following steps:
comparing the second discrete set and the second total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the second plane function:
obtaining a second plane function according to the plane function coefficient of the obtained second plane function, wherein the second plane function is obtained by:
based on the resulting second planar function, a second spine fit curve is constructed about the sagittal plane as shown on the left side of FIG. 5.
The spine curve fitting method based on the depth data with the three-dimensional attributes can avoid the influence of data dimensions on fitting accuracy, reduce interference and deviation, avoid the influence of factors such as skin colors on fitting results, and remarkably improve the accuracy of the fitting results. And the fitting of the spine in two directions of the coronal plane and the sagittal plane of the human body can be realized, and the requirement of scoliosis examination can be met. Meanwhile, the spine curve fitting method is not limited to the shape of the spine curve, can effectively fit various abnormal spine curves, and is better in applicability and data containment.
The embodiment also provides a human spine fitting system based on depth images, which includes:
the image acquisition module is used for acquiring a depth image of the back of a human body;
a depth data acquisition module for acquiring depth data of the obtained depth image;
an intercepting module for intercepting back data regarding a spine portion in the depth data;
a discrete set calculation module for calculating and obtaining a first discrete set composed of values of two dimensions of a coronal plane and a second discrete set composed of values of two dimensions of a sagittal plane according to the back data;
a connecting line construction module, configured to process the first discrete set and the second discrete set, and obtain a first connecting line used for representing a trend of a numerical distribution of the first discrete set and a second connecting line used for representing a trend of a numerical distribution of the second discrete set, respectively;
a total number of inflection points for the first line obtained by analyzing the first and second linesAnd a second total number of inflection points for the second line;
A fitting curve construction module to combine the first discrete set and the first total number of inflection pointsCalculating to obtain a first plane function about a coronal plane of the spine, and constructing a first spine fitting curve about the coronal plane based on the first plane function;
combining the second discrete set and the second total number of inflection pointsAnd calculating to obtain a second plane function about the sagittal plane of the spine, and constructing a second spine fitting curve about the sagittal plane based on the second plane function.
The human body spine fitting system based on depth images of the present embodiment and the method embodiments described above are based on the same inventive concept, and can be understood by referring to the description of the method embodiments, which is not repeated herein.
As shown in fig. 6, this embodiment further provides a computer device, which includes a processor 101 and a memory 102 connected by bus signals, where the memory 102 stores at least one instruction or at least one program, and when the at least one instruction or the at least one program is loaded by the processor 101, the method for fitting the spine of the human body based on the depth image as described above is performed. The memory 102 may be used to store software programs and modules, and the processor 101 executes various functional applications by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory 102 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 access to the memory 102.
The method embodiments provided by the embodiments of the present disclosure may be executed in a computer terminal, a server or a similar computing device, that is, the computer device may include a computer terminal, a server or a similar computing device. The internal structure of the computer device may include, but is not limited to: a processor, a network interface, and a memory. The processor, the network interface and the memory in the computer device may be connected by a bus or other means.
The processor 101 (or CPU) is a computing core and a control core of the computer device. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI, mobile communication interface, etc.). The Memory 102 (Memory) is a Memory device in the computer device for storing programs and data. It is understood that the memory 102 may be a high-speed RAM storage device, or may be a non-volatile storage device (non-volatile memory), such as at least one magnetic disk storage device; optionally, at least one memory device located remotely from the processor 101. The memory 102 provides storage space that stores an operating system of the electronic device, which may include, but is not limited to: a Windows system (an operating system), linux (an operating system), android (Android, a mobile operating system) system, IOS (a mobile operating system) system, and the like, which are not limited by the present disclosure; also, the memory space stores one or more instructions, which may be one or more computer programs (including program code), suitable for being loaded and executed by the processor 101. In this embodiment, the processor 101 loads and executes one or more instructions stored in the memory 102 to implement the depth image-based human spine fitting method according to the above embodiment.
The disclosed embodiments also provide a computer readable storage medium having at least one instruction or at least one program stored thereon, which when loaded by the processor 101, performs the method for fitting a spine of a human body based on depth images as described above. The computer-readable storage medium carries one or more programs which, when executed, implement a method according to an embodiment of the disclosure.
According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
In the description of the present disclosure, it is to be understood that the directions or positional relationships indicated by the directional terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal" and "top, bottom", etc., are generally based on the directions or positional relationships shown in the drawings for the convenience of description and simplicity of description, and in the case of not being described to the contrary, these directional terms are not intended to indicate and imply that the device or element so referred to must have a particular orientation or be constructed and operated in a particular orientation, and therefore, should not be considered as limiting the scope of the present disclosure.
Various other modifications and changes may occur to those skilled in the art based on the foregoing teachings and concepts, and all such modifications and changes are intended to fall within the scope of the appended claims.
Claims (4)
1. A human body spine fitting method based on a depth image is characterized by comprising the following steps:
s01, acquiring a depth image of the back of a human body;
s02, obtaining depth data of the obtained depth image;
s03, processing the depth data, identifying a human body contour in the depth image and labeling bony mark points; selecting two bony mark points at two ends of a spine part, and intercepting depth data between the two selected bony mark points as back data;
s04, defining a horizontal plane as an x-z plane, a coronal plane as a y-x plane, a sagittal plane as a y-z plane, the left side to the right side of the human body as the positive direction of an x axis, the feet as the positive direction of a y axis towards the head, and the back as the positive direction of a z axis towards the abdomen;
traversing the back data, obtaining all x values corresponding to each y value independently, recording as an x value set corresponding to the y value, calculating the average value and variance of each x value set, carrying out numerical judgment on the obtained variance, if the obtained variance is more than 5, taking the median of the x value set as the x value corresponding to the y value, otherwise, taking the average of the x value set as the x value corresponding to the y value, and forming a first discrete set according to each y value and the corresponding x value thereof;
traversing the back data, acquiring all z values corresponding to all y values, recording the z values as z value sets corresponding to all y values, calculating the average value and variance of each z value set, carrying out numerical judgment on the obtained variance, taking the median of the z value set as the z value corresponding to the y value if the obtained variance is more than 5, otherwise, taking the average of the z value set as the z value corresponding to the y value, and forming a second discrete set according to all y values and the z values corresponding to the y values;
s05, smoothing the first discrete set and the second discrete set and eliminating noise points to respectively obtain a first connecting line for representing the numerical value distribution trend of the first discrete set and a second connecting line for representing the numerical value distribution trend of the second discrete set;
s06, processing the first connecting line and the second connecting line through a sliding window algorithm, analyzing the numerical value change trend of each sampling point in a window, and judging whether an inflection point exists in the window, wherein the method specifically comprises the following steps:
setting the number of sampling points in the window asWhen in front of the windowEach sampling point has the same variation trend, and thenOne sampling point is another variation trend, and the most value of the first line/the second line in the window appears at the firstA sampling point orA sampling point orA sampling point and the secondWhen sampling points are arranged among the sampling points, judging that an inflection point exists in a section of the first connecting line/the second connecting line in the window; wherein, the first and the second end of the pipe are connected with each other,;
performing segment-by-segment analysis on the first connecting line and the second connecting line through a sliding window algorithm, and performing accumulation counting on the number of inflection points to obtain the total number of the first inflection pointsAnd a second total number of inflection points;
S07, combining the first discrete set and the total number of the first inflection pointsSubstituting the following formula to calculate the plane function coefficient of the first plane function:
according to the plane function coefficient of the obtained first plane function, obtaining the first plane function as:
constructing a first spine fit curve about a coronal plane based on the first planar function;
combining the second discrete set and the second total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the second plane function:
obtaining a second plane function according to the plane function coefficient of the obtained second plane function, wherein the second plane function is obtained by:
constructing a second spine-fitting curve about the sagittal plane based on the second plane function.
2. A depth image based human spine fitting system, comprising:
the image acquisition module is used for acquiring a depth image of the back of a human body;
a depth data acquisition module for acquiring depth data of the obtained depth image;
the intercepting module is used for processing the depth data, identifying a human body contour in the depth image and marking bony mark points; selecting two bony mark points at two ends of a spine part, and intercepting depth data between the two selected bony mark points as back data;
the discrete set calculation module is used for defining that the horizontal plane is an x-z plane, the coronal plane is a y-x plane, the sagittal plane is a y-z plane, the left side to the right side of the human body is the positive direction of an x axis, the feet are the positive directions of a y axis towards the head, and the back is the positive direction of a z axis towards the abdomen;
traversing the back data, acquiring all x values corresponding to each y value independently, recording as an x value set corresponding to the y value, calculating the average value and variance of each x value set, carrying out numerical judgment on the obtained variance, taking the median of the x value set as the x value corresponding to the y value if the obtained variance is more than 5, otherwise, taking the average of the x value set as the x value corresponding to the y value, and forming a first discrete set according to each y value and the corresponding x value thereof;
traversing the back data, acquiring all z values corresponding to all y values, recording as z value sets corresponding to all y values, calculating the average value and variance of each z value set, carrying out numerical judgment on the obtained variance, taking the median of the z value set as the z value corresponding to the y value if the obtained variance is more than 5, otherwise taking the average of the z value set as the z value corresponding to the y value, and forming a second discrete set according to all the y values and the corresponding z values thereof;
the connecting line construction module is used for performing smoothing processing and noise point elimination on the first discrete set and the second discrete set, and respectively obtaining a first connecting line for representing the numerical value distribution trend of the first discrete set and a second connecting line for representing the numerical value distribution trend of the second discrete set;
the inflection point calculation module is used for processing the first connecting line and the second connecting line through a sliding window algorithm, analyzing the numerical value variation trend of each sampling point in a window and judging whether an inflection point exists in the window, and specifically comprises the following steps:
setting the number of sampling points in the window asWhen the front in the windowEach sampling point has the same variation trend, and thenOne sampling point is another variation trend, and the most value of the first connection line/the second connection line in the window appears at the secondA sampling point or the secondA sampling point or the secondA sampling point and the secondWhen sampling points are arranged among the sampling points, judging that an inflection point exists in a section of the first connecting line/the second connecting line in the window; wherein the content of the first and second substances,;
performing segment-by-segment analysis on the first connecting line and the second connecting line through a sliding window algorithm, and performing accumulated counting on the number of inflection points to obtain the total number of the first inflection pointsAnd a second total number of inflection points;
A fitting curve construction module to combine the first discrete set and the first total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the first plane function:
obtaining a first plane function according to the plane function coefficient of the obtained first plane function, wherein the first plane function is obtained by:
constructing a first spine fit curve about a coronal plane based on the first planar function;
combining the second discrete set and the second total number of inflection pointsSubstituting the following formula to calculate the plane function coefficient of the second plane function:
obtaining a second plane function according to the plane function coefficient of the obtained second plane function, wherein the second plane function is obtained by:
constructing a second spine fit curve about the sagittal plane based on the second planar function.
3. A computer device comprising a processor and a memory in signal connection, wherein the memory has stored therein at least one instruction or at least one program which, when loaded by the processor, performs the depth image based human spine fitting method of claim 1.
4. A computer readable storage medium having at least one instruction or at least one program stored thereon, wherein the at least one instruction or the at least one program when loaded by a processor performs the method for depth image based spine fitting according to claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211177644.9A CN115272588B (en) | 2022-09-27 | 2022-09-27 | Human body spine fitting method and system based on depth image and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211177644.9A CN115272588B (en) | 2022-09-27 | 2022-09-27 | Human body spine fitting method and system based on depth image and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115272588A CN115272588A (en) | 2022-11-01 |
CN115272588B true CN115272588B (en) | 2022-12-30 |
Family
ID=83756056
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211177644.9A Active CN115272588B (en) | 2022-09-27 | 2022-09-27 | Human body spine fitting method and system based on depth image and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115272588B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114081471A (en) * | 2021-11-11 | 2022-02-25 | 宜宾显微智能科技有限公司 | Scoliosis cobb angle measurement method based on three-dimensional image and multi-layer sensing |
CN114299015A (en) * | 2021-12-28 | 2022-04-08 | 上海联影智融医疗科技有限公司 | Method and device for determining scoliosis angle |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AT509233B1 (en) * | 2010-03-04 | 2011-07-15 | Univ Wien Med | METHOD AND DEVICE FOR PROCESSING CT IMAGE DATA OF A BONE-CONTAINING BODY RANGE OF A PATIENT |
CN104008571B (en) * | 2014-06-12 | 2017-01-18 | 深圳奥比中光科技有限公司 | Human body model obtaining method and network virtual fitting system based on depth camera |
CN108764089B (en) * | 2018-05-18 | 2021-04-13 | 四川效率未来科技有限公司 | Human back spine midline recognition method based on depth camera |
CN109965910B (en) * | 2019-04-12 | 2021-07-02 | 东南大学 | Sagittal plane projection imaging method based on three-dimensional ultrasonic spine body data |
CN115100139A (en) * | 2022-06-21 | 2022-09-23 | 上海工程技术大学 | Scoliosis detection method based on deep learning |
-
2022
- 2022-09-27 CN CN202211177644.9A patent/CN115272588B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114081471A (en) * | 2021-11-11 | 2022-02-25 | 宜宾显微智能科技有限公司 | Scoliosis cobb angle measurement method based on three-dimensional image and multi-layer sensing |
CN114299015A (en) * | 2021-12-28 | 2022-04-08 | 上海联影智融医疗科技有限公司 | Method and device for determining scoliosis angle |
Also Published As
Publication number | Publication date |
---|---|
CN115272588A (en) | 2022-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9135498B2 (en) | Integration of intra-oral imagery and volumetric imagery | |
US9402565B2 (en) | Method and system for analyzing craniofacial complex images | |
JP5186620B2 (en) | Brain atrophy determination device, brain atrophy determination method, and brain atrophy determination program | |
CN111539944B (en) | Method, device, electronic equipment and storage medium for acquiring statistical attribute of lung focus | |
US9710907B2 (en) | Diagnosis support system using panoramic radiograph and diagnosis support program using panoramic radiograph | |
JP5601378B2 (en) | Medical image processing device | |
US9060717B2 (en) | Detection and measurement of tissue images | |
CN111091562B (en) | Method and system for measuring size of digestive tract lesion | |
KR101090375B1 (en) | Ct image auto analysis method, recordable medium and apparatus for automatically calculating quantitative assessment index of chest-wall deformity based on automized initialization | |
Fagertun et al. | 3D facial landmarks: Inter-operator variability of manual annotation | |
JP4717585B2 (en) | Medical image determination apparatus, medical image determination method and program thereof | |
JP2013500089A (en) | Three-dimensional (3D) ultrasound imaging system for scoliosis evaluation | |
TW202046241A (en) | Method and device for image processing and electronic device thereof | |
JP4022587B2 (en) | Diagnosis support method and apparatus for brain disease | |
CN113870098A (en) | Automatic Cobb angle measurement method based on spinal layered reconstruction | |
KR102097648B1 (en) | Method of automatically generating a curve corresponding to an dental arch shape on dental ct slice automatically selected from three dimensional dental ct image | |
EP3047455A1 (en) | Method and system for spine position detection | |
CN106413568A (en) | Image processing apparatus, control method for image processing apparatus, and storage medium | |
CN115272588B (en) | Human body spine fitting method and system based on depth image and electronic equipment | |
US20150023471A1 (en) | Stereo x-ray tube based suppression of outside body high contrast objects | |
CN111080769A (en) | Three-dimensional deformation model generation method and system based on nuclear magnetic resonance data and electronic equipment | |
CN115311239A (en) | Virtual scale construction method, system and measurement method for video image measurement | |
CN114266848A (en) | Medical image three-dimensional reconstruction method and device | |
CN103052970B (en) | Object support is removed from imaging data | |
CN111000580A (en) | Intervertebral disc scanning method and device, console equipment and CT system |
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 |