WO2024179011A1 - Pelvis assessment method based on three-dimensional human body model - Google Patents
Pelvis assessment method based on three-dimensional human body model Download PDFInfo
- Publication number
- WO2024179011A1 WO2024179011A1 PCT/CN2023/127750 CN2023127750W WO2024179011A1 WO 2024179011 A1 WO2024179011 A1 WO 2024179011A1 CN 2023127750 W CN2023127750 W CN 2023127750W WO 2024179011 A1 WO2024179011 A1 WO 2024179011A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- human body
- dimensional
- image
- pixel
- point
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Definitions
- the present invention relates to the field of intelligent medical health technology, and in particular to a pelvic assessment method based on a three-dimensional human body model.
- the pelvis plays an extremely important role in the physiological structure, including protecting the organs in the pelvic cavity, cooperating with muscles to provide body stability, and providing space for the fetus during the birth process. Its state is related to the normal operation of various physiological functions of the human body.
- the pelvic condition of postpartum women is of particular concern because pregnancy and childbirth processes have a significant impact on the pelvic structure.
- Problems such as pelvic anteroposterior tilt, pelvic lateral tilt, and pelvic rotation are particularly common in postpartum women and may cause a series of physical problems, such as low back pain, hip pain, and even urinary incontinence. Accurately assessing and tracking the status of the pelvis is essential for health.
- an object of the embodiments of the present invention is to provide a pelvic assessment method based on a three-dimensional human body model to solve the problems in the above-mentioned background technology.
- the present invention provides the following technical solutions:
- a pelvic assessment method based on a three-dimensional human body model comprises the following steps:
- Step S1 obtaining a three-dimensional human body network model through a three-dimensional human body scanning device
- Step S2 using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the back of the three-dimensional human network model is rendered into a two-dimensional human back image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A: performing a connected domain analysis on the A channel of the rendered human image, finding the vertex pixel position of the gap area between the legs of the human body, and drawing a vertical line at the vertex of the gap area between the legs as the center line of the human body trunk;
- Step S3 Use OpenPose to find the pixel positions of the left and right hips and the left and right knees in the back image of the human body, connect these four points to form a quadrilateral area, connect the two diagonals of the quadrilateral, draw a horizontal line through the intersection of the diagonals to divide the quadrilateral into two, and use the upper half area as the hip area in the back image of the human body, convert the image into a grayscale image by calling the cvtColor function of the image processing library OpenCV, and find all pixel points in the hip area with pixel values less than 80 in the grayscale image;
- Step S4 taking the lowest points of the left and right hip line points in the human body image as the left and right hip line landmarks respectively, mapping the two-dimensional pixel coordinates of the left and right hip line landmarks into three-dimensional space coordinates through a ray casting algorithm, and calculating the relative height difference (i.e., the difference in Y coordinates) of the left and right hip line landmarks in three-dimensional space, so as to evaluate the degree of pelvic tilt;
- Step S5 using a ray casting algorithm, the two-dimensional pixel coordinates of the vertices of the gap between the legs and the pixel points of the left hip are respectively mapped into three-dimensional space coordinates, wherein the three-dimensional coordinates of the vertices of the gap between the legs are (x 1 , y 1 , z 1 ), and the three-dimensional coordinates of the left hip are (x 2 , y 2 , z 2 );
- Step S6 traverse all vertices of the three-dimensional human body model and calculate the normal vector ( xn , yn , zn ) at each vertex, find the vertex whose Y coordinate is between y1 and y2 and whose normal vector coordinate zn ⁇ 0, and classify the points located on the left side of the vertex in the leg gap area into the left hip point set according to the X coordinate value, and classify the points located on the right side of the vertex in the leg gap area into the right hip point set, find the points with the smallest Z coordinates in the left and right hip point sets, that is, the last points of the buttocks, as the left and right hip peak points, calculate the difference in the Z coordinates of the left and right hip peak points, and use this to evaluate the degree of pelvic rotation;
- Step S7 using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the front of the three-dimensional human network model is rendered into a two-dimensional human front image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A, and a connected domain analysis is performed on the A channel of the rendered human front image to find the vertex pixel position of the gap area between the legs of the human body;
- Step S8 using OpenPose to identify two pixel points corresponding to the left and right hips in the frontal image of the human body, and mapping the two-dimensional pixel point coordinates corresponding to the pubic symphysis and the left and right hip joints into three-dimensional space coordinates through a ray casting algorithm;
- Step S9 In three-dimensional space, calculate the midpoint of the line connecting the left and right hips, and calculate the angle between the line connecting the midpoint and the pubic symphysis and the coronal plane of the human body (ie, the XY plane), and use the angle as the angle for evaluating the anteroposterior tilt of the pelvis.
- the step S2 of performing connected domain analysis on the rendered human body image A channel comprises the following steps:
- Step S2.1 In channel A of the back image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the left foot bottom point, and traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the right foot bottom point;
- Step S2.2 Take the topmost point of the left and right soles in the A channel of the back image of the human body as the reference pixel point, draw a horizontal straight line through the reference pixel point, set all pixel values below the horizontal line to 255, so that the gap between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the gap between the legs;
- Step S2.3 Traverse the pixels in the gap area between the legs and find the top pixel in the area as the vertex of the gap area between the legs.
- the virtual camera in step S2 is located 1.2m behind the human body, half the height of the human body from the ground, with a line of sight facing the center of the three-dimensional human body, a vertical field of view angle of 100°, and a resolution of the camera of 360 ⁇ 640.
- the grayscale image in step S3 uses the points located to the left of the torso centerline and more than 5 pixels laterally away from the centerline as the left hip line point set, and uses the points located to the right of the torso centerline and more than 5 pixels laterally away from the centerline as the right hip line point set.
- the step S7 of performing connected domain analysis on the rendered human body image A channel comprises the following steps:
- Step S7.1 In channel A of the front image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the right foot bottom point, traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the left foot bottom point;
- Step S7.2 Take the topmost point among the left and right soles in the A channel of the human front image as the reference pixel, draw a horizontal straight line through the reference pixel, set all pixel values below the horizontal line to 255, so that the area between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the area between the legs.
- the virtual camera in step S7 is located 1.2m in front of the human body, half the height of the human body from the ground, with a line of sight facing the center of the three-dimensional human body, a vertical field of view angle of 100°, and a resolution of the camera of 360 ⁇ 640.
- the specific calculation process of the angle between the line connecting the midpoint and the pubic symphysis in step S9 and the human coronal plane is:
- the angle between the line connecting the left and right hip joints and the coronal plane is: .
- the present invention can support the assessment of pelvic lateral tilt, pelvic rotation and pelvic anteroposterior tilt, and has the advantages of being non-invasive, radiation-free, easy to operate, and accurate in measurement. It can perform measurements multiple times in a short period of time, thereby facilitating regular tracking and assessment of pelvic health status, and can be better applied in clinical and daily health management.
- FIG1 is a flowchart of pelvic assessment based on a three-dimensional human body model according to an embodiment of the present invention.
- FIG. 2 is a schematic diagram of a three-dimensional human body model and a three-dimensional space coordinate system according to an embodiment of the invention.
- FIG3 is a schematic diagram of the structure of a human back image, an image coordinate system, and key landmark points in an embodiment of the invention.
- FIG. 4 is a schematic structural diagram of a frontal image of a human body, an image coordinate system, and key landmark points in an embodiment of the invention.
- the pelvic assessment method based on a three-dimensional human body model is characterized by comprising the following steps:
- Step S1 obtaining a three-dimensional human body network model through a three-dimensional human body scanning device
- Step S2 using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the back of the three-dimensional human network model is rendered into a two-dimensional human back image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A: performing a connected domain analysis on the A channel of the rendered human image, finding the vertex pixel position of the gap area between the legs of the human body, and drawing a vertical line at the vertex of the gap area between the legs as the center line of the human body trunk;
- Step S3 Use OpenPose to find the pixel positions of the left and right hips and the left and right knees in the back image of the human body, connect these four points to form a quadrilateral area, connect the two diagonals of the quadrilateral, draw a horizontal line through the intersection of the diagonals to divide the quadrilateral into two, and use the upper half area as the hip area in the back image of the human body, convert the image into a grayscale image by calling the cvtColor function of the image processing library OpenCV, and find all pixel points in the hip area with pixel values less than 80 in the grayscale image;
- Step S4 taking the lowest points of the left and right hip line points in the human body image as the left and right hip line landmarks respectively, mapping the two-dimensional pixel coordinates of the left and right hip line landmarks into three-dimensional space coordinates through a ray casting algorithm, and calculating the relative height difference (i.e., the difference in Y coordinates) of the left and right hip line landmarks in three-dimensional space, so as to evaluate the degree of pelvic tilt;
- Step S5 using a ray casting algorithm, the two-dimensional pixel coordinates of the vertices of the gap between the legs and the pixel points of the left hip are respectively mapped into three-dimensional space coordinates, wherein the three-dimensional coordinates of the vertices of the gap between the legs are (x 1 , y 1 , z 1 ), and the three-dimensional coordinates of the left hip are (x 2 , y 2 , z 2 );
- Step S6 traverse all vertices of the three-dimensional human body model and calculate the normal vector ( xn , yn , zn ) at each vertex, find the vertex whose Y coordinate is between y1 and y2 and whose normal vector coordinate zn ⁇ 0, and classify the points located on the left side of the vertex in the leg gap area into the left hip point set according to the X coordinate value, and classify the points located on the right side of the vertex in the leg gap area into the right hip point set, find the points with the smallest Z coordinates in the left and right hip point sets, that is, the last points of the buttocks, as the left and right hip peak points, calculate the difference in the Z coordinates of the left and right hip peak points, and use this to evaluate the degree of pelvic rotation;
- Step S7 using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the front of the three-dimensional human network model is rendered into a two-dimensional human front image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A, and a connected domain analysis is performed on the A channel of the rendered human front image to find the vertex pixel position of the gap area between the legs of the human body;
- Step S8 using OpenPose to identify two pixel points corresponding to the left and right hips in the frontal image of the human body, and mapping the two-dimensional pixel point coordinates corresponding to the pubic symphysis and the left and right hip joints into three-dimensional space coordinates through a ray casting algorithm;
- Step S9 In three-dimensional space, calculate the midpoint of the line connecting the left and right hips, and calculate the angle between the line connecting the midpoint and the pubic symphysis and the coronal plane of the human body (ie, the XY plane).
- This angle is used to assess the anteroposterior tilt of the pelvis.
- the three-dimensional human body mesh model obtained in step S1 is composed of triangular meshes, each of which is composed of three vertices, each of which has three coordinate values, namely X, Y, and Z coordinate values.
- the file format of the three-dimensional human body mesh model is obj format, and the file contains the vertex coordinate values of the triangular meshes and the connection relationship of the triangular meshes;
- the virtual camera in step S2 is located 1.2 m behind the human body, with a height from the ground equal to half the height of the human body, with a line of sight facing the center of the three-dimensional human body, a vertical field of view of 100°, and a resolution of 360 ⁇ 640;
- the grayscale image in step S3 takes the points located to the left of the center line of the torso and more than 5 pixels away from the center line in the horizontal direction as the left hip line point set, and takes the points located to the right of the center line of the torso and more than 5 pixels away from the center line in the horizontal direction as the right hip line point set;
- the virtual camera in step S7 is located 1.2 m in front of the human body, with a height from the ground equal to half the height of the human body, with a line of sight facing the center of the three-dimensional human body, a vertical field of view of 100°, and a resolution of 360 ⁇ 640;
- the angle between the line connecting the left and right hip joints and the coronal plane is: .
- the step S2 of performing connected domain analysis on the rendered human body image A channel comprises the following steps:
- Step S2.1 In channel A of the back image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the left foot bottom point, and traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the right foot bottom point;
- Step S2.2 Take the topmost point of the left and right soles in the A channel of the back image of the human body as the reference pixel point, draw a horizontal straight line through the reference pixel point, set all pixel values below the horizontal line to 255, so that the gap between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the gap between the legs;
- Step S2.3 Traverse the pixels in the gap area between the legs and find the top pixel in the area as the vertex of the gap area between the legs.
- the step S7 of performing connected domain analysis on the A channel of the rendered human body image comprises the following steps:
- Step S7.1 In channel A of the front image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the right foot bottom point, traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the left foot bottom point;
- Step S7.2 Take the topmost point among the left and right soles in the A channel of the human front image as the reference pixel, draw a horizontal straight line through the reference pixel, set all pixel values below the horizontal line to 255, so that the area between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the area between the legs.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
Description
本发明涉及智能医疗健康技术领域，具体是涉及一种基于三维人体模型的骨盆评估方法。The present invention relates to the field of intelligent medical health technology, and in particular to a pelvic assessment method based on a three-dimensional human body model.
骨盆在生理结构中承担着极其重要的角色，包括保护盆腔内的器官，配合肌肉提供身体稳定性，以及在生育过程中为胎儿提供空间，它的状态关系到人体各种生理功能的正常运行。在医学领域，产后女性的骨盆状况尤其受关注，因为妊娠和分娩过程会对骨盆结构产生显著影响。骨盆前后倾、骨盆侧倾、骨盆旋移等问题在产后女性中尤为常见，且可能引发一系列的身体问题，如腰痛、髋痛甚至尿失禁等。准确地评估和跟踪骨盆状态，对于健康至关重要。The pelvis plays an extremely important role in the physiological structure, including protecting the organs in the pelvic cavity, cooperating with muscles to provide body stability, and providing space for the fetus during the birth process. Its state is related to the normal operation of various physiological functions of the human body. In the medical field, the pelvic condition of postpartum women is of particular concern because pregnancy and childbirth processes have a significant impact on the pelvic structure. Problems such as pelvic anteroposterior tilt, pelvic lateral tilt, and pelvic rotation are particularly common in postpartum women and may cause a series of physical problems, such as low back pain, hip pain, and even urinary incontinence. Accurately assessing and tracking the status of the pelvis is essential for health.
传统的骨盆评估方法主要分为两类：一类是依赖人工目视评估，虽然操作简单，但是其评估结果受到医生主观经验因素的影响较大，无法满足临床精确度的需求。另一类则是利用X光、CT等放射性检测技术对骨盆进行评估。这类方法的评估结果较为精确，但是会对人体产生辐射，并且检测成本较高，不适合频繁进行检测，不方便对患者的骨盆健康状况进行持续跟踪和定期评估。Traditional pelvic assessment methods are mainly divided into two categories: one is to rely on manual visual assessment. Although the operation is simple, its assessment results are greatly affected by the doctor's subjective experience and cannot meet the needs of clinical accuracy. The other is to use radioactive detection technologies such as X-rays and CT to evaluate the pelvis. The assessment results of this type of method are more accurate, but it will generate radiation to the human body, and the detection cost is high. It is not suitable for frequent testing and is not convenient for continuous tracking and regular evaluation of the patient's pelvic health status.
因此，需要提供一种基于三维人体模型的骨盆评估方法，旨在解决上述问题。Therefore, it is necessary to provide a pelvic assessment method based on a three-dimensional human body model to solve the above problems.
针对现有技术存在的不足，本发明实施例的目的在于提供一种基于三维人体模型的骨盆评估方法，以解决上述背景技术中的问题。In view of the deficiencies in the prior art, an object of the embodiments of the present invention is to provide a pelvic assessment method based on a three-dimensional human body model to solve the problems in the above-mentioned background technology.
为实现上述目的，本发明提供如下技术方案：To achieve the above object, the present invention provides the following technical solutions:
一种基于三维人体模型的骨盆评估方法，包括以下步骤：A pelvic assessment method based on a three-dimensional human body model comprises the following steps:
步骤S1：通过三维人体扫描设备获取三维人体网络模型；Step S1: obtaining a three-dimensional human body network model through a three-dimensional human body scanning device;
步骤S2：使用计算机图形库OpenGL设定一个虚拟摄像机，在该虚拟摄像机的视角下，通过OpenGL将三维人体网络模型的背面渲染成一张二维人体背面图像，所述图像为png格式，包含R、G、B、A四个通道：对渲染的人体图像A通道进行连通域分析，找到人体双腿间隙区域的顶点像素位置，在双腿间隙区域顶点作一条用于作为人体躯干中心线的垂直线；Step S2: using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the back of the three-dimensional human network model is rendered into a two-dimensional human back image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A: performing a connected domain analysis on the A channel of the rendered human image, finding the vertex pixel position of the gap area between the legs of the human body, and drawing a vertical line at the vertex of the gap area between the legs as the center line of the human body trunk;
步骤S3：用OpenPose找到人体背面图像中左、右髋以及左、右膝的像素位置，将这四个点相连接组成一个四边形区域，连接该四边形的两条对角线，过对角线的交点作一条水平线将四边形一分为二，并将上半部分区域作为人体背面图像中的臀部区域，通过调用图像处理库OpenCV的cvtColor函数，将图像转成灰度图，在灰度图上，找出臀部区域内所有像素值低于80的像素点；Step S3: Use OpenPose to find the pixel positions of the left and right hips and the left and right knees in the back image of the human body, connect these four points to form a quadrilateral area, connect the two diagonals of the quadrilateral, draw a horizontal line through the intersection of the diagonals to divide the quadrilateral into two, and use the upper half area as the hip area in the back image of the human body, convert the image into a grayscale image by calling the cvtColor function of the image processing library OpenCV, and find all pixel points in the hip area with pixel values less than 80 in the grayscale image;
步骤S4：分别取人体图像中左、右臀线点集中的最低点作为左、右臀线标志点，通过光线投射算法（Ray Casting）将左、右臀线标志点的二维像素坐标映射为三维空间坐标，计算左、右臀线标志点在三维空间的相对高度差（即Y坐标之差），以此来评估骨盆侧倾的程度；Step S4: taking the lowest points of the left and right hip line points in the human body image as the left and right hip line landmarks respectively, mapping the two-dimensional pixel coordinates of the left and right hip line landmarks into three-dimensional space coordinates through a ray casting algorithm, and calculating the relative height difference (i.e., the difference in Y coordinates) of the left and right hip line landmarks in three-dimensional space, so as to evaluate the degree of pelvic tilt;
步骤S5：通过光线投射算法（Ray Casting）将双腿间隙区域顶点和左髋像素点的二维像素坐标分别映射为三维空间坐标，其中双腿间隙区域顶点的三维坐标为(x 1,y 1,z 1)，左髋的三维坐标为(x 2,y 2,z 2)； Step S5: using a ray casting algorithm, the two-dimensional pixel coordinates of the vertices of the gap between the legs and the pixel points of the left hip are respectively mapped into three-dimensional space coordinates, wherein the three-dimensional coordinates of the vertices of the gap between the legs are (x 1 , y 1 , z 1 ), and the three-dimensional coordinates of the left hip are (x 2 , y 2 , z 2 );
步骤S6：遍历三维人体模型的所有顶点，并计算每个顶点处的法线向量(x n,y n,z n)，找到Y坐标位于y 1和y 2之间且法线向量坐标z n < 0的顶点，并根据X坐标值，将各顶点中位于双腿间隙区域顶点左侧的点归类于左臀点集，将位于双腿间隙区域顶点右侧的点归类为右臀点集，分别找到左、右臀点集中Z坐标最小的点，即臀部最后的点，作为左、右臀峰点，计算左、右臀峰点的Z坐标之差，以此来评估骨盆旋移的程度； Step S6: traverse all vertices of the three-dimensional human body model and calculate the normal vector ( xn , yn , zn ) at each vertex, find the vertex whose Y coordinate is between y1 and y2 and whose normal vector coordinate zn <0, and classify the points located on the left side of the vertex in the leg gap area into the left hip point set according to the X coordinate value, and classify the points located on the right side of the vertex in the leg gap area into the right hip point set, find the points with the smallest Z coordinates in the left and right hip point sets, that is, the last points of the buttocks, as the left and right hip peak points, calculate the difference in the Z coordinates of the left and right hip peak points, and use this to evaluate the degree of pelvic rotation;
步骤S7：使用计算机图形库OpenGL设定一个虚拟摄像机，在该虚拟摄像机的视角下，通过OpenGL将三维人体网络模型的正面渲染成一张二维人体正面图像，所述图像为png格式，包含R、G、B、A四个通道，对渲染的人体正面图像A通道进行连通域分析，找到人体双腿间隙区域的顶点像素位置；Step S7: using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the front of the three-dimensional human network model is rendered into a two-dimensional human front image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A, and a connected domain analysis is performed on the A channel of the rendered human front image to find the vertex pixel position of the gap area between the legs of the human body;
步骤S8：用OpenPose识别人体正面图像中分别对应左、右髋的两个像素点，通过光线投射算法（Ray Casting）分别将找到的对应耻骨联合处以及左、右髋关节的二维像素点坐标映射为三维空间坐标；Step S8: using OpenPose to identify two pixel points corresponding to the left and right hips in the frontal image of the human body, and mapping the two-dimensional pixel point coordinates corresponding to the pubic symphysis and the left and right hip joints into three-dimensional space coordinates through a ray casting algorithm;
步骤S9：在三维空间中，计算左、右髋连线的中点，并计算中点和耻骨联合处的连线与人体冠状面（即XY平面）的夹角，将该夹角作为评估骨盆前后倾的角度。Step S9: In three-dimensional space, calculate the midpoint of the line connecting the left and right hips, and calculate the angle between the line connecting the midpoint and the pubic symphysis and the coronal plane of the human body (ie, the XY plane), and use the angle as the angle for evaluating the anteroposterior tilt of the pelvis.
作为本发明进一步的方案，所述步骤S2的对渲染的人体图像A通道进行连通域分析包括以下步骤：As a further solution of the present invention, the step S2 of performing connected domain analysis on the rendered human body image A channel comprises the following steps:
步骤S2.1：在人体背面图像A通道中，遍历图像左半边值为255的像素，找到其中最下方的像素点作为左脚底点，遍历图像右半边值为255的像素，找到其中最下方的像素点作为右脚底点；Step S2.1: In channel A of the back image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the left foot bottom point, and traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the right foot bottom point;
步骤S2.2：在人体背面图像A通道中取左、右脚底点中位置最上方的点作为参考像素点，过该参考像素点画一条水平直线，将位于该水平线下方的所有像素值置为255，使得人体的双腿间隙区域构成了一个像素值为0的封闭的连通域，取水平直线上位于左、右脚底点之间任意位置的一个像素作为样本点，通过调用OpenCV的connectedComponentsWithStats函数对A通道进行连通域分析，定位出包含该样本点的连通域，即为双腿间隙区域；Step S2.2: Take the topmost point of the left and right soles in the A channel of the back image of the human body as the reference pixel point, draw a horizontal straight line through the reference pixel point, set all pixel values below the horizontal line to 255, so that the gap between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the gap between the legs;
步骤S2.3：遍历双腿间隙区域内的像素，找到区域中位置最上的像素点作为双腿间隙区域顶点。Step S2.3: Traverse the pixels in the gap area between the legs and find the top pixel in the area as the vertex of the gap area between the legs.
作为本发明进一步的方案，所述步骤S2中的虚拟摄像机位于人体正后方1.2m的位置，离地高度为人体高度的一半，视线正对三维人体的中心位置，垂直视场角大小为100°，摄像机的分辨率为360×640。As a further solution of the present invention, the virtual camera in step S2 is located 1.2m behind the human body, half the height of the human body from the ground, with a line of sight facing the center of the three-dimensional human body, a vertical field of view angle of 100°, and a resolution of the camera of 360×640.
作为本发明进一步的方案，所述步骤S3中的灰度图将位于躯干中心线左边且横向距离中心线超过5个像素的点作为左臀线点集合，将位于躯干中心线右边且横向距离中心线超过5个像素的点作为右臀线点集合。As a further solution of the present invention, the grayscale image in step S3 uses the points located to the left of the torso centerline and more than 5 pixels laterally away from the centerline as the left hip line point set, and uses the points located to the right of the torso centerline and more than 5 pixels laterally away from the centerline as the right hip line point set.
作为本发明进一步的方案，所述步骤S7对渲染的人体图像A通道进行连通域分析包括以下步骤：As a further solution of the present invention, the step S7 of performing connected domain analysis on the rendered human body image A channel comprises the following steps:
步骤S7.1：在人体正面图像A通道中，遍历图像左半边值为255的像素，找到其中最下方的像素点作为右脚底点，遍历图像右半边值为255的像素，找到其中最下方的像素点作为左脚底点；Step S7.1: In channel A of the front image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the right foot bottom point, traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the left foot bottom point;
步骤S7.2：在人体正面图像A通道中取左、右脚底点中位置最上方的点作为参考像素点，过该参考像素点做一条水平直线，将位于该水平线下方的所有像素值置为255，使得人体的双腿间隙区域构成了一个像素值为0的封闭的连通域，取水平直线上位于左、右脚底点之间任意位置的一个像素作为样本点，通过调用OpenCV的connectedComponentsWithStats函数对A通道进行连通域分析，定位出包含该样本点的连通域，即为双腿间隙区域。Step S7.2: Take the topmost point among the left and right soles in the A channel of the human front image as the reference pixel, draw a horizontal straight line through the reference pixel, set all pixel values below the horizontal line to 255, so that the area between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the area between the legs.
作为本发明进一步的方案，所述步骤S7中的虚拟摄像机位于人体正前方1.2m的位置，离地高度为人体高度的一半，视线正对三维人体的中心位置，垂直视场角大小为100°，摄像机的分辨率为360×640。As a further solution of the present invention, the virtual camera in step S7 is located 1.2m in front of the human body, half the height of the human body from the ground, with a line of sight facing the center of the three-dimensional human body, a vertical field of view angle of 100°, and a resolution of the camera of 360×640.
作为本发明进一步的方案，所述步骤S9中的中点和耻骨联合处的连线与人体冠状面（即XY平面）的夹角的具体计算过程为：As a further solution of the present invention, the specific calculation process of the angle between the line connecting the midpoint and the pubic symphysis in step S9 and the human coronal plane (ie, the XY plane) is:
设左髋关节点的三维坐标为L=(x L,y L,z L)，右髋关节点的三维坐标为R=(x R,y R,z R)，耻骨联合处的三维坐标为P=(x p,y p,z p)，冠状面的单位法向量为N=(0,0,1)，则左、右髋关节的中点坐标为： ， Assume that the three-dimensional coordinates of the left hip joint are L=(x L ,y L ,z L ), the three-dimensional coordinates of the right hip joint are R=(x R ,y R ,z R ), the three-dimensional coordinates of the pubic symphysis are P=(x p ,y p ,z p ), and the unit normal vector of the coronal plane is N=(0,0,1), then the coordinates of the midpoints of the left and right hip joints are: ,
左、右髋关节的连线与冠状面的夹角为： 。 The angle between the line connecting the left and right hip joints and the coronal plane is: .
综上所述，本发明实施例与现有技术相比具有以下有益效果：In summary, compared with the prior art, the embodiments of the present invention have the following beneficial effects:
本发明可以支持骨盆侧倾、骨盆旋移和骨盆前后倾的评估，具有非侵入性、无辐射、操作简便、测量准确等优点，短期内可以多次进行测量，从而方便对骨盆健康状态进行定期追踪和评估，更好地应用于临床和日常健康管理中。The present invention can support the assessment of pelvic lateral tilt, pelvic rotation and pelvic anteroposterior tilt, and has the advantages of being non-invasive, radiation-free, easy to operate, and accurate in measurement. It can perform measurements multiple times in a short period of time, thereby facilitating regular tracking and assessment of pelvic health status, and can be better applied in clinical and daily health management.
为更清楚地阐述本发明的结构特征和功效，下面结合附图与具体实施例来对本发明进行详细说明。In order to more clearly illustrate the structural features and effects of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments.
图1为发明实施例的基于三维人体模型的骨盆评估流程图。FIG1 is a flowchart of pelvic assessment based on a three-dimensional human body model according to an embodiment of the present invention.
图2为发明实施例的三维人体模型和三维空间坐标系示意图。FIG. 2 is a schematic diagram of a three-dimensional human body model and a three-dimensional space coordinate system according to an embodiment of the invention.
图3为发明实施例中人体背面图像、图像坐标系以及关键标志点的结构示意图。FIG3 is a schematic diagram of the structure of a human back image, an image coordinate system, and key landmark points in an embodiment of the invention.
图4为发明实施例中人体正面图像、图像坐标系以及关键标志点的结构示意图。FIG. 4 is a schematic structural diagram of a frontal image of a human body, an image coordinate system, and key landmark points in an embodiment of the invention.
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
以下结合具体实施例对本发明的具体实现进行详细描述。The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.
在本发明的一个实施例中，参见图1，所述一种基于三维人体模型的骨盆评估方法，其特征在于，包括以下步骤：In one embodiment of the present invention, referring to FIG1 , the pelvic assessment method based on a three-dimensional human body model is characterized by comprising the following steps:
步骤S1：通过三维人体扫描设备获取三维人体网络模型；Step S1: obtaining a three-dimensional human body network model through a three-dimensional human body scanning device;
步骤S2：使用计算机图形库OpenGL设定一个虚拟摄像机，在该虚拟摄像机的视角下，通过OpenGL将三维人体网络模型的背面渲染成一张二维人体背面图像，所述图像为png格式，包含R、G、B、A四个通道：对渲染的人体图像A通道进行连通域分析，找到人体双腿间隙区域的顶点像素位置，在双腿间隙区域顶点作一条用于作为人体躯干中心线的垂直线；Step S2: using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the back of the three-dimensional human network model is rendered into a two-dimensional human back image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A: performing a connected domain analysis on the A channel of the rendered human image, finding the vertex pixel position of the gap area between the legs of the human body, and drawing a vertical line at the vertex of the gap area between the legs as the center line of the human body trunk;
步骤S3：用OpenPose找到人体背面图像中左、右髋以及左、右膝的像素位置，将这四个点相连接组成一个四边形区域，连接该四边形的两条对角线，过对角线的交点作一条水平线将四边形一分为二，并将上半部分区域作为人体背面图像中的臀部区域，通过调用图像处理库OpenCV的cvtColor函数，将图像转成灰度图，在灰度图上，找出臀部区域内所有像素值低于80的像素点；Step S3: Use OpenPose to find the pixel positions of the left and right hips and the left and right knees in the back image of the human body, connect these four points to form a quadrilateral area, connect the two diagonals of the quadrilateral, draw a horizontal line through the intersection of the diagonals to divide the quadrilateral into two, and use the upper half area as the hip area in the back image of the human body, convert the image into a grayscale image by calling the cvtColor function of the image processing library OpenCV, and find all pixel points in the hip area with pixel values less than 80 in the grayscale image;
步骤S4：分别取人体图像中左、右臀线点集中的最低点作为左、右臀线标志点，通过光线投射算法（Ray Casting）将左、右臀线标志点的二维像素坐标映射为三维空间坐标，计算左、右臀线标志点在三维空间的相对高度差（即Y坐标之差），以此来评估骨盆侧倾的程度；Step S4: taking the lowest points of the left and right hip line points in the human body image as the left and right hip line landmarks respectively, mapping the two-dimensional pixel coordinates of the left and right hip line landmarks into three-dimensional space coordinates through a ray casting algorithm, and calculating the relative height difference (i.e., the difference in Y coordinates) of the left and right hip line landmarks in three-dimensional space, so as to evaluate the degree of pelvic tilt;
步骤S5：通过光线投射算法（Ray Casting）将双腿间隙区域顶点和左髋像素点的二维像素坐标分别映射为三维空间坐标，其中双腿间隙区域顶点的三维坐标为(x 1,y 1,z 1)，左髋的三维坐标为(x 2,y 2,z 2)； Step S5: using a ray casting algorithm, the two-dimensional pixel coordinates of the vertices of the gap between the legs and the pixel points of the left hip are respectively mapped into three-dimensional space coordinates, wherein the three-dimensional coordinates of the vertices of the gap between the legs are (x 1 , y 1 , z 1 ), and the three-dimensional coordinates of the left hip are (x 2 , y 2 , z 2 );
步骤S6：遍历三维人体模型的所有顶点，并计算每个顶点处的法线向量(x n,y n,z n)，找到Y坐标位于y 1和y 2之间且法线向量坐标z n < 0的顶点，并根据X坐标值，将各顶点中位于双腿间隙区域顶点左侧的点归类于左臀点集，将位于双腿间隙区域顶点右侧的点归类为右臀点集，分别找到左、右臀点集中Z坐标最小的点，即臀部最后的点，作为左、右臀峰点，计算左、右臀峰点的Z坐标之差，以此来评估骨盆旋移的程度； Step S6: traverse all vertices of the three-dimensional human body model and calculate the normal vector ( xn , yn , zn ) at each vertex, find the vertex whose Y coordinate is between y1 and y2 and whose normal vector coordinate zn <0, and classify the points located on the left side of the vertex in the leg gap area into the left hip point set according to the X coordinate value, and classify the points located on the right side of the vertex in the leg gap area into the right hip point set, find the points with the smallest Z coordinates in the left and right hip point sets, that is, the last points of the buttocks, as the left and right hip peak points, calculate the difference in the Z coordinates of the left and right hip peak points, and use this to evaluate the degree of pelvic rotation;
步骤S7：使用计算机图形库OpenGL设定一个虚拟摄像机，在该虚拟摄像机的视角下，通过OpenGL将三维人体网络模型的正面渲染成一张二维人体正面图像，所述图像为png格式，包含R、G、B、A四个通道，对渲染的人体正面图像A通道进行连通域分析，找到人体双腿间隙区域的顶点像素位置；Step S7: using the computer graphics library OpenGL to set a virtual camera, under the perspective of the virtual camera, the front of the three-dimensional human network model is rendered into a two-dimensional human front image through OpenGL, wherein the image is in png format and contains four channels of R, G, B, and A, and a connected domain analysis is performed on the A channel of the rendered human front image to find the vertex pixel position of the gap area between the legs of the human body;
步骤S8：用OpenPose识别人体正面图像中分别对应左、右髋的两个像素点，通过光线投射算法（Ray Casting）分别将找到的对应耻骨联合处以及左、右髋关节的二维像素点坐标映射为三维空间坐标；Step S8: using OpenPose to identify two pixel points corresponding to the left and right hips in the frontal image of the human body, and mapping the two-dimensional pixel point coordinates corresponding to the pubic symphysis and the left and right hip joints into three-dimensional space coordinates through a ray casting algorithm;
步骤S9：在三维空间中，计算左、右髋连线的中点，并计算中点和耻骨联合处的连线与人体冠状面（即XY平面）的夹角，Step S9: In three-dimensional space, calculate the midpoint of the line connecting the left and right hips, and calculate the angle between the line connecting the midpoint and the pubic symphysis and the coronal plane of the human body (ie, the XY plane).
将该夹角作为评估骨盆前后倾的角度。This angle is used to assess the anteroposterior tilt of the pelvis.
在本实施例中，所述步骤S1中获取的三维人体网格模型是由三角形网格构成的，每个三角形网格由三个顶点构成，每个顶点有三个坐标值，分别是X、Y、Z坐标值，三维人体网格模型的文件格式是obj格式，文件中包含了三角形网格的顶点坐标值和三角形网格的连接关系；In this embodiment, the three-dimensional human body mesh model obtained in step S1 is composed of triangular meshes, each of which is composed of three vertices, each of which has three coordinate values, namely X, Y, and Z coordinate values. The file format of the three-dimensional human body mesh model is obj format, and the file contains the vertex coordinate values of the triangular meshes and the connection relationship of the triangular meshes;
所述步骤S2中的虚拟摄像机位于人体正后方1.2m的位置，离地高度为人体高度的一半，视线正对三维人体的中心位置，垂直视场角大小为100°，摄像机的分辨率为360×640；The virtual camera in step S2 is located 1.2 m behind the human body, with a height from the ground equal to half the height of the human body, with a line of sight facing the center of the three-dimensional human body, a vertical field of view of 100°, and a resolution of 360×640;
所述步骤S3中的灰度图将位于躯干中心线左边且横向距离中心线超过5个像素的点作为左臀线点集合，将位于躯干中心线右边且横向距离中心线超过5个像素的点作为右臀线点集合；The grayscale image in step S3 takes the points located to the left of the center line of the torso and more than 5 pixels away from the center line in the horizontal direction as the left hip line point set, and takes the points located to the right of the center line of the torso and more than 5 pixels away from the center line in the horizontal direction as the right hip line point set;
所述步骤S7中的虚拟摄像机位于人体正前方1.2m的位置，离地高度为人体高度的一半，视线正对三维人体的中心位置，垂直视场角大小为100°，摄像机的分辨率为360×640；The virtual camera in step S7 is located 1.2 m in front of the human body, with a height from the ground equal to half the height of the human body, with a line of sight facing the center of the three-dimensional human body, a vertical field of view of 100°, and a resolution of 360×640;
所述步骤S9中的中点和耻骨联合处的连线与人体冠状面（即XY平面）的夹角的具体计算过程为：The specific calculation process of the angle between the line connecting the midpoint and the pubic symphysis in step S9 and the human coronal plane (i.e., XY plane) is as follows:
L=(x L,y L,z L)，右髋关节点的三维坐标为R=(x R,y R,z R)，耻骨联合处的三维坐标为P=(x p,y p,z p)，冠状面的单位法向量为N=(0,0,1)，则左、右髋关节的中点坐标为: ， L=(x L ,y L ,z L ), the three-dimensional coordinates of the right hip joint are R=(x R ,y R ,z R ), the three-dimensional coordinates of the pubic symphysis are P=(x p ,y p ,z p ), and the unit normal vector of the coronal plane is N=(0,0,1). The coordinates of the midpoints of the left and right hip joints are: ,
左、右髋关节的连线与冠状面的夹角为： 。 The angle between the line connecting the left and right hip joints and the coronal plane is: .
具体的：Specific:
所述步骤S2的对渲染的人体图像A通道进行连通域分析包括以下步骤：The step S2 of performing connected domain analysis on the rendered human body image A channel comprises the following steps:
步骤S2.1：在人体背面图像A通道中，遍历图像左半边值为255的像素，找到其中最下方的像素点作为左脚底点，遍历图像右半边值为255的像素，找到其中最下方的像素点作为右脚底点；Step S2.1: In channel A of the back image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the left foot bottom point, and traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the right foot bottom point;
步骤S2.2：在人体背面图像A通道中取左、右脚底点中位置最上方的点作为参考像素点，过该参考像素点画一条水平直线，将位于该水平线下方的所有像素值置为255，使得人体的双腿间隙区域构成了一个像素值为0的封闭的连通域，取水平直线上位于左、右脚底点之间任意位置的一个像素作为样本点，通过调用OpenCV的connectedComponentsWithStats函数对A通道进行连通域分析，定位出包含该样本点的连通域，即为双腿间隙区域；Step S2.2: Take the topmost point of the left and right soles in the A channel of the back image of the human body as the reference pixel point, draw a horizontal straight line through the reference pixel point, set all pixel values below the horizontal line to 255, so that the gap between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the gap between the legs;
步骤S2.3：遍历双腿间隙区域内的像素，找到区域中位置最上的像素点作为双腿间隙区域顶点。Step S2.3: Traverse the pixels in the gap area between the legs and find the top pixel in the area as the vertex of the gap area between the legs.
所述步骤S7对渲染的人体图像A通道进行连通域分析包括以下步骤：The step S7 of performing connected domain analysis on the A channel of the rendered human body image comprises the following steps:
步骤S7.1：在人体正面图像A通道中，遍历图像左半边值为255的像素，找到其中最下方的像素点作为右脚底点，遍历图像右半边值为255的像素，找到其中最下方的像素点作为左脚底点；Step S7.1: In channel A of the front image of the human body, traverse the pixels with a value of 255 on the left half of the image, find the bottom pixel point as the right foot bottom point, traverse the pixels with a value of 255 on the right half of the image, find the bottom pixel point as the left foot bottom point;
步骤S7.2：在人体正面图像A通道中取左、右脚底点中位置最上方的点作为参考像素点，过该参考像素点做一条水平直线，将位于该水平线下方的所有像素值置为255，使得人体的双腿间隙区域构成了一个像素值为0的封闭的连通域，取水平直线上位于左、右脚底点之间任意位置的一个像素作为样本点，通过调用OpenCV的connectedComponentsWithStats函数对A通道进行连通域分析，定位出包含该样本点的连通域，即为双腿间隙区域。Step S7.2: Take the topmost point among the left and right soles in the A channel of the human front image as the reference pixel, draw a horizontal straight line through the reference pixel, set all pixel values below the horizontal line to 255, so that the area between the legs of the human body constitutes a closed connected domain with a pixel value of 0, take a pixel at any position between the left and right soles on the horizontal straight line as a sample point, perform a connected domain analysis on the A channel by calling the connectedComponentsWithStats function of OpenCV, and locate the connected domain containing the sample point, which is the area between the legs.
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2023/127750 WO2024179011A1 (en) | 2023-10-30 | 2023-10-30 | Pelvis assessment method based on three-dimensional human body model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2023/127750 WO2024179011A1 (en) | 2023-10-30 | 2023-10-30 | Pelvis assessment method based on three-dimensional human body model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024179011A1 true WO2024179011A1 (en) | 2024-09-06 |
Family
ID=92589502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/127750 Pending WO2024179011A1 (en) | 2023-10-30 | 2023-10-30 | Pelvis assessment method based on three-dimensional human body model |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2024179011A1 (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780715A (en) * | 2016-11-08 | 2017-05-31 | 四川大学华西医院 | Method for establishing pelvis CT three-dimensional coordinate system |
| CN107016666A (en) * | 2017-02-28 | 2017-08-04 | 四川大学华西医院 | Image post-processing method for pelvis CT three-dimensional reconstruction based on coordinate system |
| CN114569887A (en) * | 2022-02-28 | 2022-06-03 | 成都赫桥健康科技有限公司 | Female urinary incontinence treatment system based on regional dependence theory |
| US20220183760A1 (en) * | 2020-12-15 | 2022-06-16 | Stryker Corporation | Systems and methods for generating a three-dimensional model of a joint from two-dimensional images |
| CN117115104A (en) * | 2023-08-24 | 2023-11-24 | 西安维塑智能科技有限公司 | Pelvis evaluation method based on three-dimensional human body model |
-
2023
- 2023-10-30 WO PCT/CN2023/127750 patent/WO2024179011A1/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780715A (en) * | 2016-11-08 | 2017-05-31 | 四川大学华西医院 | Method for establishing pelvis CT three-dimensional coordinate system |
| CN107016666A (en) * | 2017-02-28 | 2017-08-04 | 四川大学华西医院 | Image post-processing method for pelvis CT three-dimensional reconstruction based on coordinate system |
| US20220183760A1 (en) * | 2020-12-15 | 2022-06-16 | Stryker Corporation | Systems and methods for generating a three-dimensional model of a joint from two-dimensional images |
| CN114569887A (en) * | 2022-02-28 | 2022-06-03 | 成都赫桥健康科技有限公司 | Female urinary incontinence treatment system based on regional dependence theory |
| CN117115104A (en) * | 2023-08-24 | 2023-11-24 | 西安维塑智能科技有限公司 | Pelvis evaluation method based on three-dimensional human body model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Munn et al. | Changes in face topography from supine-to-upright position—and soft tissue correction values for craniofacial identification | |
| CN107481228B (en) | Human back scoliosis angle measuring method based on computer vision | |
| CN114983396B (en) | An automatic detection system for scoliosis | |
| Douglas | Image processing for craniofacial landmark identification and measurement: a review of photogrammetry and cephalometry | |
| Pazos et al. | Reliability of trunk shape measurements based on 3-D surface reconstructions | |
| CN108151670B (en) | Device and method for evaluating three-dimensional symmetry of back | |
| Shui et al. | Densely calculated facial soft tissue thickness for craniofacial reconstruction in Chinese adults | |
| CN109893146A (en) | A kind of female pelvic dysfunction appraisal procedure and its system | |
| CN107714082A (en) | A kind of ultrasonic probe caliberating device and method based on optical alignment | |
| CN107945169B (en) | A Coronary Artery Imaging Analysis Method | |
| Huang et al. | Scoliotic imaging with a novel double-sweep 2.5-dimensional extended field-of-view ultrasound | |
| CN103055424A (en) | Radiation therapy curative effect evaluation device and method based on CT/MRI (Computed Tomography/Magnetic Resonance Imaging) double-body position scanning automatic registration and fusion | |
| Zhang | The application of forensic imaging to sex estimation: focus on skull and pelvic structures | |
| CN111184535B (en) | Handheld unconstrained scanning wireless three-dimensional ultrasonic real-time voxel imaging system | |
| CN117115104A (en) | Pelvis evaluation method based on three-dimensional human body model | |
| CN108670302A (en) | A kind of spinal three-dimensional structure reproduction method based on 2.5 dimension ultrasonic wide-scene imagings | |
| WO2024179011A1 (en) | Pelvis assessment method based on three-dimensional human body model | |
| CN119559339B (en) | Bladder EIT three-dimensional morphology real-time reconstruction and capacity measurement method based on deep learning | |
| Guo et al. | Fully Automated Localization and Measurement of Levator Hiatus Dimensions Using 3-D Pelvic Floor Ultrasound | |
| Zheng et al. | Real-time extended-field-of-view ultrasound based on a standard PC | |
| Vannier et al. | Visualization of prosthesis fit in lower-limb amputees | |
| CN116211353A (en) | Wearable ultrasound bladder volume measurement and multimodal image topography assessment system | |
| CN115880469A (en) | A Registration Method of Surface Point Cloud Data and 3D Image | |
| JP2011062253A (en) | Tomographic image processor, muscle cross-sectional area measurement system, and tomographic image processing method | |
| CN104408305B (en) | The method for setting up high definition medical diagnostic images using multi-source human organ image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23924962 Country of ref document: EP Kind code of ref document: A1 |