CN109567816B - Monocular vision-based cervical vertebra mobility measuring system and method - Google Patents
Monocular vision-based cervical vertebra mobility measuring system and method Download PDFInfo
- Publication number
- CN109567816B CN109567816B CN201811327436.6A CN201811327436A CN109567816B CN 109567816 B CN109567816 B CN 109567816B CN 201811327436 A CN201811327436 A CN 201811327436A CN 109567816 B CN109567816 B CN 109567816B
- Authority
- CN
- China
- Prior art keywords
- helmet
- coordinate system
- rotation
- camera
- target
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6803—Head-worn items, e.g. helmets, masks, headphones or goggles
Abstract
The invention discloses a system and a method for measuring the activity of cervical vertebra based on monocular vision, wherein a camera shoots helmet target images worn on the head of a tested person in the process of rotating the head of the tested person, the camera is arranged above the head of the person, and the target is positioned at the top of the helmet; the camera transmits the shot image of the helmet target to the computer, and the computer calculates a translation rotation matrix from the helmet coordinate system to the helmet coordinate system when the tested person sits up after the tested person moves, so that rotation angles alpha, beta and gamma of x, y and z axes of the helmet coordinate system to the tested person sits up after the tested person moves are obtained. The invention adopts a monocular vision mode to measure the pose of the helmet coordinate system, has high pose measurement precision and high calculation speed, and thus ensures the measurement precision and speed of the cervical vertebra mobility.
Description
Technical Field
The disclosure relates to the technical field of cervical vertebra mobility measurement, in particular to a cervical vertebra mobility measurement system and method based on machine vision.
Background
The activity of cervical vertebra is an important evaluation index of cervical vertebra function, and has important significance for early diagnosis of cervical spondylosis, prediction of cervical spondylosis and evaluation of cervical spondylosis curative effect.
The activity of the cervical vertebrae includes 6 angular ranges of forward flexion, backward extension, left lateral flexion, right lateral flexion, left rotation and right rotation. At present, the method for measuring the activity of cervical vertebra mainly comprises the following steps: tape measure, protractor, CROM, X-ray, and CT three-dimensional reconstruction, among others. The measuring processes of a tape measuring method, a protractor measuring method and a CROM instrument are complex, and workers are required to participate; the X-ray measurement method and the CT three-dimensional reconstruction measurement method are highly accurate, but are likely to cause damage to human health.
In the prior art, publication number CN105816182A discloses a cervical vertebra activity degree measuring method based on a Kinect sensor, which discloses using a sensor to acquire and transmit depth data and color data in a field of view of the sensor, then lifting three-dimensional coordinates of facial feature points and skeletal joint points of a human body, then constructing head and trunk feature vectors, and calculating a cervical vertebra activity angle.
The patent publication No. CN106447733A discloses a method, a system and a device for determining the activity of cervical vertebrae and the position of a movable axis, wherein a binocular vision camera is used for shooting an image of a detection mark worn on the head of a detected person in the head rotation process of the detected person, a triangulation method is used for determining the central position of a three-dimensional point corresponding to the detection mark image group to obtain a sampling point, the sampling point is projected into a projection plane to obtain a projection point, and a least square fitting method is used for fitting the projection point to obtain the position of the movable axis of the cervical vertebrae and the activity of the cervical vertebrae.
However, the above patent technology has problems in measurement: the cervical vertebra mobility measuring method based on the Kinect sensor needs to identify key points of a human face and characteristic points of bones, and is low in precision; during cervical vertebra horizontal rotation motion, the angle is great, and the human face key point can appear in Kinect detection blind area, unable discernment.
In addition, the measurement method of the patent CN106447733A is complex, the real-time performance is not high, and a plurality of images need to be shot in each measurement of the activity of the cervical vertebra. Meanwhile, in the specific implementation, the circle is fitted by the mark points on the chessboard through the least square method, and the error is large.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a system and a method for measuring the activity of cervical vertebrae based on monocular vision.
Cervical vertebra mobility measurement system based on monocular vision:
comprises a helmet, a camera and a computer;
the helmet is characterized in that a plurality of targets are arranged at the top of the helmet, a camera is mounted above the head of a person to be tested, and the camera shoots target images;
the camera transmits the shot image to a computer, and the computer calculates rotation angles alpha, beta and gamma of a helmet coordinate system relative to x, y and z axes of the helmet coordinate system when the tested person sits up after moving, wherein beta is the anteflexion/extension activity degree, alpha is the left side flexion/right side flexion activity degree, and gamma is the left rotation/right rotation activity degree.
Furthermore, the top of the helmet is of a plane structure, the edge of the lower portion of the helmet is on the same plane and parallel to the plane of the top, a plurality of circular targets are arranged on the top of the helmet, the targets are different in color, and the targets on the helmet can be matched with the targets in the camera image according to the color.
Furthermore, the targets at the top of the helmet are 4 circular targets which are arranged in a square shape, four sides of the square are parallel to four edges of the upper part of the helmet, the colors of the 4 targets are red, green, yellow and blue, the red target is arranged at the upper left, the green target is arranged at the upper right, the yellow target is arranged at the lower right, the blue target is arranged at the lower left, the end point near the red target is used as the origin, the marginality near the red and blue target is used as the x axis, and the marginal line near the red and green target is used as the y axis to establish a coordinate system of the helmet.
Furthermore, the front part of the helmet is provided with a positioning line, for a square helmet, two end points of the positioning line are respectively the middle points of the upper edge and the lower edge, the positioning line is combined with the central axis of the face of a user to help the tester to ensure that the wearing posture of the helmet is correct, and the camera is used for collecting a target image at the top of the helmet.
Furthermore, the computer is connected with a sound module, and the sound module is used for prompting a measurer to measure, reminding the measurer to correctly wear the helmet and reminding the measurer to do movement in a certain direction of the neck, and if the movement in other directions exceeds a set value, the sound module is used for reminding the measurer to reduce the amount of movement in other directions.
The method for measuring the activity of the cervical vertebra based on monocular vision comprises the following steps:
acquiring an image of a detection mark worn on the head of a detected person in the rotation process of the head of the detected person, wherein the image is shot by a camera, and the detection mark of the head of the detected person is a target arranged at the top of a helmet worn on the head of the detected person;
the camera transmits the shot image of the detection mark to the computer, and the rotation angles alpha, beta and gamma of the helmet coordinate system after movement to the X, Y and Z axes of the helmet coordinate system when the detected person sits up are calculated in the computer according to the position coordinate of the image of the detection mark in the helmet coordinate system, wherein beta is the forward flexion/backward extension activity, alpha is the left side flexion/right side flexion activity, and gamma is the left rotation/right rotation activity.
Furthermore, before the measured person measures the activity of the cervical vertebra, a helmet coordinate system needs to be established and the position coordinates of the center of a target circle on the helmet in the helmet coordinate system need to be measured.
Furthermore, before the measured person measures the activity of the cervical vertebra, the parameter matrix in the monocular camera needs to be calibrated.
Furthermore, when the tested person carries out cervical vertebra mobility measurement, the tested person sits up, 4 lower edges of the helmet are guaranteed to be located on the same horizontal plane and parallel to the two brows of the tested person, and the positioning line of the front portion of the helmet is overlapped with the central axis of the face of the tested person.
Further, the camera shoots helmet images of the person to be detected when sitting up, and a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system is calculated0。
Further, the camera collects the image of the tested person doing the maximum-scale neck forward/backward bending movement, and calculates the rotation and translation matrix H from the helmet coordinate system to the camera coordinate system1The rotation and translation matrix from the helmet coordinate system after the forward/backward stretching exercise to the helmet coordinate system when the tested person sits up is A1＝H1H0 -1According to A1And (3) calculating rotation angles α, β and gamma of the helmet coordinate system after exercise to x, y and z axes of the helmet coordinate system when the measurer sits up, recording that the motion degree of the helmet is the forward bending/backward stretching motion degree β if α and gamma are smaller than a set threshold t, otherwise, reminding the measurer to reduce the left and right lateral bending and left and right rotation motion amounts, and measuring the forward bending/backward stretching motion degree again by the system.
Further, the camera collects images of the tested person in the maximum-scale left/right neck bending movement, and a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system is calculated2The rotation and translation matrix from the helmet coordinate system after the forward/backward stretching exercise to the helmet coordinate system when the tested person sits up is A2＝H2H0 -1According to A1And (3) calculating rotation angles α, β and gamma of the helmet coordinate system after exercise to x, y and z axes of the helmet coordinate system when the measurer sits up, recording that the motion degree of left-side bending/right-side bending is α if β and gamma are smaller than a set threshold t, otherwise, reminding the measurer to reduce the motion amounts of front-back stretching and left-right rotation by the system, and re-performing the motion degree of left-side bending/right-side bending.
Further, the camera collects the measured dataThe image of the person doing the left/right rotation movement of the neck with the maximum scale calculates the rotation and translation matrix H from the helmet coordinate system to the camera coordinate system3The rotation and translation matrix from the helmet coordinate system after the forward/backward stretching exercise to the helmet coordinate system when the tested person sits up is A3＝H3H0 -1According to A1And (3) calculating rotation angles α, β and gamma of the helmet coordinate system to x, y and z axes of the helmet coordinate system when the measurer sits up after exercise, recording that gamma is the left rotation/right rotation activity if α and β are smaller than a set threshold t, otherwise, reminding the measurer to reduce the front and back stretching and left and right lateral bending motion and carrying out the left rotation/right rotation activity again by the system.
Further, a rotation-translation-rotation matrix H from the helmet coordinate system to the camera coordinate system is calculated, where H is H0、H1、H2Or H3The specific process is as follows:
a camera collects helmet target images;
identifying a target connected domain according to the color and the circular shape, and taking the gravity center of the connected domain as the center of a circle of the target;
color recognition: target color T (T) in image acquired by cameraR,TG,TB) And a contrast color C (C)R,CG,CB) Similarity of (2):
setting a threshold value, and considering the target color as the contrast color when d is smaller than the threshold value;
and (3) identifying the circular shape: a circularity method, Hough circle transformation or a least square method is adopted;
matching the center of a target circle in a helmet coordinate system with the center of a target circle in a camera coordinate system according to color
Calculating the coordinates of each target in the helmet coordinate system in the camera coordinate system according to the pnp algorithm
According to the coordinates of the four target feature points in the helmet coordinate system and the camera coordinate system, calculating a rotation translation matrix from the helmet coordinate system to the camera coordinate system:
the coordinate vector c of the same characteristic point in the camera coordinate system and the coordinate vector m of the same characteristic point in the helmet coordinate system have the following relationship:
c＝Rm+T (1)
wherein R represents a rotation matrix and T represents a translation matrix;
solving a rotation matrix R from a helmet coordinate system to a camera coordinate system according to a vector method;
substituting R into formula (1) to obtain translation matrix T, and rotating the translation matrix
Further, the process of calculating the rotation angles alpha, beta and gamma of the helmet coordinate system after the movement to the x, y and z axes of the helmet coordinate system when the measurer sits up according to the translation rotation matrix a from the helmet coordinate system after the movement to the helmet coordinate system when the measurer sits up includes:
a matrix A is known, where A is A1、A2Or A3；
Wherein:
then:
β＝arcsin(-r31)
compared with the prior art, the beneficial effect of this disclosure is:
1. the whole system is simple in structure, can be completed by only one camera, one target helmet and one computer, and is low in cost.
2. The measuring personnel can complete the whole measuring process according to the prompt of the system without the participation of the working personnel.
3. The method and the device combine the color of the target and the circular shape of the target to identify the target, and improve the identification accuracy.
4. The helmet coordinate system target and the pixel coordinate system target are matched based on the colors, and the matching difficulty is reduced.
5. The method adopts a monocular vision mode to measure the pose of the helmet coordinate system, and improves the pose measurement precision, thereby improving the cervical vertebra mobility measurement precision.
6. The future system upgrading of the system is mainly focused on the aspect of a pose measurement algorithm of a helmet coordinate system, and the cost increase caused by system upgrading is reduced.
7. According to the technical scheme, the camera is placed at the top of the tested person, and the range of the degree of motion of the person rotating left and right is the largest, so that the camera is placed at the top to avoid a visual field blind area during shooting.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a system diagram illustrating an exemplary embodiment of the present disclosure;
FIG. 2 is a schematic view of a helmet according to an embodiment of the present application;
fig. 3(a) -3 (b) are schematic measurement diagrams of an embodiment of the present application.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In an exemplary embodiment of the present application, as shown in fig. 1, a cervical vertebrae movement measuring system based on machine vision includes: helmet, camera, computer, sound module.
Specifically, the top of the helmet is a plane, the lower edge is in the same plane and parallel to the top plane, the helmet is preferably in a cube structure, the top of the helmet is provided with a plurality of circular targets, the colors of the targets are different, the targets can be quickly identified according to the circular shapes and colors of the targets, the targets of the helmet can be matched with the targets in the camera image according to the colors, 4 circular targets are preferably selected and arranged in a square shape, four sides of the square are parallel to four edges of the upper portion of the helmet, the 4 target colors are red, green, yellow and blue, when observed from the front portion of the helmet, the red target is on the upper left, the green target is on the upper right, the yellow target is on the lower right, the blue target is on the lower left, the end point near the red target is taken as the origin, the edge property near the red and blue targets is taken as the x axis, and the edge line near the red and, as shown in fig. 2.
In a specific implementation example, the front part of the helmet is provided with a positioning line, for a square helmet, two end points of the positioning line are respectively the middle points of the upper edge and the lower edge, and the positioning line is combined with the central axis of the face of a user to help the tester to ensure that the wearing posture of the helmet is correct. The camera is fixedly arranged above the measuring area of the measurer and used for collecting the target image at the top of the helmet, and the camera is connected with the computer.
In a specific implementation example, the computer is used for processing the images acquired by the camera and calculating the cervical vertebra activity of the measurer according to the images. The computer is connected with the sound module.
In a specific implementation example, the sound module is used for prompting a measurer to perform a measurement step, prompting the measurer to correctly wear a helmet and prompting the measurer to perform a certain direction of neck movement, and if the movement of the neck in other directions exceeds a set value during the movement, the sound module prompts the measurer to reduce the amount of movement in other directions. For example, when the left/right rotation activity is measured, the neck of the person is subjected to forward/backward stretching movement at the same time, so that the left/right rotation activity is not accurately measured, and at the moment, the sound module sends out corresponding prompt to the person to be measured, so that the forward/backward stretching movement is reduced.
In another embodiment of the present application, it is disclosed that the measurement system comprises the following steps when measuring the activity of the cervical vertebrae:
1. measuring the position coordinates of the centers of the four circular targets in a helmet coordinate system;
2. calibrating a camera intrinsic parameter matrix M by a Zhang-Yongyou calibration method:
where f denotes the focal length, dx and dy denote the pixel size, and u0 and v0 denote the coordinates of the camera optical axis in the pixel coordinate system.
The steps 1 and 2 can be performed once before the measuring system leaves a factory or is used for the first time.
The steps 1 and 2 are important steps for measuring the pose of the helmet coordinate system through a camera, and the calculation of subsequent data is carried out based on the steps.
Regarding the measurement of the activity of the cervical vertebrae, as shown in fig. 3(a) -3 (b), the steps are as follows:
step (1), a measurer sits up, wears the helmet on the head of the measurer, ensures that 4 lower edges of the helmet are positioned on the same horizontal plane and parallel to the brow of the measurer, and the positioning line at the front part of the helmet is superposed with the central axis of the face of the measurer.
Step (2) the camera shoots the helmet image when the measurer sits up, the collected image is transmitted to the computer, and the coordinate system of the helmet to the coordinate system of the camera are calculated in the computerRotational translation matrix H0。
And (3) the measurer does neck anteflexion or extension movement, stops the movement when the neck feels uncomfortable, takes a picture by the camera, transmits the acquired image to the computer, and calculates a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system in the computer1The rotation-translation matrix of the helmet coordinate system after the forward/backward flexion exercise to the helmet coordinate system when the measurer sits up is A1＝H1H0 -1According to A1And (3) calculating rotation angles α, β and gamma of the helmet coordinate system after exercise to x, y and z axes of the helmet coordinate system when the measurer sits up, recording β whether the movement degree is anteflexion or extension movement degree if α and gamma are smaller than a set threshold value t, otherwise, reminding the measurer to reduce the movement amount of left/right lateral flexion and left/right rotation by the system, and repeating the step (3).
For example, when the neck of the tested person moves forward or backward, the neck can rotate left and right and move left and right, and the forward/backward movement is affected by the left and right rotation and the left and right lateral bending, so that the activity measurement is inaccurate, and the ideal situation is as follows: the neck does the anteflexion/extension movement, the other two directions have no movement condition, namely beta is changed, and alpha and gamma are not changed, so that when alpha and gamma are smaller than a set threshold t, the neck can be regarded as the movement amount of the left and right rotation of the anteflexion and the extension and the left and right lateral flexion is in a tolerance range, and the beta at the moment is regarded as the reasonable activity degree of the anteflexion and the extension.
And (4) the measurer does left-side bending or right-side bending movement of the neck, stops moving when the neck feels uncomfortable, takes pictures by the camera, transmits the acquired images to the computer, and calculates a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system in the computer2The rotation and translation matrix from the helmet coordinate system after the left-side flexion or right-side flexion to the helmet coordinate system when the measurer sits up is A2＝H2H0 -1According to A2Calculating the rotation angles α, β and gamma of the helmet coordinate system after exercise to the x, y and z axes of the helmet coordinate system when the measurer sits up, recording α the degree of left/right bending activity if β and gamma are less than the set threshold t, otherwise, the system raisesAnd (5) waking the measurer to reduce the forward and backward stretching and left and right rotating motion amount, and then re-performing the step (4).
Step (5), the measurer does left rotation or right rotation movement of the neck, stops moving when the neck feels uncomfortable, takes pictures by the camera, transmits the collected images to the computer, and calculates a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system in the computer3The rotation-translation matrix from the helmet coordinate system after the left-rotation or right-rotation movement to the helmet coordinate system when the measurer sits up is A3＝H3H0 -1According to A3And (3) calculating rotation angles α, β and gamma of the helmet coordinate system after exercise to x, y and z axes of the helmet coordinate system when the measurer sits up, recording that gamma is a left rotation activity or a right rotation activity if α and β are smaller than a set threshold t, otherwise, reminding the measurer to reduce the front and back stretching and left and right lateral bending activities by the system, and repeating the step (5).
Wherein, a rotation and translation rotation matrix H from the helmet coordinate system to the camera coordinate system is solved, wherein H is H0、H1、H2Or H3The specific process is as follows:
(1) a camera collects a target image;
(2) identifying a target connected domain according to the color and the circular shape, and taking the gravity center of the connected domain as the center of a circle of the target;
color recognition: target color T (T) in helmet image acquired by cameraR,TG,TB) And contrast color C (C) in cameraR,CG,CB) Similarity of (2):
and setting a threshold value, and considering that the target color is the contrast color when d is smaller than the set threshold value.
For example, the camera acquires the target image, and the three rgb channel values of contrast red are C (C)R,CG,CB) If the similarity d between the target color and the contrast red is less than the set threshold, the target is identified as red.
The circle shape identification can adopt a circularity method, Hough circle transformation or a least square method.
(3) Matching the center of a target circle in the helmet coordinate system with the center of a target circle in the camera coordinate system according to the color, wherein the center of the target circle is obtained in the step (2);
(4) calculating the coordinates of each target in the helmet coordinate system in the camera coordinate system according to the pnp algorithm
(6) According to the coordinates of the four target feature points in the helmet coordinate system and the camera coordinate system, calculating a rotation translation matrix from the helmet coordinate system to the camera coordinate system:
the coordinate vector c of the same characteristic point in the camera coordinate system and the coordinate vector m of the same characteristic point in the helmet coordinate system have the following relationship:
c＝Rm+T (1)
where R represents a rotation matrix and T represents a translation matrix.
A rotation matrix R from a helmet coordinate system to a camera coordinate system can be obtained according to a vector method;
substituting R into formula (1) to obtain translation matrix T, and rotating the translation matrix
H is H1, H2 or H3, and the calculation processes of the H, the H and the H are the same;
in addition, in the present application, the process of calculating the rotation angles α, β, γ from the helmet coordinate system after the movement to the helmet coordinate system when the measurer sits up according to the translational rotation matrix a from the helmet coordinate system after the movement to the helmet coordinate system when the measurer sits up includes:
the known translational rotation matrix A, A being A1、A2Or A3The three calculation processes are the same:
wherein: a is calculated in steps (2), (3) and (4), and r is11r12r13And so on is R in AA specific numerical value;
then:
β＝arcsin(-r31)
the above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A cervical vertebra mobility measuring system based on monocular vision is characterized by comprising a helmet, a camera and a computer;
the helmet is characterized in that a plurality of targets are arranged at the top of the helmet, a camera is mounted above the head of a person to be tested, and the camera shoots target images;
the camera transmits the shot image to a computer, and the computer calculates rotation angles alpha, beta and gamma of a helmet coordinate system relative to x, y and z axes of the helmet coordinate system when the tested person sits up after moving, wherein beta is the anteflexion/extension activity degree, alpha is the left side flexion/right side flexion activity degree, and gamma is the left rotation/right rotation activity degree;
the camera shoots helmet images of the person to be detected when sitting, and the computer calculates a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system0；
The camera collects the image of the tested person doing the maximum neck forward/backward bending movement, and the computer calculates the rotation and translation matrix H from the helmet coordinate system to the camera coordinate system1Then go forward/backwardThe rotation and translation matrix from the helmet coordinate system after stretching movement to the helmet coordinate system when the tested person sits up is A1＝H1H0 -1According to A1And (3) calculating rotation angles α, β and gamma of the helmet coordinate system to the x, y and z axes of the helmet coordinate system when the tested person sits up after exercise, recording whether the front bending/rear stretching activity is β if α and gamma are smaller than a set threshold t, otherwise, reminding the tested person to reduce the left and right lateral bending and left and right rotation motion amount by the computer, and measuring the front bending/rear stretching activity again.
2. The monocular vision based cervical activity measuring system of claim 1, wherein the helmet top is a plane structure, the lower edge of the helmet is in the same plane and parallel to the top plane, the helmet top has a plurality of circular targets, the targets have different colors, and the targets on the helmet can be matched with the targets in the camera image according to the colors.
3. The monocular vision-based cervical mobility measurement system of claim 1, wherein the target at the top of the helmet is selected from 4 circular targets arranged in a square, four sides of the square are parallel to four edges of the upper portion of the helmet, the 4 targets are respectively red, green, yellow and blue, and when viewed from the front of the helmet, the red target is on the upper left, the green target is on the upper right, the yellow target is on the lower right, the blue target is on the lower left, the end point near the red target is used as the origin, the marginality near the red and blue target is used as the x-axis, and the edge line near the red and green target is used as the y-axis to establish the coordinate system of the helmet.
4. The monocular vision-based cervical mobility measurement system according to claim 1, wherein a positioning line is provided at the front part of the helmet, for a square helmet, two end points of the positioning line are middle points of upper and lower edges respectively, the positioning line is combined with a central axis of the face of the user to help the tester to ensure that the wearing posture of the helmet is correct, and the camera is used for collecting a target image at the top of the helmet;
the computer is connected with the sound module, and the sound module is used for prompting a measurer to measure, reminding the measurer to correctly wear the helmet and reminding the measurer to do movement in one direction of the neck, and if the movement in other directions exceeds a set value, the sound module is used for reminding the measurer to reduce the amount of movement in other directions.
5. The method for measuring the activity of the cervical vertebra based on monocular vision is characterized by comprising the following steps:
acquiring an image of a detection mark worn on the head of a detected person in the rotation process of the head of the detected person, wherein the image is shot by a camera, and the detection mark of the head of the detected person is a target arranged at the top of a helmet worn on the head of the detected person;
the camera transmits the shot image of the detection mark to the computer, and the rotation angles alpha, beta and gamma of the helmet coordinate system after movement to the helmet coordinate system when the detected person sits up are calculated in the computer according to the position coordinate of the image of the detection mark in the helmet coordinate system and the translation rotation matrix of the helmet coordinate system after movement to the helmet coordinate system when the detected person sits up, wherein beta is the forward flexion/backward extension activity, alpha is the left side flexion/right side flexion activity, and gamma is the left rotation/right rotation activity;
the camera shoots helmet images of the person to be detected when sitting up, and a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system is calculated0；
The camera collects the image of the tested person doing the maximum neck forward/backward bending movement, and calculates the rotation and translation matrix H from the helmet coordinate system to the camera coordinate system1The rotation and translation matrix from the helmet coordinate system after the forward/backward stretching exercise to the helmet coordinate system when the tested person sits up is A1＝H1H0 -1According to A1And (3) calculating rotation angles α, β and gamma of the helmet coordinate system after exercise to x, y and z axes of the helmet coordinate system when the measurer sits up, recording that the motion degree of the helmet is the forward bending/backward stretching motion degree β if α and gamma are smaller than a set threshold t, otherwise, reminding the measurer to reduce the left and right lateral bending and left and right rotation motion amounts, and measuring the forward bending/backward stretching motion degree again by the system.
6. The method as claimed in claim 5, wherein before the measurement of the activity of the cervical vertebrae, the coordinate system of the helmet is established and the position coordinates of the center of the target circle on the helmet in the coordinate system of the helmet are measured;
before the tested person carries out the measurement of the activity of the cervical vertebra, the parameter matrix in the monocular camera is calibrated.
7. The method as claimed in claim 5, wherein when measuring the activity of the cervical vertebrae, the person sits up to ensure that the 4 lower edges of the helmet are on the same horizontal plane and parallel to the brow of the person, and the positioning line of the front part of the helmet is coincident with the central axis of the face of the person.
8. The monocular vision-based cervical vertebrae movement degree measuring method as claimed in claim 5, wherein the camera collects the image of the person to be measured in the maximum-scale left/right flexion movement of the neck, and calculates the rotation and translation matrix H from the helmet coordinate system to the camera coordinate system2The rotation and translation matrix from the helmet coordinate system after the forward/backward stretching exercise to the helmet coordinate system when the tested person sits up is A2＝H2H0 -1According to A1Calculating rotation angles α, β and gamma of the helmet coordinate system after exercise to x, y and z axes of the helmet coordinate system when a measurer sits up, recording that α is left side bending/right side bending activity degree if β and gamma are smaller than a set threshold t, otherwise, reminding the measurer by the system to reduce the front and back stretching and left and right rotation motion amount, and re-performing the left side bending/right side bending activity degree;
further, the camera collects images of the tested person during the maximum-scale left/right rotation movement of the neck, and a rotation and translation matrix H from a helmet coordinate system to a camera coordinate system is calculated3The rotation and translation matrix from the helmet coordinate system after the forward/backward stretching exercise to the helmet coordinate system when the tested person sits up is A3＝H3H0 -1According to A1Calculating the x, y and z axes of the helmet coordinate system after exercise to the helmet coordinate system when the measurer sits upIf α and β are smaller than the set threshold t, the gamma is recorded as the left rotation/right rotation activity, otherwise, the system reminds the measurer to reduce the front and back stretching and left and right lateral bending motion amounts and to perform the left rotation/right rotation activity again.
9. The monocular vision-based cervical mobility measurement method of claim 8, wherein a rotation matrix H from a helmet coordinate system to a camera coordinate system is calculated, where H is H0、H1、H2Or H3The specific process is as follows:
a camera collects helmet target images;
identifying a target connected domain according to the color and the circular shape, and taking the gravity center of the connected domain as the center of a circle of the target;
color recognition: target color T (T) in image acquired by cameraR,TG,TB) And a contrast color C (C)R,CG,CB) Similarity of (2):
setting a threshold value, and considering the target color as the contrast color when d is smaller than the threshold value;
and (3) identifying the circular shape: a circularity method, Hough circle transformation or a least square method is adopted;
matching the center of a target circle in a helmet coordinate system with the center of a target circle in a camera coordinate system according to color
Calculating the coordinates of each target in the helmet coordinate system in the camera coordinate system according to the pnp algorithm
According to the coordinates of the four target feature points in the helmet coordinate system and the camera coordinate system, calculating a rotation translation matrix from the helmet coordinate system to the camera coordinate system:
the coordinate vector c of the same characteristic point in the camera coordinate system and the coordinate vector m of the same characteristic point in the helmet coordinate system have the following relationship:
c＝Rm+T (1)
wherein R represents a rotation matrix and T represents a translation matrix;
solving a rotation matrix R from a helmet coordinate system to a camera coordinate system according to a vector method;
substituting R into formula (1) to obtain translation matrix T, and rotating the translation matrix
10. The method as claimed in claim 8, wherein the calculating of the rotation angles α, β, γ of the helmet coordinate system after exercise to the x, y, z axes of the helmet coordinate system when the examinee sits up according to the translational rotation matrix a of the helmet coordinate system after exercise to the helmet coordinate system when the examinee sits up comprises:
a matrix A is known, where A is A1、A2Or A3；
Wherein:
then:
β＝arcsin(-r31)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811327436.6A CN109567816B (en) | 2018-11-08 | 2018-11-08 | Monocular vision-based cervical vertebra mobility measuring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811327436.6A CN109567816B (en) | 2018-11-08 | 2018-11-08 | Monocular vision-based cervical vertebra mobility measuring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109567816A CN109567816A (en) | 2019-04-05 |
| CN109567816B true CN109567816B (en) | 2020-08-25 |
Family
ID=65921990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811327436.6A Expired - Fee Related CN109567816B (en) | 2018-11-08 | 2018-11-08 | Monocular vision-based cervical vertebra mobility measuring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109567816B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163087B (en) * | 2019-04-09 | 2022-03-25 | 江西高创保安服务技术有限公司 | Face gesture recognition method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2404482Y (en) * | 1999-09-30 | 2000-11-08 | 深圳市金士吉康复用品科技有限公司 | Device for measuring cervical vertebra |
| CN201131742Y (en) * | 2008-01-09 | 2008-10-15 | 张明才 | Cervical vertebra activity degree detecting device |
| CN101879057A (en) * | 2009-05-05 | 2010-11-10 | 上海中医药大学附属岳阳中西医结合医院 | Three-dimensional head spatial repositioning offset measuring system and operation method thereof |
| WO2013146436A1 (en) * | 2012-03-27 | 2013-10-03 | 株式会社明治 | Deglutition simulation device and method |
| CN104127188A (en) * | 2014-08-08 | 2014-11-05 | 沈迪 | Method and device for monitoring amount of exercise of neck |
| CN105816182A (en) * | 2016-03-24 | 2016-08-03 | 西安交通大学 | Method for measuring cervical vertebra motion degree on basis of Kinect sensor |
| CN105997090A (en) * | 2016-04-29 | 2016-10-12 | 乐视控股（北京）有限公司 | Method and device for head-neck posture monitoring |
| CN106447733A (en) * | 2016-09-28 | 2017-02-22 | 北京理工大学 | Cervical vertebra motion degree and motion axial line position determining method, system and device |
-
2018
- 2018-11-08 CN CN201811327436.6A patent/CN109567816B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2404482Y (en) * | 1999-09-30 | 2000-11-08 | 深圳市金士吉康复用品科技有限公司 | Device for measuring cervical vertebra |
| CN201131742Y (en) * | 2008-01-09 | 2008-10-15 | 张明才 | Cervical vertebra activity degree detecting device |
| CN101879057A (en) * | 2009-05-05 | 2010-11-10 | 上海中医药大学附属岳阳中西医结合医院 | Three-dimensional head spatial repositioning offset measuring system and operation method thereof |
| WO2013146436A1 (en) * | 2012-03-27 | 2013-10-03 | 株式会社明治 | Deglutition simulation device and method |
| CN104127188A (en) * | 2014-08-08 | 2014-11-05 | 沈迪 | Method and device for monitoring amount of exercise of neck |
| CN105816182A (en) * | 2016-03-24 | 2016-08-03 | 西安交通大学 | Method for measuring cervical vertebra motion degree on basis of Kinect sensor |
| CN105997090A (en) * | 2016-04-29 | 2016-10-12 | 乐视控股（北京）有限公司 | Method and device for head-neck posture monitoring |
| CN106447733A (en) * | 2016-09-28 | 2017-02-22 | 北京理工大学 | Cervical vertebra motion degree and motion axial line position determining method, system and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109567816A (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11100636B2 (en) | Systems, devices, and methods for tracking and compensating for patient motion during a medical imaging scan | |
| CN106168853B (en) | A kind of free space wear-type gaze tracking system | |
| US20200268339A1 (en) | System and method for patient positioning | |
| CN107481228B (en) | Human back scoliosis angle measuring method based on computer vision | |
| US11576578B2 (en) | Systems and methods for scanning a patient in an imaging system | |
| CN106580470B (en) | Head localization method and system based on binocular vision | |
| US20160317122A1 (en) | In-device fusion of optical and inertial positional tracking of ultrasound probes | |
| CN108846866B (en) | Optical imaging-based craniomaxillofacial soft tissue sagittal axial median plane determination method and system | |
| US20140221819A1 (en) | Apparatus, system and method for surgical navigation | |
| US20150029322A1 (en) | Method and computations for calculating an optical axis vector of an imaged eye | |
| CN109008944A (en) | Sight measuring device, sight measuring program and sight measuring method | |
| CN113240726B (en) | Real-time measurement method for optical target size under endoscope | |
| JP2016173313A (en) | Visual line direction estimation system, visual line direction estimation method and visual line direction estimation program | |
| CN103948432A (en) | Algorithm for augmented reality of three-dimensional endoscopic video and ultrasound image during operation | |
| CN110059670B (en) | Non-contact measuring method and equipment for head and face, limb movement angle and body posture of human body | |
| CN109567816B (en) | Monocular vision-based cervical vertebra mobility measuring system and method | |
| CN106580329A (en) | Height measurement system and method based on binocular stereovision technology | |
| JP3711053B2 (en) | Line-of-sight measurement device and method, line-of-sight measurement program, and recording medium recording the program | |
| CN109620142B (en) | Cervical vertebra mobility measuring system and method based on machine vision | |
| US8915868B1 (en) | Instrument for measuring the posture of a patent | |
| CN112656366B (en) | Method and system for measuring pupil size in non-contact manner | |
| CN104305996A (en) | Image recognition technology-based respiration monitoring method and system | |
| CN111950639B (en) | Imaging method for synchronously displaying ultrasonic and tomographic anatomical images in real time | |
| CN111860275B (en) | Gesture recognition data acquisition system and method | |
| CN107843863B (en) | Magnetic resonance imaging correction method, device and equipment based on 3D topography measurement |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200825 Termination date: 20201108 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |