CN116309712B - Functional motion analysis system and method based on depth camera - Google Patents
Functional motion analysis system and method based on depth camera Download PDFInfo
- Publication number
- CN116309712B CN116309712B CN202310249317.8A CN202310249317A CN116309712B CN 116309712 B CN116309712 B CN 116309712B CN 202310249317 A CN202310249317 A CN 202310249317A CN 116309712 B CN116309712 B CN 116309712B
- Authority
- CN
- China
- Prior art keywords
- depth
- plane
- information
- points
- human body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000033001 locomotion Effects 0.000 title claims abstract description 55
- 238000004458 analytical method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 210000000988 bone and bone Anatomy 0.000 claims description 19
- 230000009916 joint effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000000691 measurement method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 210000002683 foot Anatomy 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 210000003423 ankle Anatomy 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 7
- 238000011156 evaluation Methods 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 abstract description 5
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 238000011161 development Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/579—Depth or shape recovery from multiple images from motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of electronic information, in particular to a functional motion analysis system and method based on a depth camera, comprising the following steps: acquiring multi-frame depth pictures and color pictures by using a depth camera; acquiring 16 skeleton key points of a human body and acquiring coordinate information; splicing skeleton points, and calculating angles according to three-dimensional coordinates in a depth space simplified by a relatively moving surface; measuring and calculating the distance by moving the human body forwards and backwards at regular time based on the depth information; setting a threshold value of an active area, and eliminating interference of other people; and measuring the completion degree of the special exercise, and evaluating. The invention has the functions of body posture evaluation test, functional balance analysis, movement angle monitoring under special conditions and the like; the non-contact measurement requirement data are adopted, so that the safety is ensured; the three-dimensional information is converted into two-dimensional information, so that the efficiency of calculating the technical indexes is improved; and the method has an independent scoring algorithm, scores all functional exercises, and guides the scientific development of subsequent training.
Description
Technical Field
The invention relates to the technical field of electronic information, in particular to a functional motion analysis system and method based on a depth camera.
Background
Machine vision has the advantages of no contact, no need of hardware, safety and the like, but the application of the machine vision in a complex environment such as functional movement is still a difficult problem. In the existing training, the existing technology often uses external equipment such as hardware of a sensor and the like, when people perform training practice, exertion can be greatly influenced, misjudgment is easy to cause, and the exercise personnel wearing the equipment can be damaged, so that the practical application is not facilitated. The method does not use a large amount of hardware equipment, simultaneously achieves safe non-contact measurement and digitizes indicators such as joint activity, deflection degree and the like, and becomes a difficult problem of the current functional training.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a functional motion analysis system and a functional motion analysis method based on a depth camera, which are used for calculating technical indexes such as joint activity, offset degree and the like through various algorithms, digitizing the technical indexes and guiding scientific functional training.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a functional motion analysis method based on a depth camera comprises the following specific steps:
step 1: setting a depth camera at a certain height position, enabling a person to be tested to face the camera in the forward direction, ensuring that pictures in the depth camera can shoot the whole body and the ground touched by feet, and waiting for a command from a server;
step 2: receiving a command and determining a function, and acquiring multi-frame depth pictures and color pictures by using a depth camera; acquiring 16 skeletal key points of a human body, and acquiring depth information to form a three-dimensional coordinate;
the three-dimensional coordinate information is acquired based on a three-dimensional coordinate system of the depth camera, an origin O of the three-dimensional coordinate system is positioned at the center of the camera, an X axis is parallel to a ground plane, a Y axis is perpendicular to the ground plane, and a Z axis is a plane formed by being perpendicular to XOY;
step 3: connecting skeleton points, simplifying three-dimensional coordinate information in a depth space, and calculating angles;
the bone points are logically connected, and the joint bone points to be measured and other two joint point information related to the joint bone points are extracted to obtain three-dimensional coordinate information (x 1 ,y 1 ,z 1 ) Information simplification is carried out, and angles are calculated based on the newly simplified coordinates;
step 4: measuring and calculating the front and back movement of the standing and timing human body based on the depth information of the skeleton points, and measuring and calculating the distance;
the distance measurement is carried out by evaluating the human body in standing, and is obtained by utilizing the depth value information of the bone points and using a depth-based offset distance measurement method;
step 5: setting a threshold value of an active area, and eliminating interference of other people;
the step of eliminating interference of other people is to select a depth value of the body center of a person to be measured and set a depth upper limit and a depth lower limit based on the depth value, so that detection is ensured to only occur in any specified measuring area;
step 6: measuring the degree of completion of the special exercise and grading;
the motion completion degree is used for monitoring the motion angle under special conditions, and the average value of a certain special motion completion degree is used as a reference.
Preferably, in step 2, a color picture is obtained at 30 frames per second, and a depth value Z of a skeletal point of a human body contained in each frame of picture is obtained by combining the depth image of each frame i Where i represents the subscript of the different bone points and stores the information in a storage medium ready for processing.
Preferably, in step 3, the simplified three-dimensional angle measurement method used is based on the plane in which the motion is located, the selected planes being named horizontal, sagittal and coronal according to the position, respectively; projecting a bone point and associated bone edge moving parallel to a plane in which the movement is to be performed, i.e. three-dimensional coordinate information into the plane in which the movement is to be performed, the x-axis coordinates having no effect when located on the coronal plane, is reduced to (0, y) 2 ,z 2 )。
Preferably, the plane position is determined by the position of the human body, and the horizontal plane is the ground; the sagittal plane contains the human spine line, is vertical to the horizontal plane, and the internal points are only changed by the Z-axis coordinate; the coronal plane is a plane perpendicular to the horizontal plane and sagittal plane, and parallel to the human body.
Preferably, in step 4, the proposed method for measuring and calculating the offset distance based on depth when the person stands is to establish an equal depth value plane with equal depth values but arbitrary x-coordinate and y-coordinate with respect to the ankle standing position distance in any specified measurement area, and to determine whether the other joint points are moved forward or backward by how much based on the equal depth value plane.
Preferably, in step 5, the proposed arbitrary defined measurement region is realized by limiting the maximum, minimum value of the depth values, which is 4 meters, and the minimum value is 2 meters.
Preferably, in step 6, the special scoring step adopts the proportion of the average joint activity in the whole flow calculated by the special exercise to the target activity to score, and if the average joint activity exceeds 70%, the average joint activity is considered to reach the standard.
The invention also provides a depth camera-based functional motion analysis system, which comprises:
the image acquisition module is used for acquiring multi-frame color images and auxiliary depth images;
the picture processing module is connected with the skeleton points and used for acquiring three-dimensional coordinate information and depth information of the points;
the logic calculation module comprises a logic module which is favorable for completing the executable command and is used for completing the calculation of the angle and the distance and judging the motion completion degree according to the angle;
the area selection module is used for judging the detected area and eliminating errors;
and the simulation scoring module comprises executable commands which are beneficial to completing the step 5 and is used for simulating and evaluating the motion state.
Preferably, the following functions can be implemented by using the above modules, including:
the body posture evaluation test function is used for reflecting the change of the body in real time and can freely move;
the functional balance analysis function is used for reflecting related motion data such as shaking degree and offset under the support of a single foot in real time and judging whether the standard is met;
the motion angle monitoring function under special conditions is used for showing the scoring condition of special functional motions such as shoulder abduction and elbow buckling.
The invention also provides a computer storage medium which stores the recorded picture and video information from the beginning of the movement to the end of the movement, all data related to the operation and executable instructions for realizing the steps 1 to 6, wherein the executable instructions are realized by a computer.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention has the functions of body posture evaluation test, functional balance analysis, movement angle monitoring under special conditions and the like; the non-contact measurement demand data is completely adopted, so that the safety is ensured; and the three-dimensional information is converted into two-dimensional information, so that the efficiency of calculating the technical indexes is improved.
2. The invention has independent scoring algorithm, scores all functional exercises, and guides the scientific development of subsequent training.
3. The invention can automatically debug, screen the checked personnel in the specified measuring area and improve the accuracy of the measuring index.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic view of a model of a human skeletal joint obtained in the present invention;
FIG. 3 is a schematic view of a three-dimensional reference surface proposed in the present invention;
FIG. 4 is a schematic diagram of a method for measuring and calculating angles of conversion dimensions according to the present invention (taking a left arm and a sagittal plane as an example);
fig. 5 is a schematic diagram of a depth-based offset distance measurement method according to the present invention.
Detailed Description
The following technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings, so that those skilled in the art can better understand the advantages and features of the present invention, and thus the protection scope of the present invention is more clearly defined. The described embodiments of the present invention are intended to be only a few, but not all embodiments of the present invention, and all other embodiments that may be made by one of ordinary skill in the art without inventive faculty are intended to be within the scope of the present invention.
As shown in fig. 1, a depth camera-based functional motion analysis method specifically includes the following steps:
step 1: setting a depth camera at a higher position, enabling a person to be tested to face the camera in the forward direction, ensuring that pictures in the depth camera can shoot the whole body and the ground touched by feet, and waiting for a command from a server;
step 2: receiving a command and determining a function; acquiring multi-frame depth pictures and color pictures by using a depth camera; acquiring 16 skeletal key points of a human body, and acquiring depth information to form a three-dimensional coordinate;
wherein the acquisition of the three-dimensional coordinate information is acquired based on a three-dimensional coordinate system of the depth camera. The origin O of the three-dimensional coordinate system is located at the center of the camera, the X-axis is parallel to the ground plane, the Y-axis is perpendicular to the ground plane, and the Z-axis is a plane formed by XOY.
Step 3: and connecting the skeleton points, simplifying three-dimensional coordinate information in the depth space, and performing angle calculation.
As shown in fig. 2, the bone points are logically connected, and for the sake of calculation, the connection lines of the bone points are all represented by three-dimensional vectors with arrows; extracting the joint skeleton point to be measured and other two joint point information related to the joint skeleton point to be measured to obtain three-dimensional coordinate information A (x 1 ,y 1 ,z 1 )，B(x 2 ,y 2 ,z 2 )，C(x 3 ,y 3 ,z 3 )。
Step 4: measuring and calculating the distance by moving the human body forwards and backwards at regular time based on the depth information;
the distance measurement is obtained by evaluating a human body in standing, utilizing depth value information of bone points and using the depth-based offset distance measurement method provided by the invention.
Step 5: setting a threshold value of an active area, and eliminating interference of other people;
in order to realize accurate measurement and calculation, only single skeleton points are detected, and the interference of other people is eliminated by selecting the depth value of the body center of the measured person and setting the upper depth limit and the lower depth limit based on the depth value, so that the detection is ensured to only occur in any specified measuring area.
Step 6: measuring the degree of completion of the special exercise and grading;
the motion completion degree is mainly applied to motion angle monitoring under special conditions. Taking the average value of the completion degree of a specific movement as a reference.
Wherein, a color picture is acquired by 30 frames per second,combining the depth image of each frame to obtain a depth value Z of a skeleton point of the human body contained in each frame of picture i Where i represents the subscript of the different bone points and stores the information in a storage medium ready for processing.
As shown in fig. 3, the simplified three-dimensional angle measurement method used in step 3 is based on the plane in which the motion is located, and the selected planes are named horizontal, sagittal and coronal planes, respectively, according to the position. As shown in fig. 4, the bone points and associated bone edges moving parallel to a certain plane are projected onto the parallel plane, i.e. three-dimensional coordinate information is projected into the plane in which the movement is performed, in which when the left arm is to be bent upwards, it is projected into the sagittal plane, and the x-axis coordinate has no effect when it is positioned in the coronal plane, and is abbreviated as a' (0, y 1 ,z 1 )，B'(0,y 2 ,z 2 )，C'(0,y 3 ,z 3 ). Likewise, the coronal plane is not considered the z-axis and is (x, y, 0), and the horizontal plane is not considered the y-axis and is (x, 0, z).
The plane position is determined by the position of the human body, and the horizontal plane is the ground; the sagittal plane contains the human spine line, is vertical to the horizontal plane, and the internal points are only changed by the Z-axis coordinate; the coronal plane is a plane perpendicular to the horizontal plane and sagittal plane, and parallel to the human body.
As shown in fig. 5, the method for measuring and calculating the offset distance based on depth at the time of standing human body in step 4 is that, in an arbitrary predetermined measuring area, an equal depth value plane with equal depth values and arbitrary x-coordinate and y-coordinate is established with respect to the ankle standing position distance, and whether other joint points move forward or backward is judged by taking the equal depth value plane as a reference, and the ankle point with smaller depth value is taken as a reference depth Z 0 Depth Z of shoulders A 、Z B Higher, then the reference depth needs to be subtracted to give the distances Z A -Z 0 、Z B -Z 0 The method comprises the steps of carrying out a first treatment on the surface of the The left wrist is relatively forward, and a reference depth is needed to be added to obtain the distance Z C -Z 0 。
The arbitrary specified measurement area proposed in step 6 is realized by limiting the maximum and minimum values of the depth values, wherein the maximum value is 4 meters, and the minimum value is 2 meters.
The special scoring link adopts the proportion of the average joint activity in the whole flow calculated by the special movement to the target activity to score, and the average joint activity is considered to reach the standard if the average joint activity exceeds 70%.
A depth camera based functional motion analysis system, comprising:
the image acquisition module is used for acquiring multi-frame color images and auxiliary depth images;
the picture processing module is connected with the skeleton points and used for acquiring three-dimensional coordinate information and depth information of the points;
the logic calculation module comprises a logic module which is favorable for completing the executable command and is used for completing the calculation of the angle and the distance and judging the motion completion degree according to the angle;
the area selection module is used for judging the detected area and eliminating errors;
and the simulation scoring module comprises executable commands which are beneficial to completing the step 5 and is used for simulating and evaluating the motion state.
Specifically, the invention adopts the modules to realize the following functions, including:
the body posture evaluation test function is used for reflecting the change of the body in real time and can freely move;
the functional balance analysis function is used for reflecting related motion data such as shaking degree and offset under the support of a single foot in real time and judging whether the standard is met;
the motion angle monitoring function under special conditions is used for showing the scoring condition of special functional motions such as shoulder abduction and elbow buckling.
A computer storage medium storing pictures and video information recorded from the beginning of the movement to the end of the movement, and all data relating to the operations and executable instructions for implementing the above steps 1 to 6, the executable instructions being implemented by a computer.
In conclusion, the invention has the functions of body posture evaluation test, functional balance analysis, movement angle monitoring under special conditions and the like; the non-contact measurement demand data is completely adopted, so that the safety is ensured; the three-dimensional information is converted into two-dimensional information, so that the efficiency of calculating the technical indexes is improved; the method has an independent scoring algorithm, scores all functional exercises, and guides the scientific development of subsequent training; the system can automatically debug, screen the checked personnel in the specified measurement area, and improve the accuracy of measurement indexes.
The description and practice of the invention disclosed herein will be readily apparent to those skilled in the art, and may be modified and adapted in several ways without departing from the principles of the invention. Accordingly, modifications or improvements may be made without departing from the spirit of the invention and are also to be considered within the scope of the invention.
Claims (3)
1. The functional motion analysis method based on the depth camera is characterized by comprising the following specific steps:
step 1: setting a depth camera at a certain height position, enabling a person to be tested to face the camera in the forward direction, ensuring that pictures in the depth camera can shoot the whole body and the ground touched by feet, and waiting for a command from a server;
step 2: receiving a command and determining a function, and acquiring multi-frame depth pictures and color pictures by using a depth camera; acquiring 16 skeletal key points of a human body, and acquiring depth information to form a three-dimensional coordinate;
the three-dimensional coordinate information is acquired based on a three-dimensional coordinate system of the depth camera, an origin O of the three-dimensional coordinate system is positioned at the center of the camera, an X axis is parallel to a ground plane, a Y axis is perpendicular to the ground plane, and a Z axis is a plane formed by being perpendicular to XOY;
step 3: connecting skeleton points, simplifying three-dimensional coordinate information in a depth space, and calculating angles;
the bone points are logically connected, and the joint bone points to be measured and other two joint point information related to the joint bone points are extracted to obtain three-dimensional coordinate information (x 1 ,y 1 ,z 1 ) Information simplification is carried out, and angles are calculated based on the newly simplified coordinates;
step 4: measuring and calculating the front and back movement of the standing and timing human body based on the depth information of the skeleton points, and measuring and calculating the distance;
the distance measurement is carried out by evaluating the human body in standing, and is obtained by utilizing the depth value information of the bone points and using a depth-based offset distance measurement method;
step 5: setting a threshold value of an active area, and eliminating interference of other people;
the step of eliminating interference of other people is to select a depth value of the body center of a person to be measured and set a depth upper limit and a depth lower limit based on the depth value, so that detection is ensured to only occur in any specified measuring area;
step 6: measuring the degree of completion of the special exercise and grading;
the motion completion degree is applied to motion angle monitoring under special conditions, and an average value of a certain special motion completion degree is used as a reference;
in step 2, a color picture is obtained at 30 frames per second, and a depth value Z of a skeletal point of a human body contained in each frame of picture is obtained by combining the depth image of each frame i Wherein i represents subscripts of different skeletal points, and stores information in a storage medium for preparation;
in step 3, the simplified three-dimensional angle measurement method is proposed based on the plane in which the motion is located, and the selected planes are respectively named as horizontal planes, sagittal planes and coronal planes according to the positions; projecting a bone point and associated bone edge moving parallel to a plane in which the movement is to be performed, i.e. three-dimensional coordinate information into the plane in which the movement is to be performed, the x-axis coordinates having no effect when located on the coronal plane, is reduced to (0, y) 2 ,z 2 )；
The plane position is determined by the position of a human body, and the horizontal plane is the ground; the sagittal plane contains the human spine line, is vertical to the horizontal plane, and the internal points are only changed by the Z-axis coordinate; the coronal plane is a plane perpendicular to the horizontal plane and the sagittal plane and parallel to the human body;
in step 4, the proposed method for measuring and calculating the offset distance based on depth when the human body stands is that, in any specified measuring area, an equal depth value surface with equal depth values and arbitrary x coordinate and y coordinate is established relative to the ankle standing position distance, and whether other joint points move forwards or backwards or not is judged by taking the equal depth value surface as a reference;
in step 5, the proposed arbitrary specified measurement area is realized by limiting the maximum value and the minimum value of the depth value, wherein the maximum value is 4 meters, and the minimum value is 2 meters;
in step 6, the special scoring link adopts the proportion of the average joint activity in the whole flow calculated by the special movement to the target activity to score, and if the average joint activity exceeds 70%, the standard is determined.
2. A depth camera based functional motion analysis system, comprising:
the image acquisition module is used for acquiring multi-frame color images and auxiliary depth images;
the picture processing module is connected with the skeleton points and used for acquiring three-dimensional coordinate information and depth information of the points;
a logic calculation module comprising executable instructions for facilitating completion of the calculation of the angle and distance according to claim 1, while determining the degree of completion of the movement according to the angle;
the area selection module is used for judging the detected area and eliminating errors;
a simulation scoring module comprising executable instructions for facilitating the completion of step 5 of claim 1 for simulating the assessment of the state of motion.
3. A computer storage medium storing pictures, video information recorded from the beginning of the movement to the end of the movement, and all data relating to the operations and executable instructions for implementing steps 1 to 6 of claim 1, the executable instructions being implemented by a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249317.8A CN116309712B (en) | 2023-03-15 | 2023-03-15 | Functional motion analysis system and method based on depth camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249317.8A CN116309712B (en) | 2023-03-15 | 2023-03-15 | Functional motion analysis system and method based on depth camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116309712A CN116309712A (en) | 2023-06-23 |
| CN116309712B true CN116309712B (en) | 2024-01-30 |
Family
ID=86779237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310249317.8A Active CN116309712B (en) | 2023-03-15 | 2023-03-15 | Functional motion analysis system and method based on depth camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309712B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263720A (en) * | 2019-06-21 | 2019-09-20 | 中国民航大学 | Action identification method based on depth image and bone information |
| CN110969114A (en) * | 2019-11-28 | 2020-04-07 | 四川省骨科医院 | Human body action function detection system, detection method and detector |
| CN112818800A (en) * | 2021-01-26 | 2021-05-18 | 中国人民解放军火箭军工程大学 | Physical exercise evaluation method and system based on human skeleton point depth image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI521469B (en) * | 2012-06-27 | 2016-02-11 | Reallusion Inc | Two - dimensional Roles Representation of Three - dimensional Action System and Method |
-
2023
- 2023-03-15 CN CN202310249317.8A patent/CN116309712B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263720A (en) * | 2019-06-21 | 2019-09-20 | 中国民航大学 | Action identification method based on depth image and bone information |
| CN110969114A (en) * | 2019-11-28 | 2020-04-07 | 四川省骨科医院 | Human body action function detection system, detection method and detector |
| CN112818800A (en) * | 2021-01-26 | 2021-05-18 | 中国人民解放军火箭军工程大学 | Physical exercise evaluation method and system based on human skeleton point depth image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116309712A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4136859B2 (en) | Position and orientation measurement method | |
| US9898651B2 (en) | Upper-body skeleton extraction from depth maps | |
| JP5388932B2 (en) | Information processing apparatus and control method thereof | |
| KR101738569B1 (en) | Method and system for gesture recognition | |
| US7671875B2 (en) | Information processing method and apparatus | |
| CN110913751B (en) | Wearable eye tracking system with slip detection and correction functions | |
| US20050182341A1 (en) | Posture diagnosis equipment and program therefor | |
| KR101930652B1 (en) | Gait analysis system and computer program recorded on recording medium | |
| US20180153445A1 (en) | Measurement device and measurement method | |
| JP4898464B2 (en) | Information processing apparatus and method | |
| US20220092302A1 (en) | Skeleton recognition method, computer-readable recording medium storing skeleton recognition program, skeleton recognition system, learning method, computer-readable recording medium storing learning program, and learning device | |
| CN111012353A (en) | Height detection method based on face key point recognition | |
| KR20140003265A (en) | Method for measuring movement angle of joint | |
| CN109242887A (en) | A kind of real-time body's upper limks movements method for catching based on multiple-camera and IMU | |
| JP2021105887A (en) | Three-dimensional pose obtaining method and device | |
| CN114712769A (en) | Standing long jump intelligent distance measuring method and system based on computer vision | |
| CN110477921B (en) | Height measurement method based on skeleton broken line Ridge regression | |
| Lim et al. | Camera-based hand tracking using a mirror-based multi-view setup | |
| CN116309712B (en) | Functional motion analysis system and method based on depth camera | |
| CN109740458B (en) | Method and system for measuring physical characteristics based on video processing | |
| CN116369906A (en) | Automatic testing method, device, equipment and medium for arm bending suspension | |
| CN115331304A (en) | Running identification method | |
| CN115105062A (en) | Hip and knee joint coordination evaluation method, device and system and storage medium | |
| JP2014117409A (en) | Method and apparatus for measuring body joint position | |
| TW201510939A (en) | Dynamic image analyzing system and operating method thereof |
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 |