CN110897611A - Eye-closing single-foot standing detection method based on deep learning - Google Patents
Eye-closing single-foot standing detection method based on deep learning Download PDFInfo
- Publication number
- CN110897611A CN110897611A CN201911283594.0A CN201911283594A CN110897611A CN 110897611 A CN110897611 A CN 110897611A CN 201911283594 A CN201911283594 A CN 201911283594A CN 110897611 A CN110897611 A CN 110897611A
- Authority
- CN
- China
- Prior art keywords
- foot
- human body
- eye
- standing
- closed
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4005—Detecting, measuring or recording for evaluating the nervous system for evaluating the sensory system
- A61B5/4023—Evaluating sense of balance
-
- 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
- A61B5/1116—Determining posture transitions
-
- 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
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
Abstract
The invention relates to a closed-eye single-foot standing detection method based on deep learning, which comprises the following steps: s1: training a human skeleton key point detection model and an eye closing detection model; s2: arranging a camera device at a position where key points of legs and eyes of a human body can be detected; s3: starting a camera device, shooting a human body, acquiring video frames, and respectively inputting each video frame into a human body skeleton key point detection model and a closed eye detection model; s4: judging whether the human body stands on one foot or not through the human skeleton key point detection model, and judging whether the human body is eye-closed or not through the eye-closing detection model; when a human body stands on one foot and closes eyes, timing is started; s5: when the posture of the human body does not satisfy any one of standing on a single foot, unmoving of the standing foot and eye closing, ending the detection, stopping timing and recording the total time; s6: and obtaining the total standing time of the single foot with the closed eyes through the camera device. The method solves the problems of low detection precision and inconvenient detection of the existing detection method.
Description
Technical Field
The invention relates to a detection method based on deep learning, in particular to a closed-eye single-foot standing detection method based on deep learning.
Background
The eye-closed single-foot standing is to measure the time of the body gravity center on the single-foot supporting surface by means of the coordinated movement of the balance receptors of the brain vestibular organ and the muscles of the whole body of the human body without any visual reference object so as to reflect the strength of the balance force. The eye-closing one-foot standing is an important reflection of the physical quality of people, especially the physical quality of middle-aged and old people. The eyes closed and one foot standing can not only exercise the flexibility and the balance ability of the human body, but also promote the development of the left and right brains, adjust the mood and calm the mind. Therefore, it is quite urgent to design a method for measuring the standing time of the eye-closed single foot, which is simple, fast and accurate.
In the conventional test method, manual testing is required. That is, manual timing was started when the tester was standing on one foot and in a closed-eye state, and was considered to be ended when the lifted foot was down or the eyes were open. The adoption of the testing method has the problems of low efficiency and low data accuracy, and the adoption of a manual testing mode causes great obstacles to large-scale testing.
Disclosure of Invention
The invention provides a closed-eye single-foot standing detection method based on deep learning, and solves the problems of inconvenient measurement of closed-eye single-foot standing time and inaccurate result.
The invention is realized by the following technical scheme:
a closed-eye single-foot standing detection method based on deep learning comprises the following steps:
s1: training a human skeleton key point detection model and a closed eye detection model based on deep learning;
s2: arranging a camera device at a position where key points of legs and eyes of a human body can be detected;
s3: starting a camera device, shooting a human body, acquiring video frames, and respectively inputting each video frame into a human body skeleton key point detection model and a closed eye detection model;
s4: judging whether the human body stands on one foot or not through the human skeleton key point detection model, and judging whether the human body is eye-closed or not through the eye-closing detection model; when the human body stands on one foot and closes the eyes, timing is started, and the step S5 is carried out; otherwise, continuously judging whether the human body stands on one foot and closes the eyes;
s5: continuously detecting video frames acquired by the camera device, judging whether the human body stands on one foot or not through a human skeleton key point detection model, and judging whether the human body is eye-closed or not through an eye-closing detection model; when the posture of the human body does not satisfy any one of standing on a single foot, unmoving of the standing foot and eye closing, ending the detection, stopping timing and recording the total time; otherwise, continuing timing and continuously detecting the video frames acquired by the camera device;
s6: obtaining the total standing time of the closed-eye single foot through a camera device;
the human skeleton key point detection model is obtained based on an OpenPose model and through deep learning framework TensorFlow training; the closed-eye detection model is obtained through deep learning framework TensorFlow training;
step S2, the image capturing device is disposed right in front of the human body and can capture the entire human body;
the key points of the human leg comprise a hip joint, a knee joint and an ankle joint of the human body;
in the technical scheme, the human skeleton key point detection model is based on an OpenPose model and is obtained through deep learning framework TensorFlow training, key points of human legs can be effectively identified, the human skeleton key point detection model mainly comprises hip joints, knee joints and ankle joints of a human body, and the human skeleton key point detection model obtained through deep learning framework TensorFlow training can quickly detect the position relation among all key points of the human legs, so that whether a human body stands on one foot or not and whether a standing foot moves or not can be quickly judged; the closed eye detection model is obtained through a deep learning framework TensorFlow learning through a large number of human body closed eye training sets or human body open eye training sets; therefore, when the video frame is acquired from the camera device, whether the human body closes the eyes can be quickly judged; the camera device is arranged right in front of the human body, so that the camera device can better shoot the leg postures and the eye postures of the human body, and the shot video frames are subjected to single-foot standing judgment and closed-eye judgment through the human skeleton key point detection model obtained through the training; when the human body is judged to be standing on one foot and closing eyes through the two models, starting testing, recording the time for standing on one foot and closing eyes of the human body, and finishing the testing when the posture of the human body does not satisfy any one of standing on one foot, unmoving of the standing foot and closing eyes, so as to obtain the total time for standing on one foot and closing eyes of the human body; through this technical scheme, the gesture or the closed eye gesture of standing of human single foot that can be accurate carry out quick discernment to reach the purpose of accurate, the human closed eye single foot total time of standing of record fast, simultaneously, just can realize whole testing process, convenient and fast through simple camera device.
As a further improvement of the invention, the camera device is an intelligent terminal with a camera;
in the technical scheme, the camera device adopts an intelligent terminal with a camera to acquire a video frame of a human body through the camera, and guides a trained human skeleton key point detection model and a trained closed-eye detection model into the intelligent terminal, and then judges whether the person stands on one foot with closed eyes according to the video frame of the human body; through the cooperation of two training models and intelligent terminal, can discern whether human closed eye, single foot stand and whether the foot of standing remove fast to the time of human closed eye single foot stand of record that can be accurate.
Further, in step S4, the human skeleton key point detection model identifies specific positions of a hip joint, a knee joint and an ankle joint of the human body through a video frame acquired by the camera device, and identifies whether the human body is in a single-foot standing state according to an included angle formed between a connection line formed by the hip joint and the knee joint and a connection line formed by the knee joint and the ankle joint;
in the technical scheme, because the hip joint, the knee joint and the ankle joint of the human body are parts with more characteristic points of the legs of the human body, the detection model of the key points of the bones of the human body is favorable for detecting the specific leg postures of the human body, and then whether the shanks of the human body are lifted up or not is judged according to the included angle formed between the connecting line formed by the hip joint and the knee joint and the connecting line formed by the knee joint and the ankle joint, so that whether the human body stands on one foot or not is judged.
Further, in step S5, the human skeleton key point detection model identifies the specific position of the human ankle joint through the frequency frame acquired by the camera device, records the specific position of the human ankle joint through the video frame, if the relative displacement between the specific position of the human ankle joint in the first frame of a segment of continuous frames and the last frame is greater than a set threshold, it is determined that the human standing foot has moved, otherwise, the next continuous frame is acquired in a sliding window manner, and the above determination process is repeated;
in the technical scheme, a section of continuous video frames are obtained through a camera device, if the relative displacement between the specific position of the ankle joint of the human body in the first frame of the video frames and the last frame is larger than a set threshold value, the fact that the standing foot of the human body moves is judged, otherwise, the set frame number is backwards slid in time sequence through a sliding window, a second continuous video frame is obtained, and the judging process is repeated until the timing is stopped.
Further, the case where the posture of the human body in step S5 does not satisfy any of standing on one foot, standing on foot not moving, and eye closing refers to the case where the human body is determined to be in the non-standing on one foot state by the human skeleton key point detection model, or the case where the human body is determined to be in the standing on foot movement by the human skeleton key point detection model, or the case where the human body is determined to be in the non-eye closing state by the eye closing detection model.
In conclusion, the human body eye-closing single-foot standing time can be judged quickly and accurately by training the human body skeleton key point detection model and the eye-closing detection model, guiding the camera device, arranging the camera device at the position where the key points of the legs and the eyes of the human body can be detected, and acquiring the video frame of the human body through the camera device; the invention makes up the problems of low detection precision and inconvenient detection of the traditional detection method.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1:
as shown in fig. 1, a method for detecting closed-eye and single-foot standing based on deep learning includes the steps of:
s1: training a human skeleton key point detection model and a closed eye detection model based on deep learning;
s2: arranging a camera device at a position where key points of legs and eyes of a human body can be detected;
s3: starting a camera device, shooting a human body, acquiring video frames, and respectively inputting each video frame into a human body skeleton key point detection model and a closed eye detection model;
s4: judging whether the human body stands on one foot or not through the human skeleton key point detection model, and judging whether the human body is eye-closed or not through the eye-closing detection model; when the human body stands on one foot and closes the eyes, timing is started, and the step S5 is carried out; otherwise, continuously judging whether the human body stands on one foot and closes the eyes;
s5: continuously detecting video frames acquired by the camera device, judging whether the human body stands on one foot or not through a human skeleton key point detection model, and judging whether the human body is eye-closed or not through an eye-closing detection model; when the posture of the human body does not satisfy any one of standing on a single foot, unmoving of the standing foot and eye closing, ending the detection, stopping timing and recording the total time; otherwise, continuing timing and continuously detecting the video frames acquired by the camera device;
s6: obtaining the total standing time of the closed-eye single foot through a camera device;
the human skeleton key point detection model is obtained based on an OpenPose model and through deep learning framework TensorFlow training; the closed-eye detection model is obtained through deep learning framework TensorFlow training;
step S2, the image capturing device is disposed right in front of the human body and can capture the entire human body;
the key points of the human leg comprise a hip joint, a knee joint and an ankle joint of the human body;
the human skeleton key point detection model is based on an OpenPose model and is obtained through deep learning framework TensorFlow training, key points of human legs can be effectively identified, the human skeleton key point detection model mainly comprises hip joints, knee joints and ankle joints of the human body, and the human skeleton key point detection model obtained through deep learning framework TensorFlow training can quickly detect the position relation among all key points of the human legs, so that whether a person stands on one foot or not and whether the standing foot moves or not can be quickly judged; the closed eye detection model is obtained through a deep learning framework TensorFlow learning through a large number of human body closed eye training sets or human body open eye training sets; therefore, when the video frame is acquired from the camera device, whether the human body closes the eyes can be quickly judged; the camera device is arranged right in front of the human body, so that the camera device can better shoot the leg postures and the eye postures of the human body, and the shot video frames are subjected to single-foot standing judgment and closed-eye judgment through the human skeleton key point detection model obtained through the training; when the human body is judged to be standing on one foot and closing eyes through the two models, starting testing, recording the time for standing on one foot and closing eyes of the human body, and finishing the testing when the posture of the human body does not satisfy any one of standing on one foot, unmoving of the standing foot and closing eyes, so as to obtain the total time for standing on one foot and closing eyes of the human body; through this technical scheme, the gesture or the closed eye gesture of standing of human single foot that can be accurate carry out quick discernment to reach the purpose of accurate, the human closed eye single foot total time of standing of record fast, simultaneously, just can realize whole testing process, convenient and fast through simple camera device.
The camera device is an intelligent terminal with a camera; the camera device adopts an intelligent terminal with a camera to acquire a video frame of a human body through the camera, and guides a trained human skeleton key point detection model and a trained closed-eye detection model into the intelligent terminal, and then judges whether the human body stands on one foot in a closed-eye manner according to the video frame of the human body; through the cooperation of two training models and intelligent terminal, can discern whether human closed eye, single foot stand and whether the foot of standing remove fast to the time of human closed eye single foot stand of record that can be accurate.
In step S4, the human skeleton key point detection model identifies the specific positions of the hip joint, the knee joint and the ankle joint of the human body through the video frame acquired by the camera device, and identifies whether the human body is in a single-foot standing state according to the included angle formed between the connecting line formed by the hip joint and the knee joint and the connecting line formed by the knee joint and the ankle joint;
as the hip joint, the knee joint and the ankle joint of the human body are parts with more characteristic points of the human leg, the detection model of the key points of the human skeleton is favorable for detecting the specific leg posture of the human body, and then whether the human shank is lifted up or not is judged according to the included angle formed between the connecting line formed by the hip joint and the knee joint and the connecting line formed by the knee joint and the ankle joint, and then whether the human body stands on one foot or not is judged.
In step S5, the human skeleton key point detection model identifies the specific position of the human ankle joint through the frequency frame acquired by the camera device, records the specific position of the human ankle joint through the video frame, determines that the standing foot of the human body moves if the relative displacement between the specific position of the human ankle joint in the first frame of a segment of continuous frames and the last frame is greater than a set threshold, otherwise, acquires the next continuous frame in a sliding window manner, and repeats the above determination process;
acquiring a section of continuous video frames through a camera device, judging that the standing foot of the human body moves if the relative displacement between the specific position of the ankle joint of the human body in the first frame of the video frames and the last frame is larger than a set threshold value, otherwise, sliding the set frame number backwards in time sequence through a sliding window to acquire a second continuous video frame, and repeating the judging process until the timing is stopped.
When the posture of the human body in the step S5 does not satisfy any of standing on one foot, unmoving of a standing foot, and eye closing, it is determined that the human body is in a non-standing on one foot state through the human skeleton key point detection model, or that the standing foot of the human body is moving through the human skeleton key point detection model, or that the human body is in a non-eye closing state through the eye closing detection model.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (8)
1. A closed-eye single-foot standing detection method based on deep learning is characterized by comprising the following steps:
s1: training a human skeleton key point detection model and a closed eye detection model based on deep learning;
s2: arranging a camera device at a position where key points of legs and eyes of a human body can be detected;
s3: starting a camera device, shooting a human body, acquiring video frames, and respectively inputting each video frame into a human body skeleton key point detection model and a closed eye detection model;
s4: judging whether the human body stands on one foot or not through the human skeleton key point detection model, and judging whether the human body is eye-closed or not through the eye-closing detection model; when the human body stands on one foot and closes the eyes, timing is started, and the step S5 is carried out; otherwise, continuously judging whether the human body stands on one foot and closes the eyes;
s5: continuously detecting video frames acquired by the camera device, judging whether a human body stands on one foot or not and whether the standing foot moves or not through the human body skeleton key point detection model, and judging whether the human body is eye-closed or not through the eye-closing detection model; when the posture of the human body does not satisfy any one of standing on a single foot, unmoving of the standing foot and eye closing, ending the detection, stopping timing and recording the total time; otherwise, continuing timing and continuously detecting the video frames acquired by the camera device;
s6: and obtaining the total standing time of the single foot with the closed eyes through the camera device.
2. The method for detecting the closed-eye and single-foot standing based on the deep learning of claim 1, wherein the human skeleton key point detection model is based on an openpos model and is trained by a deep learning framework tensrflow; the closed-eye detection model is obtained through deep learning framework TensorFlow training.
3. The method for detecting the closed-eye and single-foot standing based on the deep learning of claim 1, wherein the step S2 is to arrange an image capturing device right in front of the human body, and the image capturing device can capture the whole human body.
4. The method for detecting the closed-eye and single-foot standing based on the deep learning of claim 1, wherein the key points of the human leg comprise a hip joint, a knee joint and an ankle joint of the human body.
5. The method for detecting the closed-eye and single-foot standing based on the deep learning of claim 1, wherein the camera device is an intelligent terminal with a camera.
6. The method for detecting closed-eye and single-foot standing based on deep learning of claim 1, wherein in step S4, the human skeleton key point detection model identifies specific positions of a hip joint, a knee joint and an ankle joint of the human body through a video frame obtained by a camera device, and identifies whether the human body is in a single-foot standing state according to an included angle formed between a connection line formed by the hip joint and the knee joint and a connection line formed by the knee joint and the ankle joint.
7. The method for detecting the closed-eye and single-foot standing based on the deep learning of claim 1, wherein in step S5, the human skeleton key point detection model identifies the specific position of the human ankle joint through the video frames obtained by the camera device, records the specific position of the human ankle joint in the consecutive frames, and determines that the human standing foot moves if the relative displacement between the specific position of the human ankle joint in the first frame of a segment of consecutive frames and the last frame is greater than a predetermined threshold, otherwise, obtains the next consecutive frame in a sliding window manner, and repeats the above determination process.
8. The method for detecting the closed-eye and single-foot standing based on the deep learning of claim 1, wherein the gesture of the human body in the step S5 does not satisfy any one of standing on one foot, standing on foot not moving and closed-eye, which means that the human body is determined to be in the non-standing state by the human skeleton key point detection model, or the standing foot moving is determined by the human skeleton key point detection model, or the human body is determined to be in the non-closed-eye state by the closed-eye detection model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911283594.0A CN110897611A (en) | 2019-12-13 | 2019-12-13 | Eye-closing single-foot standing detection method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911283594.0A CN110897611A (en) | 2019-12-13 | 2019-12-13 | Eye-closing single-foot standing detection method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110897611A true CN110897611A (en) | 2020-03-24 |
Family
ID=69824392
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911283594.0A Pending CN110897611A (en) | 2019-12-13 | 2019-12-13 | Eye-closing single-foot standing detection method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110897611A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116509333A (en) * | 2023-05-20 | 2023-08-01 | 中国医学科学院阜外医院 | Human body balance capability assessment method, system and equipment based on binocular image |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104688237A (en) * | 2015-02-11 | 2015-06-10 | 深圳泰山在线科技有限公司 | Time measuring method and system for physique test |
CN105956549A (en) * | 2016-04-28 | 2016-09-21 | 江苏大学 | Worker pre-job safety equipment and behavior capability inspection system and method |
CN108078564A (en) * | 2017-01-11 | 2018-05-29 | 浙江师范大学 | A kind of equilibrant force appraisal procedure based on brain wave signal measurement |
CN108960071A (en) * | 2018-06-06 | 2018-12-07 | 武汉幻视智能科技有限公司 | A kind of eye opening closed-eye state detection method |
CN109199324A (en) * | 2017-06-30 | 2019-01-15 | 深圳泰山体育科技股份有限公司 | Based on optical measurement method and the system of standing on one leg of closing one's eyes |
CN109480856A (en) * | 2018-12-29 | 2019-03-19 | 中国科学院合肥物质科学研究院 | Human body static balancing capability comparison system and method based on multistation appearance |
CN109784149A (en) * | 2018-12-06 | 2019-05-21 | 北京飞搜科技有限公司 | A kind of detection method and system of skeleton key point |
-
2019
- 2019-12-13 CN CN201911283594.0A patent/CN110897611A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104688237A (en) * | 2015-02-11 | 2015-06-10 | 深圳泰山在线科技有限公司 | Time measuring method and system for physique test |
CN105956549A (en) * | 2016-04-28 | 2016-09-21 | 江苏大学 | Worker pre-job safety equipment and behavior capability inspection system and method |
CN108078564A (en) * | 2017-01-11 | 2018-05-29 | 浙江师范大学 | A kind of equilibrant force appraisal procedure based on brain wave signal measurement |
CN109199324A (en) * | 2017-06-30 | 2019-01-15 | 深圳泰山体育科技股份有限公司 | Based on optical measurement method and the system of standing on one leg of closing one's eyes |
CN108960071A (en) * | 2018-06-06 | 2018-12-07 | 武汉幻视智能科技有限公司 | A kind of eye opening closed-eye state detection method |
CN109784149A (en) * | 2018-12-06 | 2019-05-21 | 北京飞搜科技有限公司 | A kind of detection method and system of skeleton key point |
CN109480856A (en) * | 2018-12-29 | 2019-03-19 | 中国科学院合肥物质科学研究院 | Human body static balancing capability comparison system and method based on multistation appearance |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116509333A (en) * | 2023-05-20 | 2023-08-01 | 中国医学科学院阜外医院 | Human body balance capability assessment method, system and equipment based on binocular image |
CN116509333B (en) * | 2023-05-20 | 2024-02-02 | 中国医学科学院阜外医院 | Human body balance capability assessment method, system and equipment based on binocular image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111282248A (en) | Pull-up detection system and method based on skeleton and face key points | |
CN103099602B (en) | Based on the physical examinations method and system of optical identification | |
EP3205269A1 (en) | System and method for analyzing gait and postural balance of a person | |
CN113856186B (en) | Pull-up action judging and counting method, system and device | |
CN111401260A (en) | Sit-up test counting method and system based on Quick-OpenPose model | |
CN105944363A (en) | Ultrasonic pull-up tester and control method thereof | |
CN104537670A (en) | Flexibility testing method and system | |
CN104688237B (en) | The time study method and system of physical examinations | |
CN114973401A (en) | Standardized pull-up assessment method based on motion detection and multi-mode learning | |
CN113255622B (en) | System and method for intelligently identifying sit-up action posture completion condition | |
CN110897611A (en) | Eye-closing single-foot standing detection method based on deep learning | |
CN114100103B (en) | Rope skipping counting detection system and method based on key point identification | |
CN113255623B (en) | System and method for intelligently identifying push-up action posture completion condition | |
KR102369359B1 (en) | Image-based intelligent push-up discrimination method and system | |
CN113255624B (en) | System and method for intelligently identifying completion condition of pull-up action gesture | |
CN115068919B (en) | Examination method of horizontal bar project and implementation device thereof | |
KR20170119337A (en) | Apparatus and Method for Processing of Exercise Information | |
KR102425256B1 (en) | Apparatus and Method for Processing of Exercise Information | |
JP5266895B2 (en) | Pulse wave detection device, pulse wave detection program, and pulse wave detection method | |
CN114038054A (en) | Pull-up detection device and method | |
CN111012357A (en) | Seat body forward-bending detection device and method based on image recognition | |
KR20170119335A (en) | Apparatus and Method for Processing of Exercise Information | |
CN106362384A (en) | Pull-up tester and control method thereof | |
KR20230042779A (en) | Image-based intelligent push-up diagnosis method and push-up diagnosis system | |
CN115177927B (en) | Sit-up testing device and detection method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200324 |
|
RJ01 | Rejection of invention patent application after publication |