A balance training system guided by rehabilitation exercise data collection and analysis

Abstract

The present invention relates to the field of rehabilitation training technology, and in particular to a balance training system guided by the collection and analysis of rehabilitation exercise data. The system comprises a console, an acquisition module, and an exercise module. The console is internally provided with acquisition and analysis software, and the acquisition and analysis software comprises a blood oxygen detection unit, a posture detection unit, and a judgment unit. The present invention can effectively solve the problems of existing balance training systems requiring real-time observation by personnel to avoid excessive exercise load on rehabilitation personnel, low intelligence, and poor accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a balance training system guided by rehabilitation exercise data collection and analysis. Background Art

[0002] Balance training systems are devices used in rehabilitation training, but existing balance training systems still have shortcomings. Specifically, existing balance training systems require real-time observation by personnel to avoid excessive exercise load on rehabilitation personnel, have low intelligence levels, and have poor accuracy.

[0003] Therefore, a balance training system guided by rehabilitation exercise data collection and analysis is needed to solve the problems raised in the above background technology. Summary of the Invention

[0004] The purpose of the present invention is to provide a balance training system guided by the collection and analysis of rehabilitation exercise data to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A balance training system guided by rehabilitation exercise data collection and analysis includes a console, an acquisition module, and an exercise module. The console is internally provided with acquisition and analysis software, which includes a blood oxygen detection unit, a posture detection unit, and a judgment unit.

[0007] As a preferred solution of the present invention, the console is electrically connected to the acquisition module through a wire, and multiple groups of acquisition modules are provided.

[0008] As a preferred solution of the present invention, the acquisition module includes various near-infrared muscle oxygen detectors and CMOS cameras, and the exercise module is a treadmill.

[0009] As a preferred embodiment of the present invention, the specific analysis steps of the blood oxygen detection unit are as follows: the acquisition module obtains the light intensity signal of the muscle at a specific position of the subject, and transmits the light intensity signal to the acquisition and analysis software in the console; the blood oxygen detection unit receives the light intensity signal and performs preprocessing, converts the light intensity signal of the λ1 wavelength sensitive to deoxyhemoglobin into the optical density value ODHb of deoxyhemoglobin, and converts the light intensity signal of the λ2 wavelength sensitive to oxyhemoglobin into the optical density value ODHb2 of oxyhemoglobin; calculates the optical density value ratio ODR according to the optical density value ratio formula; statistics and calculations are performed on the optical density value ratios ODR received per unit time; averages the optical density value ratios ODR that increase relative to the previous value per unit time to obtain the increase average value Q; then averages the optical density value ratios that decrease relative to the previous value per unit time to obtain the decrease average value H; and calculates the relative strength index RSI according to the index formula, and inputs the relative strength index RSI into the judgment unit.

[0010] As a preferred solution of the present invention, the specific analysis steps of the posture detection unit are: the acquisition module obtains the motion video image of the athlete and transmits the video data to the acquisition and analysis software in the console; the posture detection unit extracts the human shape area of ​​each frame image from the motion video image, binarizes the extracted human shape area, and segments the binarized human shape area to obtain a binarized human body contour image; motion feature points are extracted from the human body contour in the binarized human body contour image; and the binarized human body contour image and motion feature points are input into the judgment unit.

[0011] As a preferred solution of the present invention, the specific analysis steps of the judgment unit are: the judgment unit compares the input relative strength index RSI with a preset threshold, and compares the input binary human body contour image motion feature points with the input binary human body contour image motion feature points in the previous unit time. If the input relative strength index RSI is lower than the preset threshold, and the proportion of matching motion feature points in the two binary human body contour images exceeds 70%, it indicates that the athlete is in normal rehabilitation training and can continue rehabilitation. If the input relative strength index RSI is higher than the preset threshold, and the proportion of matching motion feature points in the two binary human body contour images is 50%, it indicates that the athlete is in fatigue rehabilitation training and needs to suspend training for rest. If the proportion of matching motion feature points in the two binary human body contour images is between 50% and 70%, it indicates that the athlete's exercise intensity is high and the exercise intensity needs to be reduced before continuing training.

[0012] As a preferred solution of the present invention, the optical density value ratio formula is: The indicator formula is Preprocessing included removing motion artifacts by spline interpolation, removing physiological noise by Butterworth bandpass filtering, and avoiding baseline drift by baseline correction.

[0013] As a preferred solution of the present invention, the specific steps of the motion feature point comparison are: calculating the Euclidean distance between the feature vector of the current motion feature point and the feature vector of the motion feature point in the previous unit time; when the Euclidean distance is less than a preset threshold, determining that the current motion feature point is consistent with the motion feature point in the previous unit time; when the Euclidean distance is greater than the preset threshold, determining that the current motion feature point is inconsistent with the motion feature point in the previous unit time.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] 1. In the present invention, the light intensity signal of the muscle at a specific position of the subject and the motion video image of the athlete are obtained by the acquisition module, and the video data and the light intensity signal are transmitted to the acquisition and analysis software in the console. The blood oxygen detection unit receives the light intensity signal and performs preprocessing, converts the light intensity signal of the λ1 wavelength sensitive to deoxyhemoglobin into the optical density value ODHb of deoxyhemoglobin, and converts the light intensity signal of the λ2 wavelength sensitive to oxyhemoglobin into the optical density value ODHb2 of oxyhemoglobin. The optical density value ratio ODR is calculated according to the optical density value ratio formula, and the optical density value ratios ODR received per unit time are counted and calculated. The optical density value ratios ODR that increase relative to the previous value within the unit time are averaged to obtain the increase average value Q. The optical density value ratios that decrease relative to the previous value within the unit time are averaged to obtain the decrease average value H. The relative strength index RSI is calculated according to the indicator formula, and the relative strength index RS I is input into the judgment unit, the posture detection unit extracts the human shape area of ​​each frame image from the motion video image, binarizes the extracted human shape area, and segments the binarized human shape area to obtain a binarized human body contour image, extracts motion feature points from the human body contour in the binarized human body contour image, and inputs the binarized human body contour image and motion feature points into the judgment unit. The judgment unit compares the input relative strength index RSI with the preset threshold value, and compares the input binarized human body contour image motion feature points with the input binarized human body contour image motion feature points in the previous unit time. If the input relative strength index RS I is lower than the preset threshold value, and the proportion of matching motion feature points in the two binarized human body contour images exceeds 70%, it indicates that the athlete is in normal rehabilitation training and can continue rehabilitation. If the input relative strength index RS If I is higher than the preset threshold and the proportion of matching motion feature points in the two binary human body contour images is 50%, it indicates that the athlete is in fatigue rehabilitation training and needs to pause the training for a rest. If the proportion of matching motion feature points in the two binary human body contour images is between 50% and 70%, it indicates that the athlete's exercise intensity is high and the exercise intensity needs to be reduced before continuing training. The exercise load of rehabilitation personnel can be monitored in real time to avoid excessive exercise load of rehabilitation personnel, with high intelligence and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of the overall hardware structure of the present invention;

[0017] Figure 2 It is a schematic diagram of the system block structure of the present invention.

[0018] In the figure: 1. Control console; 2. Acquisition module; 3. Motion module; 4. Acquisition and analysis software; 5. Blood oxygen detection unit; 6. Posture detection unit; 7. Judgment unit. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] For examples, see Figure 1-2 , the present invention provides a technical solution:

[0021] A balance training system guided by rehabilitation exercise data collection and analysis includes a console 1, an acquisition module 2, and an exercise module 3. The console 1 is internally provided with acquisition and analysis software 4, which includes a blood oxygen detection unit 5, a posture detection unit 6, and a judgment unit 7.

[0022] Furthermore, the console 1 is electrically connected to the acquisition module 2 through a wire, and the acquisition module 2 is provided in multiple groups.

[0023] Furthermore, the acquisition module 2 includes various near-infrared muscle oxygen detectors and CMOS cameras, and the exercise module 3 is a treadmill.

[0024] Furthermore, the specific analysis steps of the blood oxygen detection unit 5 are as follows: the acquisition module 2 obtains the light intensity signal of the muscle at a specific position of the subject, and transmits the light intensity signal to the acquisition and analysis software 4 in the console 1; the blood oxygen detection unit 5 receives the light intensity signal and performs preprocessing, converts the light intensity signal of the λ1 wavelength sensitive to deoxyhemoglobin into the optical density value ODHb of deoxyhemoglobin, and converts the light intensity signal of the λ2 wavelength sensitive to oxyhemoglobin into the optical density value ODHb2 of oxyhemoglobin; calculates the optical density value ratio ODR according to the optical density value ratio formula; statistics and calculations are performed on the optical density value ratios ODR received per unit time; averages the optical density value ratios ODR that increase relative to the previous value per unit time to obtain the average increase Q; then averages the optical density value ratios ODR that decrease relative to the previous value per unit time to obtain the average decrease H; and calculates the relative strength index RSI according to the index formula, and inputs the relative strength index RSI into the judgment unit 7.

[0025] Furthermore, the specific analysis steps of the posture detection unit 6 are as follows: the acquisition module 2 obtains the motion video image of the athlete and transmits the video data to the acquisition and analysis software 4 in the console 1; the posture detection unit 6 extracts the human shape area of ​​each frame image from the motion video image, binarizes the extracted human shape area, and segments the binarized human shape area to obtain a binarized human body contour image; motion feature points are extracted from the human body contour in the binarized human body contour image; and the binarized human body contour image and motion feature points are input into the judgment unit 7.

[0026] Furthermore, the specific analysis steps of the judgment unit 7 are: the judgment unit 7 compares the input relative strength index RS I with the preset threshold, and compares the input binary human body contour image motion feature points with the input binary human body contour image motion feature points in the previous unit time. If the input relative strength index RS I is lower than the preset threshold, and the proportion of matching motion feature points in the two binary human body contour images exceeds 70%, it indicates that the athlete is in normal rehabilitation training and can continue rehabilitation. If the input relative strength index RS I is higher than the preset threshold, and the proportion of matching motion feature points in the two binary human body contour images is 50%, it indicates that the athlete is in fatigue rehabilitation training and needs to suspend training for rest. If the proportion of matching motion feature points in the two binary human body contour images is between 50% and 70%, it indicates that the athlete's exercise intensity is high and the exercise intensity needs to be reduced before continuing training.

[0027] Furthermore, the optical density value ratio formula is The indicator formula is Preprocessing included removing motion artifacts by spline interpolation, removing physiological noise by Butterworth bandpass filtering, and avoiding baseline drift by baseline correction.

[0028] Furthermore, the specific steps of motion feature point comparison are: calculating the Euclidean distance between the feature vector of the current motion feature point and the feature vector of the motion feature point in the previous unit time; when the Euclidean distance is less than a preset threshold, determining that the current motion feature point is consistent with the motion feature point in the previous unit time; when the Euclidean distance is greater than the preset threshold, determining that the current motion feature point is inconsistent with the motion feature point in the previous unit time.

[0029] The workflow of the present invention is as follows: When the balance training system under the guidance of rehabilitation exercise data acquisition and analysis designed in this scheme is used, the athlete uses the exercise module 3 to perform rehabilitation training, the acquisition module 2 obtains the light intensity signal of the muscle at a specific position of the subject, and transmits the light intensity signal to the acquisition and analysis software 4 in the console 1, the blood oxygen detection unit 5 receives the light intensity signal and removes motion artifacts through spline difference, removes physiological noise through a Butterworth bandpass filter, and avoids baseline drift through baseline correction, converts the light intensity signal of the λ1 wavelength sensitive to deoxyhemoglobin into the optical density value ODHb of deoxyhemoglobin, and converts the light intensity signal of the λ2 wavelength sensitive to oxyhemoglobin into the optical density value ODHb2 of oxyhemoglobin, according to the optical density value ratio formula Calculate the optical density value ratio ODR, count and calculate the optical density value ratio ODR received per unit time, average the optical density value ratio ODR that increases relative to the previous value per unit time, and get the average increase Q, then average the optical density value ratio that decreases relative to the previous value per unit time, and get the average decrease H, and according to the indicator formula Calculate the relative strength index RS I and input the relative strength index RS I into the judgment unit 7;

[0030] The acquisition module 2 acquires a motion video image of the athlete and transmits the video data to the acquisition and analysis software 4 in the console 1. The posture detection unit 6 extracts the human shape area of ​​each frame from the motion video image, performs binarization processing on the extracted human shape area, and segments the binarized human shape area to obtain a binary human body contour image. The motion feature points of the human body contour in the binary human body contour image are extracted, and the binary human body contour image and the motion feature points are input into the judgment unit 7.

[0031] The judgment unit 7 compares the input relative strength index RSI with a preset threshold value, calculates the Euclidean distance between the feature vector of the current motion feature point and the feature vector of the motion feature point in the previous unit time, and when the Euclidean distance is less than the preset threshold value, determines that the current motion feature point is consistent with the motion feature point in the previous unit time; when the Euclidean distance is greater than the preset threshold value, determines that the current motion feature point is inconsistent with the motion feature point in the previous unit time. If the input relative strength index RSI is lower than the preset threshold value, and the proportion of matching motion feature points in the two binary human body contour images exceeds 70%, it indicates that the athlete is in normal rehabilitation training and can continue rehabilitation. If the input relative strength index RSI is higher than the preset threshold value, and the proportion of matching motion feature points in the two binary human body contour images is 50%, it indicates that the athlete is in fatigue rehabilitation training and needs to suspend training for rest. If the proportion of matching motion feature points in the two binary human body contour images is between 50% and 70%, it indicates that the athlete's exercise intensity is high and the exercise intensity needs to be reduced before continuing training.

[0032] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A balance training method under the guidance of rehabilitation exercise data collection and analysis, which is based on a balance training system, the balance training system comprising a console (1), a collection module (2) and a motion module (3), the console (1) being internally provided with collection and analysis software (4), the collection and analysis software (4) comprising a blood oxygen detection unit (5), a posture detection unit (6) and a judgment unit (7), characterized in that: The acquisition module (2) obtains the light intensity signal of the muscle at a specific position of the subject and transmits the light intensity signal to the acquisition and analysis software (4) in the console (1). The blood oxygen detection unit (5) receives the light intensity signal and performs preprocessing, converting the light intensity signal of the wavelength λ1 sensitive to deoxyhemoglobin into the optical density value ODHb of deoxyhemoglobin, and converting the light intensity signal of the wavelength λ2 sensitive to oxyhemoglobin into the optical density value ODHb2 of oxyhemoglobin. The optical density value ratio ODR is calculated according to the optical density value ratio formula. The optical density value ratios ODR received per unit time are counted and calculated. The optical density value ratios ODR that increase relative to the previous value per unit time are averaged to obtain the increase average value Q. The optical density value ratios that decrease relative to the previous value per unit time are averaged to obtain the decrease average value H. The relative strength index RSI is calculated according to the index formula and the relative strength index RSI is input into the judgment unit (7). The acquisition module (2) acquires the motion video image of the athlete and transmits the video data to the acquisition and analysis software (4) in the control console (1). The posture detection unit (6) extracts the human shape area of ​​each frame from the motion video image, performs binarization processing on the extracted human shape area, and segments the binarized human shape area to obtain a binarized human body contour image. The motion feature points are extracted from the human body contour in the binarized human body contour image, and the binarized human body contour image and the motion feature points are input into the judgment unit (7). The judgment unit (7) compares the input relative strength index RSI with a preset threshold value, and compares the input binary human body contour image motion feature points with the input binary human body contour image motion feature points in the previous unit time. If the input relative strength index RSI is lower than the preset threshold value, and the proportion of matching motion feature points in the two binary human body contour images exceeds 70%, it indicates that the athlete is in normal rehabilitation training and can continue rehabilitation. If the input relative strength index RSI is higher than the preset threshold value, and the proportion of matching motion feature points in the two binary human body contour images is 50%, it indicates that the athlete is in fatigue rehabilitation training and needs to suspend training for rest. If the proportion of matching motion feature points in the two binary human body contour images is between 50% and 70%, it indicates that the athlete's exercise intensity is high and the exercise intensity needs to be reduced before continuing training.

2. The balance training method under the guidance of rehabilitation exercise data collection and analysis according to claim 1, characterized in that: The console (1) is electrically connected to the acquisition module (2) via a wire, and the acquisition module (2) is provided in multiple groups.

3. The balance training method under the guidance of rehabilitation exercise data collection and analysis according to claim 1, characterized in that: The acquisition module (2) includes various near-infrared muscle oxygen detectors and CMOS cameras, and the exercise module (3) is a treadmill.

4. The balance training method under the guidance of rehabilitation exercise data collection and analysis according to claim 1, characterized in that: The optical density ratio formula is: ,Preprocessing includes removing motion artifacts by spline interpolation, removing physiological noise by Butterworth bandpass filter, and avoiding baseline ,drift by baseline correction.

5. The balance training method under the guidance of rehabilitation exercise data collection and analysis according to claim 1, characterized in that: The specific steps of the motion feature point comparison are: calculating the Euclidean distance between the feature vector of the current motion feature point and the feature vector of the motion feature point in the previous unit time; when the Euclidean distance is less than a preset threshold, determining that the current motion feature point is consistent with the motion feature point in the previous unit time; when the Euclidean distance is greater than the preset threshold, determining that the current motion feature point is inconsistent with the motion feature point in the previous unit time.

Images