CN118053544B - Exercise injury rehabilitation training method and system - Google Patents
Exercise injury rehabilitation training method and system Download PDFInfo
- Publication number
- CN118053544B CN118053544B CN202410147581.5A CN202410147581A CN118053544B CN 118053544 B CN118053544 B CN 118053544B CN 202410147581 A CN202410147581 A CN 202410147581A CN 118053544 B CN118053544 B CN 118053544B
- Authority
- CN
- China
- Prior art keywords
- baking
- value
- red component
- time length
- analysis model
- 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
- 238000012549 training Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000006378 damage Effects 0.000 title description 15
- 208000027418 Wounds and injury Diseases 0.000 title description 9
- 208000014674 injury Diseases 0.000 title description 7
- 230000000694 effects Effects 0.000 claims abstract description 152
- 208000025978 Athletic injury Diseases 0.000 claims abstract description 120
- 206010041738 Sports injury Diseases 0.000 claims abstract description 104
- 230000009467 reduction Effects 0.000 claims abstract description 38
- 230000000875 corresponding effect Effects 0.000 claims description 112
- 238000006243 chemical reaction Methods 0.000 claims description 79
- 238000013528 artificial neural network Methods 0.000 claims description 63
- 238000003384 imaging method Methods 0.000 claims description 47
- 238000012545 processing Methods 0.000 claims description 37
- 238000010606 normalization Methods 0.000 claims description 15
- 230000002596 correlated effect Effects 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 239000000470 constituent Substances 0.000 claims description 4
- 230000003902 lesion Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 210000003127 knee Anatomy 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 238000000554 physical therapy Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000003466 welding Methods 0.000 description 5
- 230000003247 decreasing effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 210000002414 leg Anatomy 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 238000013481 data capture Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000000750 progressive effect Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 2
- 210000003041 ligament Anatomy 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000000474 nursing effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000032912 Local swelling Diseases 0.000 description 1
- 206010050031 Muscle strain Diseases 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 230000000386 athletic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003467 diminishing effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000001012 protector Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000017423 tissue regeneration Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/32—Normalisation of the pattern dimensions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Physical Education & Sports Medicine (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a sports injury rehabilitation training method, which relates to the field of sports rehabilitation, and comprises the following steps: respectively inputting specific parameter combinations of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp into an effect analysis model to obtain the descending amplitude of each red component; and taking the specific parameter combination corresponding to the red component reduction amplitude value of the maximum value as the preferred parameter combination. The invention also relates to a sports injury rehabilitation training system. According to the invention, aiming at the technical problem that the same lamp device is difficult to obtain the optimal rehabilitation effect when the same sports injury patient uses the same lamp device, the effect analysis model can be adopted to intelligently predict different rehabilitation training effect data respectively obtained by the same lamp device by adopting different numerical combinations of a plurality of working parameters, and the numerical combination corresponding to the rehabilitation training effect data with the optimal training effect is taken as the optimal numerical combination to be put into specific use, so that the technical problem is solved.
Description
Technical Field
The invention relates to the field of sports rehabilitation, in particular to a sports injury rehabilitation training method and system.
Background
Sports injury refers to a wide variety of injuries that people cause during exercise. The rehabilitation training aims to recover the state and improve the training quality. The rehabilitation early stage mainly comprises whole body activities, and performs local activity hot compress and progressive active activities under the condition of not aggravating local swelling and pain, wherein a rehabilitation baking lamp is a commonly used physiotherapy instrument, can be used for treating sports injuries, especially muscle strain, and has the principle that diseases are treated by utilizing the warm effect of infrared rays emitted by the rehabilitation baking lamp, so that the aims of diminishing inflammation and promoting blood circulation and helping tissue repair are fulfilled, namely, the strained part can be slowly relieved in a baking lamp physiotherapy mode, and the recovery of illness state can be well promoted after the blood circulation is finished.
For example, chinese patent publication CN203458696U proposes a sports injury recovery therapeutic apparatus, which includes a knee protector and a therapeutic part, and is characterized in that: a display screen is arranged on the treatment part; a battery box is arranged at the inner side of the treatment part; the battery box is provided with a DC jack; the top end of the treatment part is also provided with a key area; the key area is provided with four keys; the treatment part is also provided with ventilation holes; the four corners of the knee guard are provided with fastening belts; the knee pad part comprises an infrared lamp and a baking lamp; the center of the baking lamp is provided with an infrared lamp through hole and a baking lamp through hole respectively; silver sheets are arranged around the through holes of the infrared lamp and the baking lamp; four electrode plates are arranged on the inner side of the knee pad part and close to the fastening belt, wherein the left two electrodes are positive electrodes, and the right two electrodes are negative electrodes; two ice bag fixing rings are arranged on the inner side of the top of the knee pad part. The beneficial effects of the utility model are as follows: the infrared lamp therapy wound and the baking lamp therapy wound which are commonly used at present are integrated; four knee pads
The corners are provided with electrodes, which can provide micro-current stimulation treatment function for people with torn ligaments and injured ligaments.
The utility model provides a novel stoving physiotherapy equipment for lift surgical nursing that chinese patent publication CN112274783a proposed, stoving physiotherapy equipment includes the bottom plate, the gyro wheel is installed to the inner wall of bottom plate, the outer wall of gyro wheel links to each other with the inner wall of bottom plate, the upper surface welding of bottom plate has the landing leg, the lower surface of landing leg links to each other with the upper surface welding of bottom plate, the upper surface welding of landing leg has the roof, the lower surface welding of roof links to each other with the upper surface welding of landing leg, the right side inner wall of roof has cup jointed the pole setting, the outer wall of pole setting cup joints with the inner wall of roof and links to each other. This novel lift surgical nursing is with baking electricity physiotherapy equipment, through the cooperation between first motor, lead screw and the screw seat, under the effect of support, first motor is AC servo motor, through the size of the produced power of regulating current through the motor, and then the rotational speed of regulating motor, through the rotational speed of regulating motor, and then the regulation support is at the speed of lifting in the lead screw, improves lifting speed, improves work efficiency, is fit for using widely.
Therefore, the technical scheme related to the prior art is limited to a specific internal structure and a specific working mode of the baking lamp device for physiotherapy, the rehabilitation training effect of the baking lamp device cannot be predicted, particularly, the baking lamp device basically has a plurality of working parameters, even for patients with the same sports injury, under the rehabilitation training of the same baking lamp device, the corresponding different rehabilitation training effects can be obtained by using different number of the values of the plurality of working parameters, and the optimal parameter value combination is selected for the plurality of working parameters so as to obtain the optimal rehabilitation training effect, so that the baking lamp device is one of the technical problems to be solved in the field of sports rehabilitation at present.
Disclosure of Invention
In order to solve the technical problems in the related art, the invention provides a sports injury rehabilitation training method and a system, which can intelligently predict different rehabilitation training effect data respectively obtained by adopting different numerical combinations of a plurality of working parameters by adopting a targeted designed effect analysis model, and enable the numerical group corresponding to the rehabilitation training effect data with the best training effect in the different rehabilitation training effect data to intelligently predict the same baking lamp device
The specific numerical values of the preferable working parameters of the baking lamp device are used for being put into the practical rehabilitation training of the baking lamp device on the sports injury patient, so that the optimal rehabilitation training effect can be obtained without repeated rehabilitation training experiments.
According to a first aspect of the present invention, there is provided a method of rehabilitation training for sports injuries, the method comprising:
Performing a directed image data capturing action on a skin surface facing a lesion site of a sports injury patient to obtain and output a corresponding directed captured image;
identifying a human skin imaging region in the received orientation captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging region as a target imaging region;
Performing image content normalization processing of the same resolution on the target imaging region to obtain a normalized conversion region having a set resolution;
Extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type quantity, the signal-to-noise ratio and the contrast of the received normalized conversion area;
Synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of a patient suffering from sports injury, the noise type number of a normalized conversion area, the signal to noise ratio and the contrast into an effect analysis model, and operating the effect analysis model to obtain the red component dropping amplitude of the output red component corresponding to each specific parameter combination when the baking is completed for the fixed time length;
respectively taking each specific parameter combination of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp as a specific parameter combination corresponding to the maximum value in the descending amplitude of each red component obtained by the input content of the effect analysis model as a preferable parameter combination;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake the damaged part of a patient with sports injury, taking the average value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with the descending amplitude value of the first reference red component as the descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value corresponds to the specific parameter combination;
The effect analysis model is a feedforward neural network which is trained for many times, the training times are monotonically and positively correlated with the numerical value of the set resolution, and individual information of the sports injury patient comprises the age, sex and sports lifetime of the sports injury patient.
According to a second aspect of the present invention there is provided a sports injury rehabilitation training system, the system comprising:
a data capturing device for performing a directed image data capturing action on a skin surface of a damaged portion of a sports damaged patient to obtain and output a corresponding directed captured image;
The segmentation processing device is connected with the data capturing device and is used for identifying a human skin imaging area in the received directional captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging area as a target imaging area;
A signal conversion device connected to the segmentation processing device for performing image content normalization processing of the same resolution on the target imaging region to obtain a normalized conversion region having a set resolution;
The content detection device is connected with the signal conversion device and is used for extracting each red component value, each green component value and each blue component value which respectively correspond to each component pixel point in the received normalized conversion area, and analyzing the noise type quantity, the signal-to-noise ratio and the contrast of the received normalized conversion area;
The traversal analysis equipment is connected with the content detection equipment and used for synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, the individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal-to-noise ratio and the contrast into the effect analysis model, and operating the effect analysis model to obtain the red component drop amplitude which is output by the effect analysis model and corresponds to each specific parameter combination when the baking is completed and reaches the fixed time length;
the optimal processing equipment is connected with the traversal analysis equipment and is used for taking specific parameter combinations of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp as the specific parameter combinations corresponding to the maximum value in the descending amplitude of each red component obtained by the input content of the effect analysis model as optimal parameter combinations;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake the damaged part of a patient with sports injury, taking the average value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with the descending amplitude value of the first reference red component as the descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value corresponds to the specific parameter combination;
The effect analysis model is a feedforward neural network which is trained for many times, the training times are monotonically and positively correlated with the numerical value of the set resolution, and individual information of the sports injury patient comprises the age, sex and sports lifetime of the sports injury patient.
Thus, the present invention has at least the following four important aspects:
The first invention is as follows: aiming at the damaged part of the same sports injury patient, performing sports injury rehabilitation training by adopting a set rehabilitation baking lamp, traversing each specific parameter combination of three parameters of baking distance, baking power and baking time length of the set rehabilitation baking lamp for participating in predictive analysis of training effect obtained by rehabilitation training to obtain each effect data corresponding to each specific parameter combination, recommending the specific parameter combination corresponding to the optimal effect data as a preferred parameter combination to the sports injury patient for use, and thus obtaining the optimal rehabilitation training effect without repeated experiments;
The second invention is as follows: the method comprises the steps that an effect analysis model with a pertinence design is used for executing predictive analysis of training effects obtained by participation in rehabilitation training of each specific parameter combination, the pertinence design of the effect analysis model is characterized in that the model is a feedforward neural network after multiple times of training, the pertinence screening of the model item-by-item input data and the pertinence selection of training times which are monotonously and positively correlated with the set resolution of image normalization processing, and therefore the prediction reliability and stability of the training effects corresponding to each specific parameter combination are guaranteed;
The third invention is as follows: in each training of the feedforward neural network, a known red component drop amplitude value when a specific parameter combination of three parameters including baking distance, baking power and baking time length of a set rehabilitation baking lamp is adopted to finish baking for a fixed time length is used as output content of the feedforward neural network, each red component value, each green component value, each blue component value, noise type number of a normalized conversion area, signal to noise ratio, individual information of a sports injury patient and contrast of the feedforward neural network are used as progressive input content of the feedforward neural network, so that the training effect of each training of the feedforward neural network is ensured, and the prediction reliability and stability of the training effect corresponding to each specific parameter combination are further ensured;
The invention is as follows: the method comprises the steps of selecting the integral red component descending amplitude of a normalized conversion area obtained after resolution normalization treatment of a skin surface imaging area of a damaged part of a patient with sports injury before and after baking of a set rehabilitation baking lamp, carrying out numerical representation on rehabilitation training effects of the set rehabilitation baking lamp, and capturing integral red components obtained through analysis at a moment after baking is completed for a longer time interval according to baked data, so that effectiveness analysis on the rehabilitation training effects is realized.
Drawings
Embodiments of the present invention will be described below with reference to the accompanying drawings, in which:
FIG. 1 is a technical flow chart of a method and system for rehabilitation training of sports injury according to the present invention.
Fig. 2 is a flowchart showing steps of a sports injury rehabilitation training method according to embodiment 1 of the present invention.
Fig. 3 is a flowchart showing steps of a sports injury rehabilitation training method according to embodiment 2 of the present invention.
Fig. 4 is a flowchart showing steps of a sports injury rehabilitation training method according to embodiment 3 of the present invention.
Fig. 5 is an internal structural diagram of the sports injury rehabilitation training system according to embodiment 4 of the present invention.
Fig. 6 is an internal structural diagram of the sports injury rehabilitation training system according to embodiment 5 of the present invention.
Fig. 7 is an internal structural diagram of the sports injury rehabilitation training system according to embodiment 6 of the present invention.
Detailed Description
As shown in fig. 1, a technical flowchart of the exercise injury rehabilitation training method and system according to the present invention is provided.
As shown in fig. 1, the specific technical process of the present invention is as follows:
Technical flow A: establishing a pertinently designed effect analysis model for predicting a training effect obtained by adopting each specific parameter combination of a set rehabilitation baking lamp to participate in baking rehabilitation training of a damaged part of a patient with sports injury;
In fig. 1, the set rehabilitation baking lamp comprises a baking lamp head part 2 and a baking lamp clamping part 3, and in fig. 1, a data capturing device 1 is further included, and is used for performing a directional image data capturing action on a front scene of the set rehabilitation baking lamp so as to obtain and output a corresponding directional captured image;
Specifically, the set rehabilitation baking lamp comprises three different types of baking parameters, namely baking distance, baking power and baking duration of the set rehabilitation baking lamp, and for the three different types of baking parameters, each available value of the set rehabilitation baking lamp can be traversed to obtain a plurality of specific parameter combinations;
illustratively, the targeted design of the effect analysis model is embodied in several aspects:
(1) The effect analysis model is a feedforward neural network after multiple training and has item-by-item input data with targeted screening, wherein the item-by-item input data comprises a single specific parameter combination of the baking distance, the baking power and the baking time length of the set rehabilitation baking lamp, and also comprises red component values, green component values, blue component values, fixed time length, individual information of a patient suffering from sports injury, noise type quantity, signal to noise ratio and contrast of a normalized conversion area;
After normalization processing of a set resolution, a corresponding normalized conversion area is obtained in a target imaging area corresponding to the skin surface of a damaged part of a patient with sports damage before baking, wherein each component pixel point of the normalized conversion area corresponds to each red component value, each green component value and each blue component value respectively, and the normalized conversion area can be analyzed to obtain the noise type quantity, the signal-to-noise ratio and the contrast of the normalized conversion area;
wherein the athletic injury patient individual information includes age, sex, and athletic lifetime of the athletic injury patient;
(2) The targeted selection of training times associated with monotonic forward direction of the set resolution of the image normalization processing ensures the prediction reliability and stability of the training effect corresponding to each specific parameter combination;
(3) In each training of the feedforward neural network, a known red component drop amplitude value when a specific parameter combination of three parameters including baking distance, baking power and baking time length of a set rehabilitation baking lamp is adopted to finish baking for a fixed time length is used as output content of the feedforward neural network, each red component value, each green component value, each blue component value, noise type number of a normalized conversion area, signal to noise ratio, individual information of a sports injury patient and contrast of the feedforward neural network are used as progressive input content of the feedforward neural network, so that the training effect of each training of the feedforward neural network is ensured, and the prediction reliability and stability of the training effect corresponding to each specific parameter combination are further ensured;
Technical flow B: each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the rehabilitation baking lamp is set in a traversing mode and is input into the effect analysis model in a time sharing mode to execute predictive analysis of training effects obtained by respectively participating in rehabilitation training, and then each effect data corresponding to each specific parameter combination is obtained;
technical flow C: recommending a specific parameter combination corresponding to the optimal effect data in each effect data as a preferred parameter combination to a patient with sports injury, so that the optimal rehabilitation training effect can be obtained without repeated experiments;
Specifically, the reduction amplitude of the integral red component of the normalized conversion area obtained after the resolution normalization processing of the skin surface imaging area of the damaged part of the patient with the movement damage before and after the baking of the set rehabilitation baking lamp is selected as the effect data for setting the rehabilitation training effect of the rehabilitation baking lamp, the data before the baking is the average value of the red component values, and the data after the baking is the average value of the red component values obtained by capturing and analyzing at the moment after the baking is completed for a longer time interval.
The key points of the invention are as follows: the parameter combination optimizing mechanism is used for predicting the pertinence design of an effect analysis model of training effects obtained by adopting each specific parameter combination of a set rehabilitation baking lamp to participate in the baking rehabilitation training of the damaged part of a sports injury patient, performing time-sharing intelligent prediction by traversing each specific parameter combination so as to obtain effect data of each rehabilitation training effect respectively, and recommending the specific parameter combination corresponding to the optimal effect data in each effect data as an optimizing parameter combination.
The exercise injury rehabilitation training method and system of the present invention will be specifically described by way of examples.
Example 1
Fig. 2 is a flowchart showing steps of a sports injury rehabilitation training method according to embodiment 1 of the present invention.
As shown in fig. 2, the exercise injury rehabilitation training method comprises the following steps:
step one: performing a directed image data capturing action on a skin surface facing a lesion site of a sports injury patient to obtain and output a corresponding directed captured image;
illustratively, the resolution of the directionally captured image is not fixed, and is related to the resolution of the capture device performing the directionally image data capture action;
Step two: identifying a human skin imaging region in the received orientation captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging region as a target imaging region;
illustratively, the brightness value distribution interval corresponding to the human skin is used for distinguishing the human skin from other image contents from the image, so that the human skin imaging area can be effectively segmented;
step three: performing image content normalization processing of the same resolution on the target imaging region to obtain a normalized conversion region having a set resolution;
Specifically, the simultaneous size normalization processing and scaling processing completes the normalization processing of the resolutions of the image contents of different resolutions to obtain a normalized conversion region having a set resolution;
Step four: extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type quantity, the signal-to-noise ratio and the contrast of the received normalized conversion area;
Step five: synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of a patient suffering from sports injury, the noise type number of a normalized conversion area, the signal to noise ratio and the contrast into an effect analysis model, and operating the effect analysis model to obtain the red component dropping amplitude of the output red component corresponding to each specific parameter combination when the baking is completed for the fixed time length;
Specifically, a numerical simulation mode can be selected to realize that each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of sports injury patients, the noise type number of a normalized conversion area, a signal-to-noise ratio and a contrast ratio are synchronously input into an effect analysis model, and the effect analysis model is operated to obtain simulation and test of the output data processing process, corresponding to each specific parameter combination, of the red component reduction amplitude when the baking is completed for a fixed time length;
step six: respectively taking each specific parameter combination of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp as a specific parameter combination corresponding to the maximum value in the descending amplitude of each red component obtained by the input content of the effect analysis model as a preferable parameter combination;
Specifically, the larger the value of the red component decreasing amplitude is, the more the damage part of the sports injury patient is recovered after the baking is completed for a longer fixed time, compared with the red component decreasing degree of the damage part of the sports injury patient before the baking, namely the recovery degree of the damage part of the sports injury patient;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake the damaged part of a patient with sports injury, taking the average value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with the descending amplitude value of the first reference red component as the descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value corresponds to the specific parameter combination;
The fixed time length value is greater than or equal to a set time length threshold value, the effect analysis model is a feedforward neural network which is trained for a plurality of times, the training times are monotonically and positively correlated with the set resolution value, and the individual information of the sports injury patient comprises the age, sex and sports lifetime of the sports injury patient;
Illustratively, the effect analysis model is a feedforward neural network trained a plurality of times, and the monotonically positive correlation of the number of times of training and the value of the set resolution includes: the set resolution value is 1080P, the number of training selected for the feedforward neural network is 80, the set resolution value is 2K, the number of training selected for the feedforward neural network is 100, the set resolution value is 4K, the number of training selected for the feedforward neural network is 120, and the set resolution value is 8K, the number of training selected for the feedforward neural network is 150;
The method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain a red component reduction amplitude value when the baking is completed to reach the fixed time length, wherein the red component reduction amplitude value corresponds to each specific parameter combination and is output by the effect analysis model, and the red component reduction amplitude value comprises the following steps: executing the operation of the effect analysis model once for each specific parameter combination to obtain a red component drop amplitude corresponding to the specific parameter combination;
Specifically, each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast ratio are synchronously input into an effect analysis model, and the operation of the effect analysis model to obtain the red component reduction amplitude of the output red component corresponding to each specific parameter combination when the baking is completed for the fixed time length further comprises: the value of each red component value is between 0 and 255, the value of each green component value is between 0 and 255, and the value of each blue component value is between 0 and 255;
And wherein the value of the fixed time length is greater than or equal to a set duration threshold, the effect analysis model is a feedforward neural network after multiple training and the training times are monotonically and positively correlated with the value of the set resolution, and the individual information of the sports injury patient comprises the age, sex and sports lifetime duration of the sports injury patient, including: in each training of the feedforward neural network, a known red component descending amplitude value when a certain specific parameter combination of three parameters including a baking distance, a baking power and a baking time length of a set rehabilitation baking lamp is adopted to finish baking for a fixed time length is used as output content of the feedforward neural network, and each red component value, each green component value, each blue component value, the noise type number of a normalized conversion area, a signal-to-noise ratio, individual information of a sports injury patient and contrast ratio corresponding to a directional captured image captured before baking of the certain specific parameter combination, the fixed time length are used as item-by-item input content of the feedforward neural network to finish the training operation.
Example 2
Fig. 3 is a flowchart showing steps of a sports injury rehabilitation training method according to embodiment 2 of the present invention.
As shown in fig. 3, after the sixth step, the athletic injury rehabilitation training method further includes:
step seven: receiving three specific values corresponding to three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the preferred parameter combination, and displaying the three specific values corresponding to the three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the preferred parameter combination in real time;
For example, the three specific values corresponding to the three parameters of the baking distance, the baking power and the baking time period of the set rehabilitation baking lamp corresponding to the preferred parameter combination can be received and displayed in real time by selecting an LED display array, an LCD display array or a liquid crystal display screen.
Example 3
Fig. 4 is a flowchart showing steps of a sports injury rehabilitation training method according to embodiment 3 of the present invention.
As shown in fig. 4, before the fifth step, the athletic injury rehabilitation training method further includes:
Step eight: performing multiple training on the feedforward neural network to obtain the feedforward neural network after multiple training, and outputting the feedforward neural network after multiple training as an effect analysis model;
For example, the MATLAB tool box may be selectively used to perform multiple training on the feedforward neural network to obtain a feedforward neural network after multiple training, and the feedforward neural network after multiple training is used as a simulation of a data processing process output by the effect analysis model.
Next, the exercise injury rehabilitation training method according to the embodiments of the present invention will be further described.
Within any of the above embodiments 1-3, optionally, in the athletic injury rehabilitation training method:
identifying a human skin imaging region in the received orientation captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging region as a target imaging region comprises: the brightness value distribution interval corresponding to the human skin is limited by a brightness value upper limit threshold value and a brightness value lower limit threshold value corresponding to the human skin, wherein the value of the brightness value upper limit threshold value is larger than that of the brightness value lower limit threshold value;
Correspondingly, the value of the brightness value upper limit threshold is larger than the value of the brightness value lower limit threshold, which comprises the following steps: the value of the upper limit threshold of the brightness value and the value of the lower limit threshold of the brightness value are all between 0 and 255;
Wherein, the human skin imaging region in the received directional captured image is identified based on the brightness value distribution interval corresponding to the human skin and output as the target imaging region further comprises: taking pixel points, which are included in the directional captured image and have brightness values within a brightness value distribution interval corresponding to human skin, as skin formation pixel points, and taking pixel points, which are included in the directional captured image and have brightness values outside the brightness value distribution interval corresponding to human skin, as other pixel points;
Extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type number, the signal-to-noise ratio and the contrast of the received normalized conversion area includes: each of the constituent pixel points has a red component value, a green component value, and a blue component value in an RGB color space;
the method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude when the baking is completed and reaches the fixed time length, wherein the red component reduction amplitude corresponds to each specific parameter combination, and the red component reduction amplitude is output by the effect analysis model and comprises the following steps: each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast are respectively subjected to octave numerical conversion processing and then synchronously input into the effect analysis model;
And wherein synchronizing the input of each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, the individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast to the effect analysis model, and operating the effect analysis model to obtain the output red component drop amplitude corresponding to each specific parameter combination when the baking is completed for the fixed time length, further comprises: the effect analysis model is run to obtain the red component drop magnitude of the octave numerical representation of its output.
Example 4
Fig. 5 is an internal structural diagram of the sports injury rehabilitation training system according to embodiment 4 of the present invention.
As shown in fig. 5, the athletic injury rehabilitation training system comprises the following components:
a data capturing device for performing a directed image data capturing action on a skin surface of a damaged portion of a sports damaged patient to obtain and output a corresponding directed captured image;
Illustratively, the resolution of the orientation captured image is not fixed, and is related to the resolution of the capture device performing the orientation image data capture action, i.e., the data capture device;
The segmentation processing device is connected with the data capturing device and is used for identifying a human skin imaging area in the received directional captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging area as a target imaging area;
illustratively, the brightness value distribution interval corresponding to the human skin is used for distinguishing the human skin from other image contents from the image, so that the human skin imaging area can be effectively segmented;
A signal conversion device connected to the segmentation processing device for performing image content normalization processing of the same resolution on the target imaging region to obtain a normalized conversion region having a set resolution;
Specifically, the simultaneous size normalization processing and scaling processing completes the normalization processing of the resolutions of the image contents of different resolutions to obtain a normalized conversion region having a set resolution;
The content detection device is connected with the signal conversion device and is used for extracting each red component value, each green component value and each blue component value which respectively correspond to each component pixel point in the received normalized conversion area, and analyzing the noise type quantity, the signal-to-noise ratio and the contrast of the received normalized conversion area;
The traversal analysis equipment is connected with the content detection equipment and used for synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, the individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal-to-noise ratio and the contrast into the effect analysis model, and operating the effect analysis model to obtain the red component drop amplitude which is output by the effect analysis model and corresponds to each specific parameter combination when the baking is completed and reaches the fixed time length;
Specifically, a numerical simulation mode can be selected to realize that each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of sports injury patients, the noise type number of a normalized conversion area, a signal-to-noise ratio and a contrast ratio are synchronously input into an effect analysis model, and the effect analysis model is operated to obtain simulation and test of the output data processing process, corresponding to each specific parameter combination, of the red component reduction amplitude when the baking is completed for a fixed time length;
the optimal processing equipment is connected with the traversal analysis equipment and is used for taking specific parameter combinations of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp as the specific parameter combinations corresponding to the maximum value in the descending amplitude of each red component obtained by the input content of the effect analysis model as optimal parameter combinations;
Specifically, the larger the value of the red component decreasing amplitude is, the more the damage part of the sports injury patient is recovered after the baking is completed for a longer fixed time, compared with the red component decreasing degree of the damage part of the sports injury patient before the baking, namely the recovery degree of the damage part of the sports injury patient;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake the damaged part of a patient with sports injury, taking the average value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with the descending amplitude value of the first reference red component as the descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value corresponds to the specific parameter combination;
The fixed time length value is greater than or equal to a set time length threshold value, the effect analysis model is a feedforward neural network which is trained for a plurality of times, the training times are monotonically and positively correlated with the set resolution value, and the individual information of the sports injury patient comprises the age, sex and sports lifetime of the sports injury patient;
Illustratively, the effect analysis model is a feedforward neural network trained a plurality of times, and the monotonically positive correlation of the number of times of training and the value of the set resolution includes: the set resolution value is 1080P, the number of training selected for the feedforward neural network is 80, the set resolution value is 2K, the number of training selected for the feedforward neural network is 100, the set resolution value is 4K, the number of training selected for the feedforward neural network is 120, and the set resolution value is 8K, the number of training selected for the feedforward neural network is 150;
The method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain a red component reduction amplitude value when the baking is completed to reach the fixed time length, wherein the red component reduction amplitude value corresponds to each specific parameter combination and is output by the effect analysis model, and the red component reduction amplitude value comprises the following steps: executing the operation of the effect analysis model once for each specific parameter combination to obtain a red component drop amplitude corresponding to the specific parameter combination;
Specifically, each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast ratio are synchronously input into an effect analysis model, and the operation of the effect analysis model to obtain the red component reduction amplitude of the output red component corresponding to each specific parameter combination when the baking is completed for the fixed time length further comprises: the value of each red component value is between 0 and 255, the value of each green component value is between 0 and 255, and the value of each blue component value is between 0 and 255;
And wherein the value of the fixed time length is greater than or equal to a set duration threshold, the effect analysis model is a feedforward neural network after multiple training and the training times are monotonically and positively correlated with the value of the set resolution, and the individual information of the sports injury patient comprises the age, sex and sports lifetime duration of the sports injury patient, including: in each training of the feedforward neural network, a known red component descending amplitude value when a certain specific parameter combination of three parameters including a baking distance, a baking power and a baking time length of a set rehabilitation baking lamp is adopted to finish baking for a fixed time length is used as output content of the feedforward neural network, and each red component value, each green component value, each blue component value, the noise type number of a normalized conversion area, a signal-to-noise ratio, individual information of a sports injury patient and contrast ratio corresponding to a directional captured image captured before baking of the certain specific parameter combination, the fixed time length are used as item-by-item input content of the feedforward neural network to finish the training operation.
Example 5
Fig. 6 is an internal structural diagram of the sports injury rehabilitation training system according to embodiment 5 of the present invention.
As shown in fig. 6, the athletic injury rehabilitation training system further includes:
The instant display device is connected with the preferential treatment device and is used for receiving three specific values corresponding to three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the preferential parameter combination;
The instant display device is further used for displaying three specific values corresponding to three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the optimal parameter combination in an instant mode;
For example, the instant display device may be implemented by using an LED display array, an LCD display array or a liquid crystal display screen, so as to perform receiving and instant display of three specific values corresponding to three parameters, namely, a baking distance, a baking power and a baking duration of the set rehabilitation baking lamp corresponding to the preferred parameter combination.
Example 6
Fig. 7 is an internal structural diagram of the sports injury rehabilitation training system according to embodiment 6 of the present invention.
As shown in fig. 7, the athletic injury rehabilitation training system further includes:
The network reconstruction device is connected with the traversal analysis device and is used for performing multiple training on the feedforward neural network to obtain the feedforward neural network after multiple training;
The network reconstruction equipment is also used for sending the feedforward neural network which is trained for many times to the traversal analysis equipment as an effect analysis model;
For example, the MATLAB tool box may be selectively used to perform multiple training on the feedforward neural network to obtain a feedforward neural network after multiple training, and the feedforward neural network after multiple training is used as a simulation of a data processing process output by the effect analysis model.
Next, the athletic injury rehabilitation training system according to various embodiments of the present invention will be further described.
Within any of the various embodiments 4-6 above, optionally, in the athletic injury rehabilitation training system:
identifying a human skin imaging region in the received orientation captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging region as a target imaging region comprises: the brightness value distribution interval corresponding to the human skin is limited by a brightness value upper limit threshold value and a brightness value lower limit threshold value corresponding to the human skin, wherein the value of the brightness value upper limit threshold value is larger than that of the brightness value lower limit threshold value;
Correspondingly, the value of the brightness value upper limit threshold is larger than the value of the brightness value lower limit threshold, which comprises the following steps: the value of the upper limit threshold of the brightness value and the value of the lower limit threshold of the brightness value are all between 0 and 255;
Wherein, the human skin imaging region in the received directional captured image is identified based on the brightness value distribution interval corresponding to the human skin and output as the target imaging region further comprises: taking pixel points, which are included in the directional captured image and have brightness values within a brightness value distribution interval corresponding to human skin, as skin formation pixel points, and taking pixel points, which are included in the directional captured image and have brightness values outside the brightness value distribution interval corresponding to human skin, as other pixel points;
Extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type number, the signal-to-noise ratio and the contrast of the received normalized conversion area includes: each of the constituent pixel points has a red component value, a green component value, and a blue component value in an RGB color space;
the method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude when the baking is completed and reaches the fixed time length, wherein the red component reduction amplitude corresponds to each specific parameter combination, and the red component reduction amplitude is output by the effect analysis model and comprises the following steps: each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast are respectively subjected to octave numerical conversion processing and then synchronously input into the effect analysis model;
And wherein synchronizing the input of each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, the individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast to the effect analysis model, and operating the effect analysis model to obtain the output red component drop amplitude corresponding to each specific parameter combination when the baking is completed for the fixed time length, further comprises: the effect analysis model is run to obtain the red component drop magnitude of the octave numerical representation of its output.
In addition, the salient features and significant advances of the athletic injury rehabilitation training method and system according to the present invention may be further characterized from the following aspects:
Synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, the signal to noise ratio and the contrast into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude value when the baking is completed to reach the fixed time length, which corresponds to each specific parameter combination, of the output of the effect analysis model, wherein the step of obtaining the red component reduction amplitude value comprises the following steps: the method comprises the steps of selecting a numerical simulation processing mode to finish the synchronous input of each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal-to-noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain simulation operation of a data processing process, which is output by the effect analysis model, of which the corresponding specific parameter combination is used for finishing the red component dropping amplitude when the baking reaches the fixed time length;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake a damaged part of a sports injury patient, taking a mean value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with a descending amplitude value of the first reference red component as a descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value of the red component when the baking is completed corresponding to the specific parameter combination comprises: performing maximum value removal processing and minimum value removal processing on each red component value corresponding to the directional captured image captured when the baking is completed for a fixed time length, and taking the average value of the obtained red component values as a second reference red component;
The value of the fixed time length is greater than or equal to a set duration threshold, the effect analysis model is a feedforward neural network after multiple times of training, the training times and the value of the set resolution are monotonically and positively correlated, and the individual information of the sports injury patient comprises the age, sex and sports lifetime duration of the sports injury patient, wherein the steps of: a numerical mapping function is adopted to represent the numerical mapping relation of the monotonic forward association of the training times and the numerical value of the set resolution;
Illustratively, the numerical mapping relationship that uses a numerical mapping function to represent the monotonically positive association of the number of training times with the numerical value of the set resolution includes: in the numerical mapping function, the horizontal resolution and the vertical resolution of the set resolution are two input parameters, the training frequency is a single output parameter, and the horizontal resolution and the vertical resolution of the set resolution are monotonically and positively associated with the training frequency;
Specifically, in the numerical mapping function, the horizontal resolution and the vertical resolution of the set resolution are two input parameters, the number of training is a single output parameter, and the monotonically positive association between the horizontal resolution and the vertical resolution of the set resolution and the number of training includes: the horizontal resolution of the set resolution is the total number of pixel columns of the corresponding normalized image, and the vertical resolution of the set resolution is the total number of pixel rows of the corresponding normalized image.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
From the above description of embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus a general purpose hardware platform, or may be implemented by hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the related art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (4)
1. A method of rehabilitation training for sports injuries, the method comprising:
Performing a directed image data capturing action on a skin surface facing a lesion site of a sports injury patient to obtain and output a corresponding directed captured image;
identifying a human skin imaging region in the received orientation captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging region as a target imaging region;
Performing image content normalization processing of the same resolution on the target imaging region to obtain a normalized conversion region having a set resolution;
Extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type quantity, the signal-to-noise ratio and the contrast of the received normalized conversion area;
Synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of a patient suffering from sports injury, the noise type number of a normalized conversion area, the signal to noise ratio and the contrast into an effect analysis model, and operating the effect analysis model to obtain the red component dropping amplitude of the output red component corresponding to each specific parameter combination when the baking is completed for the fixed time length;
respectively taking each specific parameter combination of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp as a specific parameter combination corresponding to the maximum value in the descending amplitude of each red component obtained by the input content of the effect analysis model as a preferable parameter combination;
Receiving three specific values corresponding to three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the preferred parameter combination, and displaying the three specific values corresponding to the three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the preferred parameter combination in real time;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake the damaged part of a patient with sports injury, taking the average value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with the descending amplitude value of the first reference red component as the descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value corresponds to the specific parameter combination;
The fixed time length value is greater than or equal to a set time length threshold value, the effect analysis model is a feedforward neural network which is trained for a plurality of times, the training times are monotonically and positively correlated with the set resolution value, and the individual information of the sports injury patient comprises the age, sex and sports lifetime of the sports injury patient;
The method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain a red component reduction amplitude value when the baking is completed to reach the fixed time length, wherein the red component reduction amplitude value corresponds to each specific parameter combination and is output by the effect analysis model, and the red component reduction amplitude value comprises the following steps: executing the operation of the effect analysis model once for each specific parameter combination to obtain a red component drop amplitude corresponding to the specific parameter combination;
The value of the fixed time length is greater than or equal to a set duration threshold, the effect analysis model is a feedforward neural network after multiple times of training, the training times and the value of the set resolution are monotonically and positively correlated, and the individual information of the sports injury patient comprises the age, sex and sports lifetime duration of the sports injury patient, wherein the steps of: in each training of the feedforward neural network, taking a known red component descending amplitude value when a certain specific parameter combination of three parameters including a baking distance, a baking power and a baking time length of a set rehabilitation baking lamp is adopted to finish baking for a fixed time length as output content of the feedforward neural network, and taking each red component value, each green component value, each blue component value, the noise type number of a normalized conversion area, a signal-to-noise ratio, individual information of a sports injury patient and contrast of the specific parameter combination, the fixed time length and a directional captured image captured before baking as item-by-item input content of the feedforward neural network to finish the training operation;
Wherein, the human skin imaging region in the received orientation captured image is identified based on the brightness value distribution interval corresponding to the human skin and output as the target imaging region comprises: the brightness value distribution interval corresponding to the human skin is limited by a brightness value upper limit threshold value and a brightness value lower limit threshold value corresponding to the human skin, wherein the value of the brightness value upper limit threshold value is larger than that of the brightness value lower limit threshold value;
Wherein, the human skin imaging region in the received directional captured image is identified based on the brightness value distribution interval corresponding to the human skin and output as the target imaging region further comprises: taking pixel points, which are included in the directional captured image and have brightness values within a brightness value distribution interval corresponding to human skin, as skin formation pixel points, and taking pixel points, which are included in the directional captured image and have brightness values outside the brightness value distribution interval corresponding to human skin, as other pixel points;
Extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type number, the signal-to-noise ratio and the contrast of the received normalized conversion area includes: each of the constituent pixel points has a red component value, a green component value, and a blue component value in an RGB color space;
the method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude when the baking is completed and reaches the fixed time length, wherein the red component reduction amplitude corresponds to each specific parameter combination, and the red component reduction amplitude is output by the effect analysis model and comprises the following steps: each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast are respectively subjected to octave numerical conversion processing and then synchronously input into the effect analysis model;
the method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude when the baking is completed and reaches the fixed time length, wherein the red component reduction amplitude corresponds to each specific parameter combination, and the red component reduction amplitude is output by the effect analysis model and comprises the following steps: the effect analysis model is run to obtain the red component drop magnitude of the octave numerical representation of its output.
2. The athletic injury rehabilitation training method of claim 1, further comprising:
and performing multiple times of training on the feedforward neural network to obtain the feedforward neural network after multiple times of training, and outputting the feedforward neural network after multiple times of training as an effect analysis model.
3. A sports injury rehabilitation training system, the system comprising:
a data capturing device for performing a directed image data capturing action on a skin surface of a damaged portion of a sports damaged patient to obtain and output a corresponding directed captured image;
The segmentation processing device is connected with the data capturing device and is used for identifying a human skin imaging area in the received directional captured image based on a brightness value distribution interval corresponding to human skin and outputting the human skin imaging area as a target imaging area;
A signal conversion device connected to the segmentation processing device for performing image content normalization processing of the same resolution on the target imaging region to obtain a normalized conversion region having a set resolution;
The content detection device is connected with the signal conversion device and is used for extracting each red component value, each green component value and each blue component value which respectively correspond to each component pixel point in the received normalized conversion area, and analyzing the noise type quantity, the signal-to-noise ratio and the contrast of the received normalized conversion area;
The traversal analysis equipment is connected with the content detection equipment and used for synchronously inputting each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, the individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal-to-noise ratio and the contrast into the effect analysis model, and operating the effect analysis model to obtain the red component drop amplitude which is output by the effect analysis model and corresponds to each specific parameter combination when the baking is completed and reaches the fixed time length;
the optimal processing equipment is connected with the traversal analysis equipment and is used for taking specific parameter combinations of three parameters of the baking distance, the baking power and the baking time of the traversal setting rehabilitation baking lamp as the specific parameter combinations corresponding to the maximum value in the descending amplitude of each red component obtained by the input content of the effect analysis model as optimal parameter combinations;
The instant display device is connected with the preferential treatment device and is used for receiving three specific values corresponding to three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the preferential parameter combination;
Under the condition that the set rehabilitation baking lamp adopts a specific parameter combination to bake the damaged part of a patient with sports injury, taking the average value of red component values corresponding to the directional captured images captured when the baking is completed for a fixed time length as a second reference red component, and comparing the second reference red component with the descending amplitude value of the first reference red component as the descending amplitude value of the red component when the baking is completed for the fixed time length, wherein the descending amplitude value corresponds to the specific parameter combination;
The fixed time length value is greater than or equal to a set time length threshold value, the effect analysis model is a feedforward neural network which is trained for a plurality of times, the training times are monotonically and positively correlated with the set resolution value, and the individual information of the sports injury patient comprises the age, sex and sports lifetime of the sports injury patient;
The method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain a red component reduction amplitude value when the baking is completed to reach the fixed time length, wherein the red component reduction amplitude value corresponds to each specific parameter combination and is output by the effect analysis model, and the red component reduction amplitude value comprises the following steps: executing the operation of the effect analysis model once for each specific parameter combination to obtain a red component drop amplitude corresponding to the specific parameter combination;
The value of the fixed time length is greater than or equal to a set duration threshold, the effect analysis model is a feedforward neural network after multiple times of training, the training times and the value of the set resolution are monotonically and positively correlated, and the individual information of the sports injury patient comprises the age, sex and sports lifetime duration of the sports injury patient, wherein the steps of: in each training of the feedforward neural network, taking a known red component descending amplitude value when a certain specific parameter combination of three parameters including a baking distance, a baking power and a baking time length of a set rehabilitation baking lamp is adopted to finish baking for a fixed time length as output content of the feedforward neural network, and taking each red component value, each green component value, each blue component value, the noise type number of a normalized conversion area, a signal-to-noise ratio, individual information of a sports injury patient and contrast of the specific parameter combination, the fixed time length and a directional captured image captured before baking as item-by-item input content of the feedforward neural network to finish the training operation;
The instant display device is further used for displaying three specific values corresponding to three parameters of the baking distance, the baking power and the baking time of the set rehabilitation baking lamp corresponding to the optimal parameter combination in an instant mode;
Wherein, the human skin imaging region in the received orientation captured image is identified based on the brightness value distribution interval corresponding to the human skin and output as the target imaging region comprises: the brightness value distribution interval corresponding to the human skin is limited by a brightness value upper limit threshold value and a brightness value lower limit threshold value corresponding to the human skin, wherein the value of the brightness value upper limit threshold value is larger than that of the brightness value lower limit threshold value;
Wherein, the human skin imaging region in the received directional captured image is identified based on the brightness value distribution interval corresponding to the human skin and output as the target imaging region further comprises: taking pixel points, which are included in the directional captured image and have brightness values within a brightness value distribution interval corresponding to human skin, as skin formation pixel points, and taking pixel points, which are included in the directional captured image and have brightness values outside the brightness value distribution interval corresponding to human skin, as other pixel points;
Extracting each red component value, each green component value and each blue component value corresponding to each component pixel point in the received normalized conversion area, and analyzing the noise type number, the signal-to-noise ratio and the contrast of the received normalized conversion area includes: each of the constituent pixel points has a red component value, a green component value, and a blue component value in an RGB color space;
the method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude when the baking is completed and reaches the fixed time length, wherein the red component reduction amplitude corresponds to each specific parameter combination, and the red component reduction amplitude is output by the effect analysis model and comprises the following steps: each specific parameter combination of three parameters of the baking distance, the baking power and the baking time length of the traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, the fixed time length, individual information of the sports injury patient, the noise type number of the normalized conversion area, the signal to noise ratio and the contrast are respectively subjected to octave numerical conversion processing and then synchronously input into the effect analysis model;
the method comprises the steps of synchronously inputting each specific parameter combination of three parameters of a baking distance, a baking power and a baking time length of a traversal setting rehabilitation baking lamp, each red component value, each green component value, each blue component value, a fixed time length, individual information of a sports injury patient, the noise type number of a normalized conversion area, a signal to noise ratio and a contrast ratio into an effect analysis model, and operating the effect analysis model to obtain the red component reduction amplitude when the baking is completed and reaches the fixed time length, wherein the red component reduction amplitude corresponds to each specific parameter combination, and the red component reduction amplitude is output by the effect analysis model and comprises the following steps: the effect analysis model is run to obtain the red component drop magnitude of the octave numerical representation of its output.
4. The athletic injury rehabilitation training system of claim 3, further comprising:
The network reconstruction device is connected with the traversal analysis device and is used for performing multiple training on the feedforward neural network to obtain the feedforward neural network after multiple training;
the network reconstruction device is further used for sending the feedforward neural network after multiple times of training to the traversal analysis device as an effect analysis model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410147581.5A CN118053544B (en) | 2024-02-01 | 2024-02-01 | Exercise injury rehabilitation training method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410147581.5A CN118053544B (en) | 2024-02-01 | 2024-02-01 | Exercise injury rehabilitation training method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118053544A CN118053544A (en) | 2024-05-17 |
| CN118053544B true CN118053544B (en) | 2024-07-23 |
Family
ID=91053165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410147581.5A Active CN118053544B (en) | 2024-02-01 | 2024-02-01 | Exercise injury rehabilitation training method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118053544B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113223662A (en) * | 2021-02-03 | 2021-08-06 | 广东易生活信息科技有限公司 | Intelligent limb rehabilitation training method and system |
| CN114203275A (en) * | 2021-12-16 | 2022-03-18 | 江苏海洋大学 | Recovery state analysis system for rehabilitation training movement |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012135365A2 (en) * | 2011-03-29 | 2012-10-04 | Biolyst, Llc | Systems and methods for use in treating sensory impairment |
| US8861847B2 (en) * | 2012-12-21 | 2014-10-14 | Intel Corporation | System and method for adaptive skin tone detection |
| WO2015150931A1 (en) * | 2014-04-03 | 2015-10-08 | Universiti Brunei Darussalam | Realtime biofeedback mechanism and data presentation for knee injury rehabilitation monitoring and a soft real time intelligent system thereof |
| WO2021014149A1 (en) * | 2019-07-22 | 2021-01-28 | Virtihealth Limited | Methods and systems for musculoskeletal rehabilitation |
| CN218652751U (en) * | 2022-08-11 | 2023-03-21 | 中实创科技（广东）有限公司 | A physiotherapy lamp for promoting skeleton is restoreed |
| CN116486996A (en) * | 2023-04-17 | 2023-07-25 | 西安力邦康迈德医疗科技有限公司 | Device for rehabilitation training and assessment |
| CN116650914A (en) * | 2023-05-09 | 2023-08-29 | 重庆电子工程职业学院 | Multi-information fusion upper limb active and passive rehabilitation training robot system |
-
2024
- 2024-02-01 CN CN202410147581.5A patent/CN118053544B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113223662A (en) * | 2021-02-03 | 2021-08-06 | 广东易生活信息科技有限公司 | Intelligent limb rehabilitation training method and system |
| CN114203275A (en) * | 2021-12-16 | 2022-03-18 | 江苏海洋大学 | Recovery state analysis system for rehabilitation training movement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118053544A (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR20180114692A (en) | Brain training simulation system based on behavior modeling | |
| Pau et al. | Quantitative assessment of the effects of 6 months of adapted physical activity on gait in people with multiple sclerosis: a randomized controlled trial | |
| CN110993056A (en) | Hybrid active rehabilitation method and device based on mirror image neurons and brain-computer interface | |
| CN1803122A (en) | Method for producing rehabilitation exerciser controlling order using imagination movement brain wave | |
| Chen et al. | EEG-controlled functional electrical stimulation rehabilitation for chronic stroke: system design and clinical application | |
| CN107096127A (en) | Control output current intensity method and can adjustment threshold value electric stimulation therapeutic apparatus | |
| CN114469641A (en) | Functional electrical stimulation dyskinesia mirror image training method based on myoelectric recognition | |
| KR20160139960A (en) | Obesity Management System based on World Wide Web | |
| WO2023236667A1 (en) | Surface electromyographic value-based rehabilitation level quantification method and rehabilitation system | |
| McHugh et al. | Epidural spinal cord stimulation for motor recovery in spinal cord injury: A systematic review | |
| CN115607802A (en) | Method, system and device for autonomic nerve function regulation and intervention | |
| EP3782546B1 (en) | Method for identifying an acupuncture point and/or a meridian | |
| CN118053544B (en) | Exercise injury rehabilitation training method and system | |
| CN1887222A (en) | Chinese medicine meridian health detecting system | |
| US10799174B1 (en) | System and methods to track and increase muscle efficiency | |
| CN117547731A (en) | Mirror neuron and neuromuscular electrical stimulation combined rehabilitation assessment training system | |
| CN113713333A (en) | Dynamic virtual induction method and system for lower limb rehabilitation full training process | |
| CN114420249B (en) | Exercise rehabilitation course management method based on action labels | |
| CN110739083A (en) | Comprehensive evaluation method and device for enhancing rehabilitation training effect, storage medium and equipment | |
| WO2022120913A1 (en) | Brain injury electroencephalogram neural oscillation analysis system and method | |
| KR100456038B1 (en) | The bio-feedback system | |
| Drużbicki et al. | The use of a treadmill with biofeedback function in assessment of relearning walking skills in post-stroke hemiplegic patients–a preliminary report | |
| CN112156361A (en) | Portable pelvic floor rehabilitation instrument with internet of things function and using method | |
| CN113869084B (en) | Electroencephalogram signal processing method, brain-computer interface device, and storage medium | |
| Song et al. | Design of a Wireless Distributed Real-time Muscle Fatigue Detection System |
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 |