Muscle compensation assessment method
By capturing and analyzing images of the test subject's movements using a camera, muscle compensation is assessed, solving the problem that existing technologies cannot effectively assess muscle compensation. This enables scoring of muscle compensation and movement correction, thereby improving training effectiveness.
Patent Information
- Application Number
- CN202310664732.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-06
- Publication Date
- 2025-11-25
- Estimated Expiration
- 2043-06-06
AI Technical Summary
Existing technologies lack effective methods for assessing muscle compensation, making it impossible to specifically evaluate muscle compensation, which leads to deformed movement patterns and muscle damage.
The system uses a camera to capture images of the test subject performing preset test actions, classifies and breaks down compensatory actions, extracts spatial coordinate data of joint markers, calculates scores for compensatory actions and muscles, and forms a scoring mechanism.
It enables the scoring of muscles involved in compensatory movements, visually displays the assessment results, helps test subjects to target specific muscles for training, avoid muscle damage, and improve training efficiency.
Smart Images

Figure CN116616752B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of motion correction technology, and in particular to a method for assessing muscle compensation. Background Technology
[0002] Muscle compensation can be understood as muscle substitution, meaning that when the body needs to perform a certain movement, the muscles that should be performing their function cannot do so properly, causing other muscles to take over and compensate for the lost function. There are two types of muscle compensation: one is synergistic muscle compensation, where when the agonist muscle becomes weak due to poor habits, the synergistic muscles are forced to exert force to support the movement; the other is irrelevant muscle compensation, such as when performing lat pulldowns to train the back, if the latissimus dorsi is too weak, it's easy to complete the movement by shrugging the shoulders and relying on the trapezius muscles. The harms of muscle compensation include: distorted movement patterns, making it impossible to achieve training goals; causing body pain; and causing muscle damage.
[0003] Currently, there are few methods for scoring muscles in compensatory movements, and most are tests for correcting erroneous movements, failing to specifically evaluate the muscles involved. For example, invention patent CN110664404B discloses a trunk compensation detection and elimination system based on surface electromyography signals, and invention patent application CN115984957A discloses a recognition method and system for detecting movements and postures. Both of these patents are limited by the testing and recognition instruments, lack a scoring mechanism, and cannot intuitively display the test results. Summary of the Invention
[0004] In view of this, embodiments of the present invention provide a muscle compensation assessment method capable of scoring the muscles involved in compensatory movements.
[0005] A method for assessing muscle compensation includes:
[0006] Acquire human images of the test subject performing preset test actions, captured by a camera;
[0007] The compensatory movements that occur when the test subject performs the preset test action are classified, and the compensatory movements are broken down to obtain the muscles corresponding to the compensatory movements in each category.
[0008] Extract the spatial coordinate data of the test subject's body joint markers from the human image;
[0009] Calculate the score of the compensatory action based on the spatial coordinate data;
[0010] Based on the score of the compensatory action, calculate the score of the muscle corresponding to the compensatory action;
[0011] The muscles responsible for compensatory movements are evaluated based on their scores.
[0012] Furthermore, the classification includes two categories: muscle tension and muscle weakness.
[0013] Furthermore, the preset test action includes at least one of the following: wall angel and overhead squat.
[0014] Furthermore, under the category of muscle tension, the compensatory movements involved in the Angel on the Wall include: shrugging, arm forward movement, and elbow flexion. At this time, the muscles corresponding to shrugging include the sternocleidomastoid and upper trapezius, the muscles corresponding to arm forward movement include the latissimus dorsi and pectoralis major, and the muscles corresponding to elbow flexion include the biceps brachii, latissimus dorsi, and triceps brachii.
[0015] In the category of muscle weakness, the compensatory movements involved in the "Angel on the Wall" exercise include: shrugging, arm extension, and elbow flexion. In this case, the muscles involved in shrugging include the lower trapezius, the muscles involved in arm extension include the teres minor, supraspinatus, subscapularis, lower trapezius, and infraspinatus, and the muscles involved in elbow flexion include the teres minor, supraspinatus, subscapularis, lower trapezius, and infraspinatus.
[0016] Furthermore, under the category of muscle tension, the compensatory movements involved in overhead squats include: arm drop forward, center of gravity shift, excessive forward lean, knee lateral displacement, and knee valgus. At this time, the muscles corresponding to the arm drop forward include the pectoralis major, pectoralis minor, latissimus dorsi, and teres major; the muscles corresponding to the center of gravity shift include the gluteus medius and tensor fasciae latae; the muscles corresponding to excessive forward lean include the piriformis, iliopsoas, rectus abdominis, soleus, external oblique, gastrocnemius, and rectus femoris; the muscles corresponding to knee lateral displacement include the gluteus minimus, biceps femoris, tensor fasciae latae, and piriformis; and the muscles corresponding to knee valgus include the vastus lateralis, adductor magnus, gastrocnemius, adductor longus, tensor fasciae latae, adductor brevis, biceps femoris, and pectineus.
[0017] In the category of muscle weakness, the compensatory movements involved in overhead squats include: arm drop forward, weight shift, excessive forward lean, knee lateral movement, and knee valgus. At this time, the muscles corresponding to the arm drop forward include the teres minor, posterior deltoid, subscapularis, rhomboids, infraspinatus, lower trapezius, and supraspinatus. The muscles corresponding to the weight shift include the adductor magnus, pectineus, adductor longus, gluteus medius, and adductor brevis. The muscles corresponding to excessive forward lean include the internal oblique, gluteus maximus, erector spinae, and tibialis anterior. The muscles corresponding to knee lateral movement include the gluteus maximus, adductor longus, semimembranosus, adductor brevis, adductor magnus, and pectineus. The muscles corresponding to knee valgus include the tibialis anterior, gluteus maximus, vastus medialis, gastrocnemius, gluteus medius, and semimembranosus.
[0018] Furthermore, the joint markers include at least 16 markers, namely: head, neck, spine shoulder position, left / right shoulder, left / right elbow, left / right wrist, sacrum, left / right hip, left / right knee, and left / right ankle.
[0019] Furthermore, calculating the score of the muscle corresponding to the compensatory action based on the score of the compensatory action includes:
[0020] The preset value for each muscle is added to the score of the corresponding compensatory movement to obtain the score for each muscle.
[0021] Furthermore, the step of adding the preset value of each muscle to the score of the corresponding compensatory movement to obtain the score of each muscle is further described as follows:
[0022] Multiply the preset assignment coefficient by the preset assignment value of each muscle, and add it to the score of the corresponding compensatory movement to obtain the score of each muscle.
[0023] Furthermore, the assessment of the compensatory muscles based on the muscle scores includes:
[0024] Summarize and sort the scores of all muscles;
[0025] The top N muscles in the muscle tension category are classified as muscle tension, and the top N muscles in the muscle weakness category are classified as muscle weakness.
[0026] Furthermore, the process of summarizing and sorting the scores of all muscles includes:
[0027] For the same muscle group, take the average value.
[0028] The present invention establishes a scoring mechanism that can score the muscles involved in compensatory movements and intuitively display the evaluation results. This allows test subjects to target their muscle training, avoid muscle damage caused by muscle compensation, and improve training efficiency. Attached Figure Description
[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0030] Figure 1 This is a flowchart illustrating the muscle compensation assessment method of the present invention.
[0031] Figure 2 This is a schematic diagram showing the location of the joint markers on the test subject's body in this invention;
[0032] Figure 3 This is a flowchart illustrating the specific process of muscle compensation assessment in this invention. Detailed Implementation
[0033] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0034] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0035] This invention provides a method for assessing muscle compensation, such as... Figure 1 As shown, it includes:
[0036] Step 1: Acquire human images of the test subject performing preset test actions captured by the camera;
[0037] In this step, a frontal human image of the test subject performing a preset test action is captured by a camera. This camera can be a regular 2D camera or a depth camera with 3D functionality.
[0038] The preset test movements can include at least one of the following: angel on the wall and overhead squat. In practice, the test subject can perform three repetitions of both the overhead squat and the angel on the wall. The test subject starts standing upright facing the instrument, 3 meters away, and follows the voice prompts to perform the movement test. ① Overhead Squat: The test subject stands upright with feet shoulder-width apart and toes pointing forward. Raise both arms overhead until elbows are fully extended. Arms should be raised to the sides of the torso. Slowly squat down to approximately chair height, then return to the starting position. ② Angel on the Wall: The test subject stands with feet shoulder-width apart, arms extended horizontally outward, elbows bent at 90 degrees, then raises them until elbows are fully extended.
[0039] Step 2: Classify the compensatory movements that occur when the test subject performs the preset test action, and break down the compensatory movements to obtain the muscles corresponding to the compensatory movements in each category;
[0040] In this step, the compensatory movements that occur when the test subject performs the preset test action are classified. As an optional embodiment, the classification may include two categories: muscle tension and muscle weakness. Then, the compensatory movements are broken down to obtain the muscles corresponding to the compensatory movements in each category.
[0041] Angels on the Wall
[0042] The compensatory movements observed in the "Angel on the Wall" exercise are categorized into two main types: shoulder shrugs, forward arm movements, and elbow flexions. These are further divided into two categories: muscle tension and muscle weakness. The compensatory movements are then broken down further. Details are as follows:
[0043] Under the category of muscle tension, the compensatory movements involved in the Angel on the Wall include: shrugging, arm extension, and elbow flexion. At this time, the muscles involved in shrugging include the sternocleidomastoid and upper trapezius, the muscles involved in arm extension include the latissimus dorsi and pectoralis major, and the muscles involved in elbow flexion include the biceps brachii, latissimus dorsi, and triceps brachii.
[0044] In the category of muscle weakness, the compensatory movements involved in the "Angel on the Wall" exercise include: shrugging, arm extension, and elbow flexion. The muscles involved in shrugging include the lower trapezius; the muscles involved in arm extension include the teres minor, supraspinatus, subscapularis, lower trapezius, and infraspinatus; and the muscles involved in elbow flexion include the teres minor, supraspinatus, subscapularis, lower trapezius, and infraspinatus. See Table 1.
[0045] Table 1. Angelic Compensation Movements on the Wall and the Muscles Involved
[0046]
[0047] Overhead squat
[0048] Compensatory movements occurring during overhead squats are categorized as follows: arm drop forward, weight shift, excessive forward lean, knee lateral displacement, and knee valgus. These are further divided into two main categories: muscle tension and muscle weakness. The compensatory movements are then broken down further. Details are as follows:
[0049] Under the category of muscle tension, the compensatory movements involved in overhead squats include: arm drop forward, center of gravity shift, excessive forward lean, knee lateral displacement, and knee valgus. At this time, the muscles corresponding to the arm drop forward include the pectoralis major, pectoralis minor, latissimus dorsi, and teres major; the muscles corresponding to the center of gravity shift include the gluteus medius and tensor fasciae latae; the muscles corresponding to excessive forward lean include the piriformis, iliopsoas, rectus abdominis, soleus, external oblique, gastrocnemius, and rectus femoris; the muscles corresponding to knee lateral displacement include the gluteus minimus, biceps femoris, tensor fasciae latae, and piriformis; and the muscles corresponding to knee valgus include the vastus lateralis, adductor magnus, gastrocnemius, adductor longus, tensor fasciae latae, adductor brevis, biceps femoris, and pectineus.
[0050] Under the category of muscle weakness, the compensatory movements involved in overhead squats include: arm drop forward, weight shift, excessive forward lean, knee lateral movement, and knee valgus. The muscles involved in arm drop forward include the teres minor, posterior deltoid, subscapularis, rhomboids, infraspinatus, lower trapezius, and supraspinatus. The muscles involved in weight shift include the adductor magnus, pectineus, adductor longus, gluteus medius, and adductor brevis. The muscles involved in excessive forward lean include the internal oblique, gluteus maximus, erector spinae, and tibialis anterior. The muscles involved in knee lateral movement include the gluteus maximus, adductor longus, semimembranosus, adductor brevis, adductor magnus, and pectineus. The muscles involved in knee valgus include the tibialis anterior, gluteus maximus, vastus medialis, gastrocnemius, gluteus medius, and semimembranosus. (See Table 2.)
[0051] Table 2 Compensatory Movements of Overhead Squats and the Muscles Involved Step 3: Extract the spatial coordinate data of the test subject's body joint markers from the human image;
[0052] In this step, a visual recognition system can be used to extract the spatial coordinate data (including the coordinates of joint markers in both static and dynamic states during movement) corresponding to the time series of the test subject's body joint markers from the human image. The specific extraction method can adopt conventional techniques in this field, which will not be elaborated here.
[0053] As an optional embodiment, the joint markers may include at least 16 markers, namely: head, neck, spine shoulder position, left / right shoulder, left / right elbow, left / right wrist, sacrum, left / right hip, left / right knee, and left / right ankle.
[0054] The extracted spatial coordinate data can be, for example, as follows:
[0055] ι i =(x i y i Let R(x,y) represent the coordinates of the i-th joint marker. The set of joint markers for the test subject is represented as R(x,y). Spatial coordinate data of 16 joint markers from each time series of human images were collected during the test.
[0056] The joint markers and numbers of the test subjects can be shown in Table 3 and Figure 2 As shown.
[0057] Table 3 Joint Markers and Numbers
[0058] serial number Marker point serial number Marker point 0 head 8 right wrist 1 neck 9 Sacrum 2 Spine and shoulder position 10 Left hip 3 left shoulder 11 left knee 4 left elbow 12 left ankle 5 left wrist 13 Right hip 6 right shoulder 14 right knee 7 right elbow 15 Right ankle
[0059] The joint markers defined in this invention typically correspond to joints or bony landmarks on the human body with a certain degree of freedom. The current state of the human body is estimated by calculating the relative positions of key points in space. Due to the special nature of the human body structure, the lines connecting the markers are only connected by the human body structure.
[0060] To improve the accuracy of subsequent evaluations, the extracted spatial coordinate data can be preprocessed as follows:
[0061] After marker point identification, data denoising is first performed using wavelet thresholding. Then, based on the marker point coordinates and time series, the marker point acceleration is obtained. According to the upper limit of human acceleration and expert discussions, a new data limit is set; if the limit is exceeded, the data is deleted. These two processes result in a marker point sequence that better reflects the human body.
[0062] Step 4: Calculate the score of the compensatory action based on the spatial coordinate data;
[0063] In this step, the compensatory action can be scored by identifying joint markers and performing logical calculations. The specific calculation method is shown in Table 4-5.
[0064] Table 4. Judgment Logic of Compensatory Action Scores
[0065]
[0066]
[0067] The scoring rules for compensatory actions are shown in the table below:
[0068] Table 5 Scoring Rules for Compensatory Actions
[0069]
[0070]
[0071] Note: X in "Intermediate Value Range" of Table 5 is the final value obtained in "Judgment Logic" of Table 4.
[0072] Step 5: Calculate the score of the muscle corresponding to the compensatory action based on the score of the compensatory action;
[0073] As an optional embodiment, the step of calculating the score of the muscle corresponding to the compensatory action based on the score of the compensatory action (step 5) may include:
[0074] The preset value for each muscle is added to the score of the corresponding compensatory movement to obtain the score for each muscle.
[0075] In practice, the score F for each muscle is: F = X + x, where X is the score of the corresponding compensatory movement, and x is a preset value for each muscle. The preset value for each muscle can be flexibly set as needed, as shown in the table below:
[0076] Table 6: Assignment of Angel Muscles on the Wall
[0077]
[0078] Table 7 Muscle Assignments for Overhead Squat
[0079]
[0080] To make the score for each muscle more accurate, the process of adding the preset value of each muscle to the score of the corresponding compensatory movement to obtain the score for each muscle can be further described as follows:
[0081] Multiply the preset assignment coefficient by the preset assignment value of each muscle, and add it to the score of the corresponding compensatory movement to obtain the score of each muscle.
[0082] In practice, the preset assignment coefficient can be flexibly set as needed, for example, 0.01. At this time, the score F of each muscle is: F = X + 0.01 * x, where X is the score of the corresponding compensatory action and x is the preset assignment for each muscle.
[0083] In one example, the wall angel muscle scores are shown in Table 8, where L represents the left side and R represents the right side.
[0084] Table 8. Muscle Scoring for Angel Compensation Movements on the Wall
[0085]
[0086] In one example, the muscle score for overhead squats is shown in Table 9:
[0087] Table 9 Muscle Scoring for Overhead Squat Compensatory Movements
[0088]
[0089]
[0090] Step 6: Evaluate the compensatory muscles based on the muscle scores.
[0091] As an optional embodiment, the assessment of the compensatory muscles based on the muscle scores (step 6) may include:
[0092] Step 61: Summarize and sort the scores of all muscles;
[0093] The previous steps yielded scores for the muscles corresponding to each compensatory movement. This step summarizes and sorts these muscle scores. In practice, the average score can be used for the same muscle.
[0094] Step 62: Rank the top N muscles in the muscle tension category as muscle tension, and rank the top N muscles in the muscle weakness category as muscle weakness.
[0095] In this step, N is an integer and can take any value as needed, such as 3, 4, 5, etc. In the example above, the top 3 muscles can be selected as those with muscle tension or insufficient strength for display, resulting in the muscles finally displayed as shown in Table 10. At this point, the specific flowchart for muscle compensation assessment in this invention can be as follows: Figure 3 As shown.
[0096] Table 10 Output Muscles
[0097]
[0098] In summary, the muscle compensation assessment method of this invention first acquires human images of a test subject performing a preset test action captured by a camera. The compensatory movements occurring during the test subject's performance of the preset test action are then categorized and broken down to obtain the muscles corresponding to each category. Next, spatial coordinate data of the test subject's joint markers are extracted from the human images. Based on the spatial coordinate data, a score for the compensatory movement is calculated. Then, based on the score of the compensatory movement, a score for the corresponding muscle is calculated. Finally, based on the muscle scores, the compensatory movement muscles are evaluated. Specifically, this invention uses a camera for motion recognition to evaluate preset test actions such as overhead squats and wall angels, breaking them down to obtain muscle compensation scores, ultimately displaying muscles with tension and insufficient strength. Thus, this invention forms a scoring mechanism that can score the muscles involved in compensatory movements, intuitively displaying the evaluation results. This allows test subjects to target their muscle training, avoid muscle damage caused by muscle compensation, and improve training efficiency.
[0099] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for assessing muscle compensation, characterized in that, include: Acquire human images of the test subject performing preset test actions, captured by a camera; The compensatory movements that occur when the test subject performs the preset test action are classified and the compensatory movements are broken down to obtain the muscles corresponding to the compensatory movements in each category. The classification includes two categories: muscle tension and muscle weakness. Extract the spatial coordinate data of the test subject's body joint markers from the human image; Calculate the score of the compensatory action based on the spatial coordinate data; Based on the score of the compensatory action, calculate the score of the muscle corresponding to the compensatory action; The compensatory muscles are evaluated based on their scores. The step of calculating the score of the muscle corresponding to the compensatory action based on the score of the compensatory action includes: Multiply the preset assignment coefficient by the preset assignment of each muscle, and add it to the score of the corresponding compensatory movement to obtain the score of each muscle. The assessment of compensatory muscles based on their scores includes: Summarize and sort the scores of all muscles; The top N muscles in the muscle tension category are classified as muscle tension, and the top N muscles in the muscle weakness category are classified as muscle weakness.
2. The method according to claim 1, characterized in that, The preset test actions include at least one of the following: angel on the wall and overhead squat.
3. The method according to claim 2, characterized in that, Under the category of muscle tension, the compensatory movements involved in the Angel on the Wall include: shrugging, arm extension, and elbow flexion. At this time, the muscles involved in shrugging include the sternocleidomastoid and upper trapezius, the muscles involved in arm extension include the latissimus dorsi and pectoralis major, and the muscles involved in elbow flexion include the biceps brachii, latissimus dorsi, and triceps brachii. In the category of muscle weakness, the compensatory movements involved in the "Angel on the Wall" exercise include: shrugging, arm extension, and elbow flexion. In this case, the muscles involved in shrugging include the lower trapezius, the muscles involved in arm extension include the teres minor, supraspinatus, subscapularis, lower trapezius, and infraspinatus, and the muscles involved in elbow flexion include the teres minor, supraspinatus, subscapularis, lower trapezius, and infraspinatus.
4. The method according to claim 2, characterized in that, Under the category of muscle tension, the compensatory movements involved in overhead squats include: arm drop forward, center of gravity shift, excessive forward lean, knee lateral displacement, and knee valgus. At this time, the muscles corresponding to the arm drop forward include the pectoralis major, pectoralis minor, latissimus dorsi, and teres major; the muscles corresponding to the center of gravity shift include the gluteus medius and tensor fasciae latae; the muscles corresponding to excessive forward lean include the piriformis, iliopsoas, rectus abdominis, soleus, external oblique, gastrocnemius, and rectus femoris; the muscles corresponding to knee lateral displacement include the gluteus minimus, biceps femoris, tensor fasciae latae, and piriformis; and the muscles corresponding to knee valgus include the vastus lateralis, adductor magnus, gastrocnemius, adductor longus, tensor fasciae latae, adductor brevis, biceps femoris, and pectineus. In the category of muscle weakness, the compensatory movements involved in overhead squats include: arm drop forward, weight shift, excessive forward lean, knee lateral movement, and knee valgus. At this time, the muscles corresponding to the arm drop forward include the teres minor, posterior deltoid, subscapularis, rhomboids, infraspinatus, lower trapezius, and supraspinatus. The muscles corresponding to the weight shift include the adductor magnus, pectineus, adductor longus, gluteus medius, and adductor brevis. The muscles corresponding to excessive forward lean include the internal oblique, gluteus maximus, erector spinae, and tibialis anterior. The muscles corresponding to knee lateral movement include the gluteus maximus, adductor longus, semimembranosus, adductor brevis, adductor magnus, and pectineus. The muscles corresponding to knee valgus include the tibialis anterior, gluteus maximus, vastus medialis, gastrocnemius, gluteus medius, and semimembranosus.
5. The method according to claim 1, characterized in that, The joint markers include at least 16 markers, namely: head, neck, spine shoulder position, left / right shoulder, left / right elbow, left / right wrist, sacrum, left / right hip, left / right knee, and left / right ankle.
6. The method according to claim 1, characterized in that, The scores of all muscles are summarized and sorted, including averaging the scores of the same muscle.
Citation Information
Patent Citations
A system for detecting and eliminating trunk compensation based on surface electromyography signals
CN110664404B
Recognition method and system for motion and posture detection
CN115984957A
Exercising apparatus
CN101850172A
Method, system, program and computer device for identifying site of cause of compensatory movement, and method and system for eliminating compensatory movement
CN109843170A
Body health assessment method based on joint point recognition
CN115497626A