TWI821772B - Muscle state detection method and muscle state detection device using the same - Google Patents

Abstract

A muscle state detection method and a muscle state detection deviceusing the same are provided. The muscle state detection method is implemented by the muscle state detection device. The muscle state detection method includes the following steps. A plurality of detection actions are provided according to a user data. Each of the detection actions corresponds to a plurality of detection items. Each of the detection items corresponds to a plurality of muscles. A description information of each of the detection actions is displayed. A motion image of the user performing each of the detection actions is captured. A plurality of nodes are identified in each of the motion images. A detection result of each of the detection items is analyzed. The detection results of the detection items are combined to evaluate a muscle state information of the muscles.

Description

Muscle condition detection method and muscle condition detection device using the same set

The present disclosure relates to a muscle condition detection method and a muscle condition detection device using the same.

As the population ages, empowering exercise to maintain physical function is in high demand. Moreover, modern people pay attention to health and fitness, and fitness exercises are also very popular. Generally speaking, the elderly can perform empowering exercises through the guidance of physical therapists. Young people can also practice fitness exercises through the guidance of fitness coaches. However, different physical therapists and fitness coaches often have different assessment results on the correctness of movements, making it difficult to give the most appropriate training recommendations for muscle condition.

The smart training equipment currently launched in the industry mainly detects the movement posture of the subject to evaluate the correctness of the movement. However, equipment in this area only uses image recognition technology to compare single action postures. The correctness of a single action posture is affected by quite a few muscular factors. Difficulty in correctness from a single posture In order to understand the overall muscle condition information of the subject, it is more difficult to give the most appropriate muscle condition training suggestions.

The present disclosure relates to a muscle condition detection method and a muscle condition detection device using the same.

According to one aspect of the present disclosure, a muscle condition detection device is provided. The muscle condition detection device includes a detection action providing unit, a display unit, an image capture unit, a node identification unit, an item analysis unit and a muscle evaluation unit. The detection action providing unit is used to provide several detection actions based on a subject's data. Each detection action corresponds to several detection items. Each test item corresponds to several muscles. The display unit is used to display prompt information for each detection action. The image capture unit is used to capture action images of the subject performing each detection action. The node identification unit is used to identify several nodes in each action image. The item analysis unit is used to analyze the test results of one of each test item. The muscle assessment unit is used to synthesize the test results of these test items to evaluate muscle condition information of one of these muscles.

According to another aspect of the present disclosure, a muscle condition detection method is provided. The muscle condition detection method is performed by a muscle condition detection device. The muscle condition testing method includes the following steps. According to a subject's information, several detection actions are provided, and each detection action corresponds to several detection items. Each test item corresponds to several muscles. Display prompt information for each detection action. Capture the action images of the subject performing one of each detection action. Several nodes are identified in each action image. Analysis of the The test result of one of each test item. The test results from these tests are combined to evaluate muscle condition information for one of these muscles.

According to another aspect of the present disclosure, a graphical user interface of a muscle condition detection device is provided. A muscle condition detection device includes a display unit. The graphical user interface is displayed on the display unit. The graphical user interface includes a front human figure and a back human figure. The frontal figure features several frontal muscle tiles. The back figure features several back muscle tiles. The content of each front muscle tile and each back muscle tile is related to a muscle condition information.

In order to have a better understanding of the above and other aspects of the present disclosure, embodiments are given below and described in detail with reference to the accompanying drawings:

100: Muscle condition detection device

110:Input unit

120: Detection action providing unit

130:Display unit

140:Image capture unit

150: Node identification unit

160:Project analysis unit

170:Muscle Assessment Unit

180: Training program provision unit

190:Storage unit

700: Graphical user interface

710: Frontal human figure

720: Human figure on the back

900: Subject

Ai,A1,A2,A3: detect action

B1: Frontal muscle block

B2: Back muscle block

D1: Predetermined distance

D9: moving distance

DB1: Action database

DFi: prompt information

Eij,E11,E12,E13,E21,E22,E23,E31,E32,E41,E72,E73: Test items

HT: Host

IMi: Action Image

MD1: Pre-training mode

MD2: Post-training mode

MF:Muscle condition information

Mk,M1,M2,M3,M4,M5,M6,M7,M8,M9: Muscle

Nim: node

Rij: test results

S110, S120, S130, S140, S150, S160, S170, S180: Steps

SDij: standard range

St,S1,S3,S5: Muscle condition training program

T9: time

UD: subject data

WL: screen

Wijk: weight information

θ: included angle

Figure 1 is a schematic diagram of a muscle condition detection device according to an embodiment.

Figure 2 shows an example of detection actions, detection items, muscles, muscle condition information, Cross-relationship with muscle condition training programs.

Figure 3 illustrates a block diagram of a muscle condition detection device according to an embodiment.

Figure 4 illustrates a flow chart of a muscle condition detection method according to an embodiment.

Figure 5 illustrates the top view structure of the muscle condition detection device.

Figure 6 illustrates step S110.

Figure 7 illustrates step S120.

Figures 8A to 8C illustrate step S130.

Figures 9A to 9C illustrate step S140.

Figure 10 illustrates step S150.

Figures 11A to 11C illustrate step S160.

Figure 12A illustrates step S170.

Figure 12B illustrates the results of a comprehensive muscle assessment.

Figure 13 illustrates the graphical use of the muscle condition detection device according to one embodiment. User interface.

Figure 14 illustrates step S180.

Please refer to FIG. 1 , which illustrates a schematic diagram of a muscle condition detection device 100 according to an embodiment. The muscle condition detection device 100 can display a screen, accept input of information, and capture images. In this embodiment, the muscle condition detection device 100 can provide a variety of detection actions Ai (shown in Figure 2). When the subject 900 performs these detection actions Ai, the muscle condition detection device 100 can detect individual detection items Eij (shown in Figure 2), and comprehensively evaluate the muscle condition information MF (shown in Figure 2) of the subject 900 Picture 2). Muscle condition information MF refers to the tightness of muscles connected to human bones, which can be divided into three conditions: weak, normal and too tight. In one embodiment, the muscle condition information MF is, for example, muscle strength information. Muscles attached to the body's bones receive messages from the nervous system to contract or relax. Long-term fixed movements, compensatory force application (excessive muscle compression) and other factors can easily cause the muscles on the force-applying side to be too tight and the muscles on the antagonistic side to be weak. For example, long-term Muscles that are stretched and chronically shortened are essentially "tight" conditions. It is possible that the muscles may become tight due to long-term shortening, which is a condition of muscle overtightness. It is also possible that the muscles become tight due to long-term stretching, which is a condition of muscle weakness.

The muscle condition detection device 100 does not simply inform the subject 900 of the correctness of the detection action Ai, but comprehensively evaluates the subject based on the interlaced relationship between multiple detection actions Ai and numerous muscles Mk (shown in Figure 2). 900 Muscle Condition Information MF.

For example, please refer to Figure 2, which illustrates the interlaced relationship between the detection action Ai, the detection item Eij, the muscle Mk, the muscle condition information MF, and the muscle condition training plan St. As shown in Figure 2, the detection actions A1, A2, A3, ... are, for example, "front standing", "standing on one leg", "side standing", "side standing reaching forward", "squatting", " "Sitting and side stretching", "shoulder lift", "sitting and side stretching", etc. Detection action A1 corresponds to multiple detection items E11, E12, E13,...; detection action A2 corresponds to multiple detection items E21, E22, E23,...; detection action A3 corresponds to multiple detection items E31, E32,... .. Test items E11, E12, E13, E21, E22, E23, E31, E32,...for example, "head deflection", "balance between the two", "pelvic balance", "knee bend", "hip center of gravity deviation" "Move" etc. Detection item E11 is related to muscles M1 and M2; detection item E12 is related to muscles M3 and M4; detection item E13 is related to muscles M2 and M4; the rest are as shown in the figure. Muscle M1 corresponding to test item E11, M2 partially overlaps with the muscles M2 and M4 corresponding to test item E13; the rest are as shown in the figure.

Muscle M2 corresponds to various test items E11, E13, and E21; muscle M3 corresponds to various test items E12, E22, E23, E31, and E32; the rest are as shown in the figure. Muscle M2 corresponds to multiple detection actions A1 and A2; muscle M3 corresponds to multiple detection actions A1, A2 and A3; the rest are as shown in the figure. In one embodiment, the muscle Mk may be the same or adjacent muscle group with the same function. For example, the muscle Mk is an adductor muscle group, and the adductor muscle group includes the adductor major, the adductor brevis, and the adductor longus. , and pectineus muscle and gracilis muscle; in another embodiment, muscle Mk can be a single muscle, such as one of the left pectoralis major muscle or the right pectoralis major muscle.

In this embodiment, the muscles of the subject 900 can be comprehensively evaluated based on the interlaced relationship between multiple detection actions A1, A2, A3, ... and numerous muscles M1, M2, M3, M4, M5, ... Status information MF. As shown in Figure 2, the tight muscles are muscles M1, M4,...; the normal muscles are muscles M2, M3,...; the weak muscles are muscles M5,...

With the muscle condition information MF, you can provide suitable muscle condition training programs S1, S4, S5, based on the tight muscles M1, M4,... and weak muscles M5,... of the muscle condition information MF. .... The muscle condition detection method and the muscle condition detection device 100 using it will be described in detail below with a block diagram and a flow chart.

Please refer to Figures 3 to 4. Figure 3 illustrates a block diagram of the muscle condition detection device 100 according to one embodiment. Figure 4 illustrates a muscle condition detection device 100 according to one embodiment. Flowchart of condition detection method. The muscle condition detection device 100 includes an input unit 110, a detection action providing unit 120, a display unit 130, an image capture unit 140, a node identification unit 150, an item analysis unit 160, a muscle evaluation unit 170, and a training unit. Solution providing unit 180 and a storage unit 190. The input unit 110 is used for the subject 900 to input data, such as a card reader, a touch panel, a keyboard, a stylus, a gesture sensor device, a voice input device, or a fingerprint reading device. The display unit 130 is used to display information, such as a display panel, a projector, or an AR/VR glasses. The image capturing unit 140 is used to capture images, such as a black and white camera, a color camera, a depth camera, or a video camera. The storage unit 190 is used to store data, such as a hard drive, a pen drive, a memory card, a memory or a cloud data center. The detection action providing unit 120, the node identification unit 150, the item analysis unit 160, the muscle evaluation unit 170 and/or the training program providing unit 180 are used to perform various analysis procedures, such as a circuit, a chip, a circuit board, and a computer program. A product, a program, or a storage device that stores a computer program product or program code. The detection action providing unit 120, the node identification unit 150, the item analysis unit 160, the muscle evaluation unit 170 and the training plan providing unit 180 can be several separate components, or they can be integrated into the same component, such as a processing module. In one embodiment, the processing module includes a processing chip.

Please refer to FIG. 5 , which illustrates an example of the top view structure of the muscle condition detection device 100 . The image capturing unit 140 is, for example, disposed above the display unit 130 . For example, a host HT is disposed behind the display unit 130 and includes the detection action providing unit 120, the node identification unit 150, the item analysis unit 160, and the muscle evaluation unit. 170. The training plan providing unit 180 and the storage unit 190 are, for example, provided in the host HT. For example, the subject 900 stands on the ) within. After the subject 900 is within the visual range of the image capturing unit 140, the muscle condition detection method can be started.

The muscle condition detection method includes steps S110 to S180. Please refer to Figure 6, which illustrates step S110. In step S110, the subject 900 inputs subject data UD through the input unit 110. The subject data UD includes, for example, an image, a gender, an age, and a dominant hand information.

Next, please refer to Figure 7, which illustrates step S120. The detection action providing unit 120 provides several detection actions Ai based on the subject data UD. For example, the action database DB1 stores all possible detection actions Ai. The detection action providing unit 120 can gradually filter according to age, gender, and dominant hand to obtain a suitable detection action Ai. In one embodiment, the detection action Ai of sitting on a chair may be provided for the elderly.

Then, please refer to Figures 8A to 8C, which illustrate step S130. In step S130, the display unit 130 displays one prompt information DFi of each detection action Ai. The detection action Ai in Figure 8A is "front standing"; the detection action Ai in Figure 8B is "side standing and reaching forward"; the detection action Ai in Figure 8C is "sitting and side extension". The display unit 130 may use images, videos, text, etc. Assist in explaining these detection actions Ai, and you can use the timeline or color to tell the start time and end time of the action.

In another embodiment, the display unit 130 may further have a loudspeaker function, and the prompt information DFi may be sound information. The display unit 130 can further display a confirmation button to confirm whether the subject 900 needs to repeatedly view the prompt information DFi.

In addition, when there are multiple detection actions Ai, the display unit 130 can only display the prompt information DFi of one detection action Ai at a time and inform the remaining number.

Then, please refer to Figures 9A to 9C, which illustrate step S140. In step S140, the image capturing unit 140 captures action images IMi of the subject 900 performing each detection action Ai. Picture 9A is the action image IMi of "front standing"; Picture 9B is the action image IMi of "side standing and reaching forward"; Picture 9C is the action image IMi of "sitting and side stretching". The image capturing unit 140 can capture a continuous image or a static image according to each detection action Ai. When capturing the action image IMi, the action image IMi can be presented on the display unit 130 at the same time. The action image IMi is presented in the form of mapping. That is, the subject 900 looks at the display unit 130 as if looking at a mirror. When the subject 900 is performing the detection action Ai, auxiliary information may be provided to assist the subject 900 in completing the detection action Ai.

In one embodiment, the display unit 130 can continuously display the detection action Ai at the corner, or draw a human-shaped dotted line, and superimpose the human-shaped dotted line on the displayed action image IMi to facilitate the inspection and detection of the subject 900 The error of action Ai.

Next, please refer to Figure 10, which illustrates step S150. The node identification unit 150 identifies several nodes Nim in each action image IMi. Nodes Nim are knees, elbows, wrists, noses, eyes, ears, pelvis, soles of feet, ankles, necks, shoulders, etc. If the image capturing unit 140 is a black and white camera or a color camera, the node identification unit 150 can obtain the node Nim of the two-dimensional space. If the image capturing unit 140 is a depth camera, the node identification unit 150 can obtain the node Nim of the three-dimensional space. These nodes Nim may or may not be displayed on the display unit 130 .

Then, please refer to Figures 11A to 11C, which illustrate step S160. In step S160, the item analysis unit 160 analyzes the detection results Rij of each detection item Eij. Each detection action Ai corresponds to a plurality of detection items Eij, for example. Each detection action Ai is a whole-body action or a large-scale limb action, and each detection item Eij is a local body posture. For example, the detection action Ai of "frontal standing" can correspond to the detection items Eij such as "head forward", "abdominal thrust", and "knee bend"; the detection action Ai of "overhead squat" can correspond to "arm Detection items Eij such as "fall", "foot external rotation", "hip center of gravity shift", etc.

When the item analysis unit 160 analyzes and detects the item Eij, it can measure angle, displacement, time, etc. For example, as shown in Figure 11A, the item analysis unit 160 can analyze the angle θ between the node Nim of "ear" and "shoulder" and the vertical line. Alternatively, as shown in FIG. 11B , the item analysis unit 160 may analyze the movement distance D9 of the node Nim of the "wrist". Or, as shown in Figure 11C, the project analysis unit 160 can analyze the node Nim of the "foot" and return after leaving the original height. The time of the original height is T9. Alternatively, the item analysis unit 160 may analyze the angle difference at different time points, the duration of maintaining the same posture, the time intervals of different actions, and so on.

Each detection item Eij corresponds to a standard range SDij. For example, the standard range SDij of the detection item Eij of "head tilt" is, for example, "the angle between the node Nim of the 'ear' and 'shoulder' and the vertical line is less than 15 degrees"; "side stance forward" The standard range SDij of the detection item Eij is, for example, "the movement distance of the node Nim of the "wrist" is greater than 20 cm." The standard range SDij has, for example, an upper limit value and a lower limit value. The standard range SDij has, for example, only an upper limit value or only a lower limit value. The above standard range SDij can be adjusted according to the subject's data UD. For example, a looser standard range SDij can be given to children.

The item analysis unit 160 analyzes whether each test item Eij of the subject 900 satisfies the standard range SDij to output the test result Rij.

Next, please refer to Figure 12A, which illustrates step S170. In step S170, the muscle evaluation unit 170 combines the detection results Rij of these detection items Eij to evaluate the muscle condition information MF of these muscles Mk. Based on the body's action muscle groups and muscle size, the contribution of the muscle Mk to the detection item Eij is the weight information Wijk. Each muscle Mk corresponds to different detection items Eij and has different weight information Wijk. For example, in the "pelvic balance" test item Eij when standing frontally, the middle left hip muscle Mk is the main muscle group that is too tight for the "left pelvis is high", so it can be given higher weight information Wijk ( For example, +0.8; a positive sign indicates too tight); while in overhead squats, the "lower back is concave" In the detection item Eij of "sag/kyphosis", the middle left hip muscle Mk is a weak secondary muscle group in the case of "sag in the lower back", so it can be given a lower weight information Wijk (for example -0.5; a negative sign indicates powerless). Weight information Wijk can evaluate and initially set the correlation between the detection movement and the primary and secondary muscle groups based on the basic knowledge of sports mechanics or kinesiology. It can also be supplemented by electromyography (EMG) to measure the potential difference of each muscle group to accurately set the weight information. The muscle evaluation unit 170 performs weighted calculations on the detection results Rij and the weight information Wijk of these detection items Eij to evaluate the muscle condition information MF of each muscle Mk. As shown in Figure 12A, in the test results R41, R72, and R73 of test items E41, E72, and E73, the muscles M1, M3, M4, and M5 that are too tight are weighted and calculated using the weight information Wijk, and the overtight muscles are comprehensively evaluated. Tight muscles M3, M4, and M5; in this embodiment, muscle M1 is not considered too tight after comprehensive evaluation. Specifically, although muscle M1 is too tight in the test result R73, muscle M1 is not considered too tight for test item E73. It is said to be a minor muscle group, so after a comprehensive evaluation by weight information Wijk, it is not considered too tight. Similarly, after the weak muscles M6, M7, M8, and M9 are weighted and calculated using the weight information Wijk, the muscles M6, M8, and M9 that are too tight are comprehensively evaluated; in this embodiment, the muscle M7 is not considered to be too tight after the comprehensive evaluation. Weakness. Specifically, although muscle M7 shows weakness in test result R41, muscle M7 is a minor muscle group for test item E41, so it is not considered weak after the comprehensive evaluation of weight information Wijk. Finally, based on the highest and lowest scores of each muscle Mk in each test item Eij, statistical calculations (such as Σ test results Rijx weight information Wijk) are performed to define the upper and lower limits of the muscle Mk. Based on the final muscle condition information, MF is located in The percentage of the upper and lower limits determines the degree to which the muscle Mk is too tight, normal, or weak. Taking muscle M3 as an example, muscle M3 is judged to be moderately too tight in the test result R41, is judged to be severely too tight in the test result R72, and is judged to be moderately too tight in the test item R73. The final value weighted with each contribution is 9.7, accounting for 84% of the total. Among them, 9.7 and 84% are calculated as follows: (+3x0.9)+(+5x0.8)+(+5x0.6)=9.7, (+3x0.9)+(+5x0.8)+(+5x0 .6)]/[(+5x0.9)+(+5x0.8)+(+5x0.6)=84%. Figure 12B illustrates the results of the comprehensive assessment of muscle Mk. In terms of the degree of tightness divided into 4 levels (such as "normal", "too tight 1", "too tight 2", "too tight 3"), the tightness of muscle M3 accounts for 84% of the total, so a comprehensive evaluation The result is "too tight 3".

Please refer to FIG. 13 , which illustrates a graphical user interface 700 of the muscle condition detection device 100 according to an embodiment. The graphical user interface 700 is displayed on the display unit 130 . The graphical user interface 700 includes a front human figure 710 and a back human figure 720 . The frontal human figure 710 has several frontal muscle patches B1. The back human figure 720 has several back muscle patches B2. The contents of each front muscle block B1 and each back muscle block B2 are related to the muscle condition information MF. For example, in Figure 13, the front muscle block B1 and the back muscle block B2 can have three colors, and these colors are used to represent tight muscles, weak muscles and normal muscles. Figure 13, for example, uses three different colors of red, white, and blue with a diagonal mesh base, a dotted mesh base, and a blank mesh base to represent tight muscles, weak muscles, and normal muscles respectively.

Please refer to Figure 13. In this embodiment, the front muscle block B1 and the back muscle block B2 can have three single-color mesh bottom styles. These single-color mesh bottom styles are used to represent tight muscles, weak muscles, and normal muscles. . In another embodiment, the front muscle patch B1 and the back muscle patch B2 may have three color levels, and these color levels are used to represent the degree of tight muscles and the degree of weak muscles. In Figure 13, the bottom of the diagonal mesh corresponding to the overtight muscles can be represented by three different densities: deep red, red, and light red, to respectively present the three degrees of overtight muscles. The bottom of the dotted mesh corresponding to weak muscles can represent dark blue, blue, and light blue in three different densities to present three degrees of weak muscles respectively.

As shown in FIG. 13 , the graphical user interface 700 may have a pre-training mode MD1 and a post-training mode MD2. Users can switch between pre-training mode MD1 and post-training mode MD2. In the pre-training mode MD1, the contents of each front muscle block B1 and each back muscle block B2 are related to the muscle condition information MF before training. In the post-training mode MD2, the contents of each front muscle patch B1 and each back muscle patch B2 are related to the post-training muscle condition information MF.

Then, please refer to Figure 14, which illustrates step S180. In step S180, the training program providing unit 180 retrieves a database based on the muscle condition information MF of these muscles Mk to provide a muscle condition training program St. For example, as shown in Figure 14, for the overly tight "rectus abdominis", the muscle condition training program St for rectus abdominis relaxation can be provided; for the weak "quadriceps", the muscle condition training with leg press machine can be provided Program St.

In another embodiment, the training program providing unit 180 may further refer to the detection item Eij with a poor detection result Rij to provide the muscle condition training program St.

In summary, although the present disclosure has been disclosed in the above embodiments, they are not used to limit the present disclosure. Those with ordinary knowledge in the technical field to which this disclosure belongs can make various modifications and modifications without departing from the spirit and scope of this disclosure. Therefore, the protection scope of the present disclosure shall be subject to the scope of the appended patent application.

S110, S120, S130, S140, S150, S160, S170, S180: Steps

Claims (27)

A muscle condition detection device, including: a detection action providing unit, used to provide a plurality of detection actions according to a subject's data, each detection action corresponds to a plurality of detection items, and each detection item corresponds to A plurality of muscles; a display unit used to display prompt information for each detection action, the prompt information including a text information, a sound information, a picture information and a video information; an image capture unit used to capture the An action image of the subject performing each of the detection actions; a node identification unit for identifying a plurality of nodes in each of the action images; an item analysis unit for analyzing a detection result of each of the detection items; and A muscle assessment unit is used to synthesize the test results of the test items to evaluate muscle condition information of the muscles. The muscle condition detection device as described in claim 1, wherein each subject's information includes a gender, an age and a dominant hand information. The muscle condition detection device as claimed in claim 1, wherein the image capture unit captures a continuous image or a static image according to each detection action. The muscle condition detection device as claimed in claim 1, wherein each detection action is a whole body action, and each detection item is a local body posture. The muscle condition detection device as claimed in claim 1, wherein the muscles corresponding to the detection items partially overlap. The muscle condition detection device of claim 1, wherein the item analysis unit analyzes the test results of each test item based on a standard range of each test item. The muscle condition detection device as claimed in claim 6, wherein the standard range is adjusted based on the subject's data. The muscle condition detection device of claim 1, wherein each muscle has a weight information corresponding to each detection item, and the muscle evaluation unit performs weighted calculations on the detection results of these detection items and the weight information, To evaluate the muscle condition information of each muscle. The muscle condition detection device as described in claim 1 further includes: a training program providing unit for retrieving a database based on the muscle condition information of the muscles to provide at least one muscle condition training program. The muscle condition detection device as claimed in claim 1, wherein each muscle is a single muscle or a muscle group. A muscle condition detection method. The muscle condition detection method is executed by a muscle condition detection device. The muscle condition detection method includes: providing a plurality of detection actions based on one of the subject data of a subject, and each detection action corresponds to In a plurality of test items, each test item corresponds to a plurality of muscles; display prompt information for each test action, and the prompt information includes a text information, a sound information, a picture information, and a video information; and retrieve the subject Perform an action image of each of the test actions; identify a plurality of nodes in each of the action images; analyze a test result of each of the test items; and combine the test results of the test items to evaluate the strength of the muscles. 1. Muscle condition information. The muscle condition detection method as described in claim 11, wherein the subject information includes a gender, an age and a dominant hand information. The muscle condition detection method as described in claim 11, wherein according to each detection action, the action image is a continuous image or a static image. The muscle condition detection method as described in claim 11, wherein each detection action is a whole body action, and each detection item is a local body posture. The muscle condition detection method as described in claim 11, wherein the muscles corresponding to the detection items partially overlap. The muscle condition detection method as described in claim 11, wherein the test results of each test item are analyzed based on a standard range of each test item. The muscle condition detection method as described in claim 16, wherein the standard range is adjusted based on the subject's data. The muscle condition detection method as described in claim 11, wherein each muscle has a weight information corresponding to each test item, and the test results of the test items are weighted with the weight information to evaluate each test item. Information about the condition of this muscle. The muscle condition detection method as described in claim 11 further includes: retrieving a database based on the muscle condition information of the muscles to provide at least one muscle condition training program. The muscle condition detection method as described in claim 11, wherein the steps of providing the detection actions are performed by a detection action providing unit according to the subject data of the subject; The step of displaying the prompt information of each of the detection actions is performed by a display unit; the step of capturing the action image of the subject performing each of the detection actions is performed by an image capture unit; in each of the actions The step of identifying the nodes in the image is performed by a node identification unit; the step of analyzing the test results of each of the test items is performed by a project analysis unit; and the step of synthesizing the test results of the test items, The step of evaluating the muscle condition information of the muscles is performed by a muscle evaluation unit. The muscle condition detection method as described in claim 11, wherein each muscle is a single muscle or a muscle group. The muscle condition detection device as claimed in claim 1, wherein a graphical user interface is displayed on the display unit, and the graphical user interface includes: a front human figure with a plurality of front muscle patches; and a back surface The humanoid figure has a plurality of back muscle tiles, and the content of each front muscle tile and each back muscle tile is related to the muscle condition information. The muscle condition detection device as claimed in claim 22, wherein the front muscle tiles and the back muscle tiles have three colors, and the colors are used to represent a tight muscle, a weak muscle and a normal muscle. The muscle condition detection device as described in claim 22, wherein the front muscle blocks and the back muscle blocks have three single-color mesh bottom patterns, and the single-color mesh bottom patterns are used to represent an overtight muscle, a muscle that is too tight, and a muscle that is too tight. Weak muscles and one normal muscle. The muscle condition detection device as claimed in claim 22, wherein the front muscle patches and the back muscle patches have three color levels, and the color levels are used to represent a degree of tight muscles and a degree of weak muscles. . The muscle condition detection device as claimed in claim 22, wherein the graphical user interface has a pre-training mode and a post-training mode; in the pre-training mode, the front muscle tiles and the back muscle tiles are The content is related to the muscle condition information before training; in the post-training mode, the content of each front muscle picture block and each back muscle picture block is related to the muscle condition information after training. The muscle condition detection device as claimed in claim 22, wherein each muscle is a single muscle or a muscle group.

Images