Method and device for evaluating rotational motion level of alpine skiing based on plantar pressure
By setting up a sole pressure sensor in the ski boots, using deep learning technology to evaluate the slewing level in alpine skiing, the problem of evaluation difficulties in the prior art is solved, and low-cost and accurate sports level assessment and guidance are achieved.
Patent Information
- Application Number
- CN202411019866.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-29
AI Technical Summary
The prior art is difficult to effectively evaluate the slewing level in alpine skiing. The traditional method is costly, the data transmission is large, and the pose drift is solved, which interferes with the skier's behavior.
By setting up a sole pressure measurement sensor in the ski boot, the sole pressure of each slewing cycle is collected, the skier's posture is estimated using deep learning technology, and the posture control, explosive force, force control and balance ability characteristics are extracted for quantitative evaluation.
The interference-free and low-cost skier slewing sports level assessment is achieved, the data transmission volume and calculation drift problems of traditional methods are solved, and detailed sports guidance suggestions are provided.
Smart Images

Figure CN118949378A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of skiing quantification evaluation, and in particular to a method and device for evaluating the level of alpine skiing slalom based on plantar pressure. Background Art
[0002] Artificial intelligence has had a significant impact on the development of sports. The continuous upgrading of smart devices has been prominently applied in the field of sports and has become an important tool for improving sports performance. As one of the core events of winter sports, alpine skiing has been widely welcomed. However, the current evaluation of alpine skiing slalom level mostly relies on qualitative evaluation based on the experience of coaches.
[0003] Based on this, the present invention proposes a method and device for evaluating the alpine skiing slalom level based on plantar pressure to solve the above technical problems. Summary of the invention
[0004] The invention describes a method and a device for evaluating the slalom motion level of alpine skiing based on plantar pressure, which can quantitatively evaluate the slalom motion level of a skier in alpine skiing.
[0005] According to a first aspect, the present invention provides a method for evaluating alpine skiing slalom performance based on plantar pressure, comprising:
[0006] Acquire the plantar pressure in each rotation cycle collected by a plantar pressure measurement sensor disposed inside the ski boot;
[0007] Based on the plantar pressure, determining a target feature set; wherein the target feature set is used to characterize the posture force control state of the skier in alpine skiing;
[0008] Based on the target feature set, the skier's slalom performance in alpine skiing is evaluated.
[0009] According to a second aspect, the present invention provides an alpine skiing slalom level assessment device based on plantar pressure, comprising:
[0010] An acquisition unit configured to acquire the plantar pressure in each rotation cycle collected by a plantar pressure measurement sensor disposed inside the ski boot;
[0011] A determination unit is configured to determine a target feature set based on the plantar pressure; wherein the target feature set is used to characterize a posture force control state of a skier in alpine skiing;
[0012] The evaluation unit is configured to evaluate the slalom motion level of the skier in alpine skiing based on the target feature set.
[0013] In a third aspect, an embodiment of this specification further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.
[0014] In a fourth aspect, an embodiment of the present specification further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method described in any embodiment of the present specification.
[0015] According to the method and device for evaluating the level of alpine skiing slalom based on plantar pressure provided by the present invention, the plantar pressure measurement sensor arranged inside the ski boots collects the plantar pressure in each rotation cycle, and then determines the target feature set for characterizing the posture and force control state of the skier in alpine skiing based on the plantar pressure, and finally evaluates the skier's slalom level in alpine skiing based on the target feature set. Therefore, the above technical solution can quantitatively evaluate the skier's slalom level in alpine skiing by collecting the skier's plantar pressure in each rotation cycle. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 A schematic flow chart of a method for evaluating alpine skiing slalom performance based on plantar pressure according to an embodiment is shown;
[0018] Figure 2 A schematic block diagram of an alpine skiing slalom athletic level assessment device based on plantar pressure according to an embodiment is shown;
[0019] Figure 3 A schematic diagram showing an upper body inclination angle and a lower body inclination angle according to one embodiment is shown. DETAILED DESCRIPTION
[0020] The solution provided by the present invention is described below in conjunction with the accompanying drawings.
[0021] Figure 1 FIG. 1 is a flow chart of a method for evaluating the level of alpine skiing slalom based on plantar pressure according to an embodiment. It can be understood that the method can be executed by any device, equipment, platform, or device cluster with computing and processing capabilities. Figure 1 As shown, the method includes:
[0022] Step 100, obtaining the plantar pressure in each rotation cycle collected by a plantar pressure measurement sensor disposed inside the ski boot;
[0023] Step 102: determining a target feature set based on the plantar pressure; wherein the target feature set is used to characterize the posture force control state of the skier in alpine skiing;
[0024] Step 104: Based on the target feature set, the skier's slalom skill in alpine skiing is evaluated.
[0025] In this embodiment, the plantar pressure measurement sensor disposed inside the ski boots collects the plantar pressure in each rotation cycle, and then determines the target feature set used to characterize the posture and force control state of the skier in alpine skiing based on the plantar pressure, and finally evaluates the skier's rotation level in alpine skiing based on the target feature set. Therefore, the above technical solution can quantitatively evaluate the skier's rotation level in alpine skiing by collecting the skier's plantar pressure in each rotation cycle.
[0026] In one embodiment of the present invention, the target feature set includes posture control features, explosive power features, strength control features and balance ability features, and the abilities of rotational motion level assessment include posture control ability, explosive power, strength control ability and balance ability.
[0027] Alpine skiing is a complex whole-body sport. Skiers need to maintain their body balance while pushing off the ground to achieve a slalom. Skiers need to have good posture control, explosive power, strength control, and balance abilities to successfully complete the slalom without causing sports injuries. Therefore, the skier's posture control, explosive power, strength control, and balance abilities are important evaluation indicators for quantitatively evaluating the level of slalom sports.
[0028] The skier's posture control ability is reflected in the body posture, while the explosive power, strength control ability and balance ability are reflected in the plantar pressure data. The existing methods for evaluating alpine skiing slalom are mostly to extract the skier's posture information through images or wearable inertial sensors. However, both methods have many problems. On the one hand, due to the fast speed, long distance and large drop of alpine skiing, it is difficult to capture the skier's slalom image throughout the whole process using a camera, and the camera is easily affected by weather, light and occlusion, which makes it difficult to evaluate the slalom. In addition, this acquisition method is costly, with large data transmission and calculation volume. On the other hand, based on the acquisition method of wearable inertial sensors, the calculated posture will drift over time, which is not suitable for long-term use, and wearable devices are prone to problems such as inconvenience in wearing and interference with skier behavior.
[0029] In view of the above problems and defects, the present invention proposes a method for evaluating the level of alpine skiing slalom based on plantar pressure. The plantar pressure measuring insole is placed inside the ski boot (that is, each plantar pressure measuring insole contains n measuring units, and the collected left plantar pressure data is f 11 ,f 12 ,...,f 1n , the right plantar pressure data is f 21 ,f 22 ,...,f 2n ), without interfering with the skier's movement, deep learning technology is used to estimate the skier's important posture, and then based on the measured plantar pressure information and the estimated posture information, posture control features, explosive power features, strength control features and balance ability features are extracted to evaluate the skier's posture control ability, explosive power, strength control ability and balance ability individually, and to comprehensively evaluate the slalom level. Finally, corresponding guidance and suggestions are given based on the evaluation results. For details, please see below:
[0030] In one embodiment of the present invention, the gesture control feature is determined by:
[0031] The plantar pressure in each rotation cycle is processed by matrix to obtain time series data; wherein the time series data includes M samples, the dimension of each sample is 2×n, and n is the length of the sliding window;
[0032] Input the time series data into the first extraction model and the second extraction model respectively, and perform feature fusion on the results output by the first extraction model and the second extraction model to obtain fused data; wherein the first extraction model is used to sequentially extract local time features of the time series data, and the second extraction model is used to extract global time features of the time series data;
[0033] The fused data is input into the posture recognition model, and the upper body inclination angle and the lower body inclination angle of the skier in the frontal plane are output;
[0034] The posture control characteristics are determined based on the following formula:
[0035]
[0036]
[0037]
[0038] In the formula, t 1 ,t 2 ,t 3 They represent the posture control characteristics, It represents the maximum lower body tilt angle of the skier in each rotation cycle. It indicates the maximum upper body tilt angle of the skier in each rotation cycle.
[0039] In this embodiment, considering that the skier's level is not only reflected in the plantar pressure data during alpine skiing slalom, but also closely related to the body posture data, the inventor creatively thought of a method for estimating the body posture angle of alpine skiing slalom using plantar pressure data, that is, the skier's inclination angle can be estimated without a posture acquisition device. Among them, the skier's posture during slalom is as follows: Figure 3 As shown, and They respectively represent the inclination angle of the skier's upper body and lower body in the frontal plane. These two inclination angles are closely related to the skiing level in the turning motion and are important posture information.
[0040] In some embodiments, the first extraction model may include multiple one-dimensional convolutional layers, each of which is followed by a batch normalization layer. The one-dimensional convolutional layer can well mine the temporal interaction features between time series data. Each one-dimensional convolutional layer contains multiple convolution kernels, each of which slides in the time series, multiplies the local area data point by point, and adds the results to generate a new feature map. This operation can well extract local time features in time series data. The batch normalization layer is used for data normalization, accelerating the model convergence speed, and improving the model stability.
[0041] In some embodiments, the second extraction model may include a plurality of double-layer gated recurrent units for extracting forward and backward temporal features in the sequence.
[0042] In some embodiments, the state recognition model may include a fully connected layer and a random dropout layer for posture angle estimation. During the model learning process, the random dropout layer randomly resets some weights or outputs of the hidden layer to zero to reduce the interdependence between nodes, thereby achieving regularization of the neural network and reducing the risk of the network structure.
[0043] In one embodiment of the present invention, the explosive force characteristic is determined by the following formula:
[0044]
[0045]
[0046] Where, t 4 ,t 5 Represent the explosive force characteristics, F 1max It represents the maximum left foot pressure of the skier in each rotation cycle, F 2max It represents the maximum plantar pressure on the right side of the skier in each rotation cycle, and G represents the skier's weight.
[0047] In one embodiment of the present invention, the force control characteristic is determined by the following formula:
[0048]
[0049]
[0050] Where, t 6 ,t 7 Represent the force control characteristics, F 1min It represents the minimum left foot pressure of the skier in each rotation cycle, F 2min It indicates the minimum plantar pressure on the right side of the skier during each slalom cycle.
[0051] In one embodiment of the present invention, the balance capability characteristic is determined by the following formula:
[0052]
[0053]
[0054] Where, t 8 ,t 9 They represent the balance ability characteristics respectively.
[0055] It should be noted that the skier's posture control characteristics are reflected in the maximum tilt angle of the lower limbs, the maximum posture angle of the upper body and the difference between the two in each rotation cycle; the skier's explosive power characteristics are reflected in the maximum plantar pressure in each rotation cycle; the skier's power control characteristics are reflected in the difference between the maximum plantar pressure and the minimum plantar pressure in each rotation cycle; the skier's balance ability characteristics are reflected in the difference between the left and right foot pressures in each rotation cycle. Therefore, it can be obtained that t in the above embodiment 1 to 9 And so on nine rotation features.
[0056] In one embodiment of the present invention, the level of rotational motion is evaluated by the following formula:
[0057]
[0058]
[0059]
[0060]
[0061]
[0062] In the formula, S 1 Indicates the skier's posture control ability score, S 2 Indicates the skier's explosive power, S 3 Indicates the skier's power control ability score, S 4 represents the balance ability score of the skier, S 5 It represents the comprehensive ability score of the skier, and the full score is 100. i represents the weight of each feature, t i ′ represents the characteristics of an excellent coach, α i Indicates the weight of each individual score,
[0063] In this embodiment, according to the above four items (i.e., S 1 To S 4 ) score, and give corresponding guidance suggestions. 1 If the score is less than 80 points, guidance suggestions are given: lack of posture control ability, it is recommended to increase the tilt angle of the lower limbs as much as possible, while keeping the upper body as upright as possible; if S 2 If the score is less than 80 points, guidance suggestions are given: if the explosive ability is lacking, it is recommended to push the ground with both legs and use the strength of the lower limbs and core to complete the rotation; if S 3If the score is less than 80 points, guidance suggestions are given: lack of strength control ability, it is recommended to exercise core strength, use waist and abdomen strength to control and drive the lower limbs to rotate; if S 4 If the score is less than 80 points, guidance suggestions will be given: lack of balance ability, it is recommended to exercise the strength of the non-dominant leg to maintain body balance.
[0064] In summary, the present invention has the following advantages: 1) It can estimate the important posture of the skier by using only the plantar pressure information without using the posture acquisition equipment, thus solving many problems and defects of image and inertial sensor information acquisition and posture calculation. 2) It can evaluate the skier's posture control ability, explosive power, power control ability and balance ability by using only the plantar pressure information, and comprehensively evaluate the alpine skiing slalom level. 3) It can give corresponding guidance suggestions based on the single evaluation results.
[0065] The above describes specific embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0066] According to an embodiment of another aspect, the present invention provides an apparatus for evaluating alpine skiing slalom proficiency based on plantar pressure. Figure 2 FIG. 1 is a schematic block diagram of an apparatus for evaluating the level of alpine skiing slalom based on plantar pressure according to an embodiment. It can be understood that the apparatus can be implemented by any apparatus, device, platform, or device cluster with computing and processing capabilities. Figure 2 As shown, the device includes: an acquisition unit 200, a determination unit 202 and an evaluation unit 204. The main functions of each component unit are as follows:
[0067] An acquisition unit 200 is configured to acquire the plantar pressure in each rotation cycle collected by a plantar pressure measurement sensor disposed inside the ski boot;
[0068] A determination unit 202 is configured to determine a target feature set based on the plantar pressure; wherein the target feature set is used to characterize the posture force control state of the skier in alpine skiing;
[0069] The evaluation unit 204 is configured to evaluate the skier's slalom skill in alpine skiing based on the target feature set.
[0070] As a preferred embodiment, the target feature set includes posture control features, explosive power features, strength control features and balance ability features, and the abilities of the rotational motion level assessment include posture control ability, explosive power, strength control ability and balance ability.
[0071] As a preferred implementation, the posture control feature is determined in the following manner:
[0072] Performing matrix processing on the plantar pressure in each rotation cycle to obtain time series data; wherein the time series data includes M samples, each of which has a dimension of 2×n, and n is the length of the sliding window;
[0073] The time series data is input into a first extraction model and a second extraction model respectively, and the results output by the first extraction model and the second extraction model are subjected to feature fusion to obtain fused data; wherein the first extraction model is used to sequentially extract local time features of the time series data, and the second extraction model is used to extract global time features of the time series data;
[0074] Inputting the fused data into a posture recognition model, and outputting the upper body inclination angle and the lower body inclination angle of the skier in the frontal plane;
[0075] The posture control characteristics are determined based on the following formula:
[0076]
[0077]
[0078]
[0079] In the formula, t 1 ,t 2 ,t 3 They represent the posture control characteristics, represents the maximum lower body tilt angle of the skier in each rotation cycle, It represents the maximum upper body tilt angle of the skier in each rotation cycle.
[0080] As a preferred implementation, the explosive force characteristic is determined by the following formula:
[0081]
[0082]
[0083] In the formula, t 4 ,t 5 Represent the explosive force characteristics, F 1maxrepresents the maximum left foot pressure of the skier in each rotation cycle, F 2max represents the maximum plantar pressure on the right side of the skier in each rotation cycle, and G represents the weight of the skier.
[0084] As a preferred implementation, the force control characteristic is determined by the following formula:
[0085]
[0086]
[0087] In the formula, t 6 ,t 7 Represent the force control characteristics, F 1min represents the minimum left foot pressure of the skier in each rotation cycle, F 2min It represents the minimum plantar pressure on the right side of the skier in each rotation cycle.
[0088] As a preferred implementation, the balancing capability characteristic is determined by the following formula:
[0089]
[0090]
[0091] In the formula, t 8 ,t 9 They represent the balance ability characteristics respectively.
[0092] As a preferred embodiment, the rotational motion level is evaluated by the following formula:
[0093]
[0094]
[0095]
[0096]
[0097]
[0098] In the formula, S 1 represents the skier's posture control ability score, S 2 represents the explosive power of the skier, S 3 represents the skier's power control ability score, S 4 represents the balance ability score of the skier, S 5represents the comprehensive ability score of the skier, where the full score is 100 points, ω i represents the weight of each feature, t i ′ represents the characteristics of an excellent coach, α i Indicates the weight of each individual score,
[0099] According to another embodiment, there is also provided a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute a combination of Figure 1 The method described.
[0100] According to another embodiment of the present invention, there is also provided an electronic device, comprising a memory and a processor, wherein the memory stores an executable code, and when the processor executes the executable code, the Figure 1 The method described.
[0101] The various embodiments of the present invention are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0102] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, firmware or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.
[0103] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for evaluating the level of alpine skiing slalom based on plantar pressure, characterized in that: include: Acquire the plantar pressure in each rotation cycle collected by a plantar pressure measurement sensor disposed inside the ski boot; Based on the plantar pressure, determining a target feature set; wherein the target feature set is used to characterize the posture force control state of the skier in alpine skiing; Based on the target feature set, the skier's slalom performance in alpine skiing is evaluated.
2. The method according to claim 1, characterized in that The target feature set includes posture control features, explosive power features, strength control features and balance ability features, and the abilities of the rotational motion level assessment include posture control ability, explosive power, strength control ability and balance ability.
3. The method according to claim 2, characterized in that The posture control feature is determined by: Performing matrix processing on the plantar pressure in each rotation cycle to obtain time series data; wherein the time series data includes M samples, each of which has a dimension of 2×n, and n is the length of the sliding window; The time series data is input into a first extraction model and a second extraction model respectively, and the results output by the first extraction model and the second extraction model are subjected to feature fusion to obtain fused data; wherein the first extraction model is used to sequentially extract local time features of the time series data, and the second extraction model is used to extract global time features of the time series data; Inputting the fused data into a posture recognition model, and outputting the upper body inclination angle and the lower body inclination angle of the skier in the frontal plane; The posture control characteristics are determined based on the following formula: Where t1, t2, and t3 represent the posture control characteristics, represents the maximum lower body tilt angle of the skier in each rotation cycle, It represents the maximum upper body tilt angle of the skier in each rotation cycle.
4. The method according to claim 3, characterized in that The explosive force characteristic is determined by the following formula: In the formula, t4 and t5 represent the explosive force characteristics, F 1max represents the maximum left foot pressure of the skier in each rotation cycle, F 2max represents the maximum plantar pressure on the right side of the skier in each rotation cycle, and G represents the weight of the skier.
5. The method according to claim 4, characterized in that The force control characteristic is determined by the following formula: Where t6 and t7 represent the force control characteristics, F 1min represents the minimum left foot pressure of the skier in each rotation cycle, F 2min It represents the minimum plantar pressure on the right side of the skier in each rotation cycle.
6. The method according to claim 5, characterized in that The balance capability characteristic is determined by the following formula: Where t8 and t9 represent the balancing ability characteristics respectively.
7. The method according to claim 6, characterized in that The level of rotational motion is evaluated by the following formula: Wherein, S1 represents the skier's posture control ability score, S2 represents the skier's explosive ability, S3 represents the skier's power control ability score, S4 represents the skier's balance ability score, S5 represents the skier's comprehensive ability score, and the comprehensive score is 100 points. i represents the weight of each feature, t i ′ represents the characteristics of an excellent coach, α i Indicates the weight of each individual score, 8. A device for evaluating the level of alpine skiing slalom based on plantar pressure, characterized in that: include: An acquisition unit configured to acquire the plantar pressure in each rotation cycle collected by a plantar pressure measurement sensor disposed inside the ski boot; A determination unit is configured to determine a target feature set based on the plantar pressure; wherein the target feature set is used to characterize a posture force control state of a skier in alpine skiing; The evaluation unit is configured to evaluate the slalom motion level of the skier in alpine skiing based on the target feature set.
9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Action evaluation and action guidance method suitable for skiing training platform
CN112516559A
Method for evaluating skiing rotation level based on monocular video
CN115457440A
Moving robot and contorlling method thereof
KR102269851B1
Method and System for Functional Balance Assessment
US20160128642A1
