Multi-sensor fusion longitudinal jump force estimation and height compensation method and system

Abstract

The invention discloses a multi-sensor fusion longitudinal jump force estimation and height compensation method and system. The method comprises the following steps: acquiring sensing data of a plurality of inertial measurement units arranged at different segments of a human body; based on sensing data of a plurality of inertial measurement units, determining a ground clearance moment and a landing moment in a longitudinal jumping process, applying a physical constraint that the ground reaction force approaches to zero in a flying period, and estimating a time sequence of the ground reaction force from the ground clearance to the landing moment; calculating a first vertical jump height estimation value based on the ground reaction force time sequence, and calculating a second vertical jump height estimation value based on the off-ground moment and the landing moment; and determining a height error compensation amount according to the first longitudinal jump height estimation value and the second longitudinal jump height estimation value in combination with action characteristics extracted from the sensing data so as to correct the second longitudinal jump height estimation value and obtain the compensated longitudinal jump height. According to the invention, the accuracy and scene adaptability of measuring and calculating the longitudinal jumping ground reaction force and the flying height are improved.

Description

Technical Field

[0001] This invention relates to the field of sports biomechanics measurement and intelligent sensing technology, and in particular to a method and system for estimating vertical jump force and compensating for height through multi-sensor fusion. Background Technology

[0002] To address the needs of measuring ground reaction force during vertical jump and calculating height, existing technologies have developed diverse solutions, but they generally present a challenge in balancing accuracy, portability, and scenario adaptability.

[0003] As the gold standard in laboratories, force platforms can acquire complete reaction force time series and accurately calculate take-off speed and height based on the impulse-momentum theorem. However, the equipment is large and expensive, and can only be used in fixed venues, making it difficult to meet the needs of daily training monitoring and large-scale physical fitness testing.

[0004] Contact pads and photoelectric timing systems estimate flight time by calculating the time from takeoff to landing, enabling high jump estimation. They are portable and low-cost, and widely used in grassroots training, schools, and fitness settings. However, they cannot capture the details of reaction force, limiting their value for evaluating athletic techniques.

[0005] Video and visual measurement methods identify the trajectory of the human center of mass and key events through two-dimensional or three-dimensional motion capture. They can simultaneously calculate height and inversely calculate some dynamic parameters. Their application in scientific research and professional institutions is gradually increasing, but they are strictly limited by the complexity of equipment, ambient light, and the time required for post-processing.

[0006] Wearable inertial sensor solutions fix one or a few nodes to the waist, pelvis, or lower leg, use acceleration integration to obtain velocity displacement to estimate jump height, and attempt to indirectly infer the force peak shape and impulse through signal characteristics, which fits the trend of site-specific and real-time applications. However, integral drift and the limitation of single position information lead to long-term accuracy decay and weak ability to restore reaction force waveforms.

[0007] Data-driven and machine learning approaches attempt to establish a mapping model from inertial characteristics to reaction force indicators, breaking through hardware dependence to achieve site-based force monitoring. However, they are still hampered by the insufficient data dimension of single sensors, making it difficult for the model's generalization ability to cover individual motion differences and action variations.

[0008] In summary, existing technologies either require compromises between accuracy and portability, or face limitations due to single-sensor information, and the fusion accuracy of reaction force estimation and height measurement is insufficient. A systematic solution that balances measurement accuracy, lightweight equipment, and flexibility in various scenarios has not yet been developed, thus hindering the in-depth application of vertical jump ability assessment in competitive sports, rehabilitation training, and mass fitness. Therefore, there is an urgent need to provide a technical solution to address these issues. Summary of the Invention

[0009] To address the aforementioned technical problems, this invention provides a method and system for estimating vertical jump force and compensating height using multi-sensor fusion.

[0010] In a first aspect, the present invention provides a method for estimating vertical jump force and compensating for height through multi-sensor fusion, the technical solution of which is as follows: Collect sensor data from multiple inertial measurement units installed in different segments of the human body; Based on the sensing data from the multiple inertial measurement units, the takeoff time and landing time during the vertical jump are determined. Based on the sensing data of the multiple inertial measurement units, the time of takeoff and the time of landing, and with the physical constraint that the ground reaction force during takeoff approaches zero, the time series of ground reaction force from before takeoff to after landing is estimated. Based on the ground reaction force time series, the first vertical jump height estimate is calculated, and based on the takeoff time and the landing time, the second vertical jump height estimate is calculated. Based on the first vertical jump height estimate and the second vertical jump height estimate, and combined with the motion features extracted from the sensing data of the plurality of inertial measurement units, the height error compensation amount is determined; The second vertical jump height estimate is corrected based on the height error compensation amount to obtain the compensated vertical jump height.

[0011] The beneficial effects of the multi-sensor fusion method for estimating vertical jump force and compensating height according to the present invention are as follows: The method of this invention deploys multiple inertial measurement units in different segments of the human body and fuses sensor data. It applies a physical constraint that the ground reaction force during the takeoff period approaches zero to estimate the complete reaction force time series. It combines the dual height estimates and motion characteristics for error compensation, which solves the technical problems of insufficient information dimension of single sensors, accuracy decay caused by integral drift, and poor portability of high-precision equipment. This improves the accuracy and scene adaptability of vertical jump ground reaction force and takeoff height calculation.

[0012] Based on the above scheme, the multi-sensor fusion method for estimating vertical jump force and compensating height of the present invention can be further improved as follows.

[0013] In one alternative approach, the step of determining the takeoff and landing times during a vertical jump based on the sensing data from the plurality of inertial measurement units includes: Based on sensing data from at least one inertial measurement unit located on the human foot or lower leg, the system detects a first moment when the amplitude or rate of change of the acceleration signal in the sensing data exceeds a first threshold, and a second moment when the angular velocity signal undergoes a sudden change in direction. Based on the sensing data of the multiple inertial measurement units, the differences or phase relationships between the angular velocity signals of the corresponding inertial measurement units in different segments are calculated to obtain the coordination index. Based on the first time point, the second time point, and the first set of preset conditions satisfied by the coordination index, it is determined that an off-ground event has occurred, and the time corresponding to the off-ground event is determined as the off-ground time. Based on the first time point, the second time point, and the second set of preset conditions satisfied by the coordination index, a landing event is determined to have occurred, and the time corresponding to the landing event is determined as the landing time.

[0014] The advantages of adopting the above-mentioned optional methods are: further capturing the peak acceleration and sudden changes in angular velocity direction through foot or lower leg inertial measurement units, combined with multi-segment coordination indicators, improving the accuracy of determining the moment of takeoff and the moment of landing, and reducing detection errors caused by motion variations.

[0015] In one alternative approach, the step of estimating the time series of ground reaction forces from before takeoff to after landing, based on the sensing data of the plurality of inertial measurement units, the takeoff time, and the landing time, and applying a physical constraint that the ground reaction force during takeoff approaches zero, includes: Based on the sensing data from the multiple inertial measurement units, the acceleration sequence of the human body's center of mass in the vertical direction is calculated; Based on the acceleration sequence and human body mass, calculate the basic ground reaction force sequence; Based on the sensing data from the multiple inertial measurement units, a feature set containing the kinematic parameters of each segment is extracted; The feature set is input into a pre-trained force mapping model to obtain an initial ground reaction force sequence; Based on the basic ground reaction force sequence and the initial ground reaction force sequence, a fused ground reaction force sequence is generated; In the fused ground reaction force sequence, a zero-reduction constraint is applied to the force value corresponding to the target time period between the takeoff time and the landing time, so that the ground reaction force in the target time period approaches zero, thus obtaining the ground reaction force time sequence.

[0016] The advantages of adopting the above-mentioned optional method are: further integrating the basic ground reaction force calculated by the centroid acceleration with the initial sequence output by the force mapping model, and applying a zero-reset constraint to the take-off period, so that the time series estimation of reaction force is more in line with physical laws and individual dynamic characteristics.

[0017] In one alternative approach, the step of calculating the estimated first vertical jump height based on the ground reaction force time series includes: Extract the ground reaction force data corresponding to the force stage before the moment of liftoff from the ground reaction force time series; The ground reaction force data is integrated to obtain the corresponding impulse; Based on the impulse, human body mass, and gravitational acceleration components, the takeoff velocity at the moment of takeoff is calculated. Based on the takeoff speed and gravitational acceleration, the estimated value of the first vertical jump height is calculated.

[0018] The advantages of using the above-mentioned optional method are: further extracting the pre-leap momentum data from the ground reaction force time series, and calculating the take-off velocity by combining the human body mass and gravitational acceleration components, thereby realizing the estimation of the first vertical jump height based on the momentum theorem.

[0019] In one alternative approach, the step of calculating the estimated second vertical jump height based on the takeoff time and the landing time includes: Calculate the time difference between the landing time and the takeoff time to obtain the initial flight time; Based on the sensing data from the multiple inertial measurement units, the characteristics of human posture changes during the takeoff phase are identified. The initial flight time is corrected based on the human posture change characteristics to obtain the effective flight time; Based on the effective flight time and gravitational acceleration, the estimated value of the second vertical jump height is calculated.

[0020] The beneficial effects of adopting the above-mentioned optional methods are: further identifying the characteristics of human posture changes during the takeoff phase based on inertial data, correcting the initial flight time to obtain the effective flight time, and improving the adaptability of the second vertical jump height estimate to limb movements.

[0021] In one optional approach, the motion features include: event detection reliability features and airborne attitude features; the step of determining the height error compensation amount based on the first vertical jump height estimate and the second vertical jump height estimate, combined with the motion features extracted from the sensing data of the plurality of inertial measurement units, includes: Calculate the difference in vertical jump height between the first vertical jump height estimate and the second vertical jump height estimate; From the sensing data of the multiple inertial measurement units, features reflecting the stability of the identification of takeoff and landing events are extracted as the event detection reliability features, and features reflecting the relative motion of limbs during the takeoff phase are extracted as the takeoff posture features. The vertical jump height difference, the event detection reliability characteristics, and the take-off attitude characteristics are input into the error compensation model to determine the height error compensation amount; The error compensation model establishes a mapping relationship between the vertical jump height difference, the event detection reliability characteristics, the take-off posture characteristics, and the height error compensation amount based on training data.

[0022] The advantages of using the above-mentioned optional method are: further calculating the difference between the estimated first vertical jump height and the estimated second vertical jump height, integrating the event detection reliability characteristics and the takeoff attitude characteristics into the input error compensation model, determining the height error compensation amount, and improving the correction accuracy.

[0023] In one alternative approach, the step of correcting the second vertical jump height estimate based on the height error compensation amount to obtain the compensated vertical jump height includes: Obtain the confidence assessment result corresponding to the height error compensation amount; Based on the confidence assessment results, the height error compensation amount is weighted and assigned to obtain a weighted compensation amount; The second vertical jump height estimate is corrected and calculated based on the weighted compensation amount to obtain the compensated vertical jump height.

[0024] The advantages of adopting the above optional method are: to further obtain the confidence assessment results of the height error compensation amount, to generate a weighted compensation amount based on the confidence level, to dynamically adjust the correction intensity of the second vertical jump height estimate, and to improve the robustness of the results.

[0025] Secondly, the present invention provides a multi-sensor fusion system for vertical jump estimation and height compensation, the technical solution of which is as follows: The data acquisition module is used to collect sensor data from multiple inertial measurement units installed in different segments of the human body. The acquisition module is used to determine the takeoff time and landing time during the vertical jump based on the sensing data of the multiple inertial measurement units. The estimation module is used to estimate the time series of ground reaction forces from before takeoff to after landing, based on the sensing data of the multiple inertial measurement units, the takeoff time and the landing time, and by applying the physical constraint that the ground reaction force during takeoff approaches zero. The calculation module is used to calculate a first vertical jump height estimate based on the ground reaction force time series, and to calculate a second vertical jump height estimate based on the takeoff time and the landing time; The determination module is used to determine the height error compensation amount based on the first vertical jump height estimate and the second vertical jump height estimate, combined with the motion features extracted from the sensing data of the plurality of inertial measurement units; The compensation module is used to correct the second vertical jump height estimate based on the height error compensation amount to obtain the compensated vertical jump height.

[0026] The beneficial effects of the multi-sensor fusion vertical jump force estimation and height compensation system of the present invention are as follows: The system of this invention deploys multiple inertial measurement units in different segments of the human body and fuses sensor data. It applies a physical constraint that the ground reaction force during the takeoff period approaches zero to estimate the complete reaction force time series. It combines dual height estimates and motion characteristics for error compensation, which solves the technical problems of insufficient information dimension of single sensors, accuracy decay caused by integral drift, and poor portability of high-precision equipment. It improves the accuracy and scene adaptability of vertical jump ground reaction force and takeoff height measurement.

[0027] Thirdly, the technical solution of an electronic device according to the present invention is as follows: It includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps of the multi-sensor fusion method for estimating vertical force and compensating height as described in this invention.

[0028] Fourthly, the technical solution of a computer-readable storage medium provided by the present invention is as follows: The computer-readable storage medium stores instructions that, when read, cause the computer-readable storage medium to perform the steps of the multi-sensor fusion method for estimating vertical force and compensating height as described in this invention.

[0029] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0030] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating an embodiment of a multi-sensor fusion method for estimating vertical jump force and compensating height according to the present invention. Figure 2 This is a schematic diagram illustrating the overall principle. Figure 3 This is a schematic diagram of an embodiment of a multi-sensor fusion system for estimating vertical jump force and compensating height according to the present invention. Figure 4 This is a schematic diagram of an embodiment of an electronic device according to the present invention. Detailed Implementation

[0031] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0032] Figure 1 This diagram illustrates a flowchart of an embodiment of a multi-sensor fusion method for estimating vertical jump force and compensating altitude, provided by the present invention. This method can be executed by an electronic device such as a terminal device or a server. The terminal device can be any fixed or mobile terminal, such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, or wearable device. The server can be a single server or a server cluster consisting of multiple servers. Any electronic device can implement the multi-sensor fusion method for estimating vertical jump force and compensating altitude by having its processor call computer-readable instructions stored in its memory. Figure 1 As shown, it includes the following steps: S1. Collect sensor data from multiple inertial measurement units installed in different segments of the human body.

[0033] In this context, "different human segments" refers to the division of the human body into multiple parts based on anatomical features and motor functions in sports biomechanics analysis, such as the trunk, pelvis, thighs, calves, and feet. For example, in a vertical jump test, sensors are worn on the test subject's waist, the middle of both thighs, and the middle of both calves. "Multiple inertial measurement units" refers to two or more sensor devices capable of measuring the acceleration and angular velocity of an object in three-dimensional space. Each unit typically includes a three-axis accelerometer and a three-axis gyroscope. For example, a test subject might use five inertial measurement units during a vertical jump, fixed at the waist, left thigh, right thigh, left calf, and right calf. "Sensing data" refers to the raw signals collected and output by the inertial measurement units, including acceleration values ​​in at least three orthogonal directions and angular velocity values ​​in three orthogonal directions. For example, a set of data output from the waist inertial measurement unit includes acceleration values ​​along the X, Y, and Z axes (unit: m / s²). 2 ) and angular velocity values ​​about the X, Y, and Z axes (unit: rad / s).

[0034] S2. Based on the sensing data of the multiple inertial measurement units, determine the time of takeoff and the time of landing during the vertical jump.

[0035] The moment of takeoff refers to the instant during a vertical jump when the feet make their final contact with the ground and begin to enter the airborne state; for example, by analyzing the foot inertial measurement unit (IMU) signal, it can be determined that the test subject's feet completely leave the ground at 2.15 seconds during the jump. The moment of landing refers to the instant after the airborne phase of the vertical jump ends when the feet first contact the ground and begin to cushion the impact; for example, by analyzing the foot IMU signal, it can be determined that the test subject's feet touch the ground again at 2.45 seconds during the jump.

[0036] S3. Based on the sensing data of the multiple inertial measurement units, the time of takeoff and the time of landing, and applying the physical constraint that the ground reaction force during the takeoff period approaches zero, estimate the time series of ground reaction force from before takeoff to after landing.

[0037] The physical constraint that the ground reaction force during the airborne phase approaches zero refers to the fact that, based on Newtonian mechanics, there is no direct contact force between the person and the ground during the airborne phase after the person has completely left the ground. Therefore, the ground reaction force should theoretically be zero, and this is a mandatory condition in the algorithm. For example, when estimating the ground reaction force waveform, all force values ​​between the time of takeoff (2.15 seconds) and the time of landing (2.45 seconds) are forcibly corrected to be close to 0 N. The ground reaction force time series refers to a set of continuous data arranged in chronological order, describing the magnitude of the vertical reaction force exerted by the ground on the person during the vertical jump. For example, a set of force values ​​(unit: N) recorded at a frequency of 1000 points per second from before the start of the vertical jump to after the landing buffer forms a force-time curve from second 0 to second 3.

[0038] S4. Based on the ground reaction force time series, calculate the first vertical jump height estimate, and based on the takeoff time and the landing time, calculate the second vertical jump height estimate.

[0039] The first vertical jump height estimate refers to the numerical value of the takeoff height calculated using the impulse-momentum theorem based on the estimated ground reaction force time series. For example, using the net impulse calculated from the pre-takeoff force curve, the takeoff velocity is found to be 2.8 m / s, thus yielding a first vertical jump height estimate of 0.40 m. The second vertical jump height estimate refers to the numerical value of the vertical jump height estimated by calculating the takeoff time and substituting it into a physical formula based on the detected takeoff and landing times. For example, if the measured takeoff time is 0.30 s, substituting it into the formula h = (g * t)... 2 The estimated value of the second vertical jump height calculated by ) / 8 is 0.44 m.

[0040] S5. Based on the first vertical jump height estimate and the second vertical jump height estimate, and combined with the motion features extracted from the sensing data of the plurality of inertial measurement units, determine the height error compensation amount.

[0041] Among them, motion characteristics refer to parameters or indicators extracted from the sensor data of the inertial measurement unit that can quantify specific aspects of the vertical jump motion; for example, motion characteristics include features used to assess the reliability of takeoff event detection, and features describing whether the legs are tucked in during takeoff. Altitude error compensation refers to an adjustment value calculated to correct systematic biases in the second vertical jump altitude estimate; for example, if error model analysis determines that the current jump's flight time is artificially high due to leg tuck in mid-air, 0.05 m needs to be subtracted from the second vertical jump altitude estimate as the altitude error compensation.

[0042] S6. Based on the height error compensation amount, the second vertical jump height estimate is corrected to obtain the compensated vertical jump height.

[0043] The compensated vertical jump height refers to the final vertical jump height result obtained after applying the height error compensation to the second vertical jump height estimate; for example, subtracting the height error compensation of 0.05 m from the second vertical jump height estimate of 0.44 m results in a compensated vertical jump height of 0.39 m.

[0044] The technical solution of this embodiment deploys multiple inertial measurement units in different segments of the human body and fuses sensor data. It applies a physical constraint that the ground reaction force during the takeoff period approaches zero to estimate the complete reaction force time series. It combines the dual height estimates and motion characteristics for error compensation, which solves the technical problems of insufficient information dimension of single sensors, accuracy decay caused by integral drift, and poor portability of high-precision equipment. This improves the accuracy and scene adaptability of vertical jump ground reaction force and takeoff height calculation.

[0045] In one alternative approach, S2 specifically includes: Based on sensing data from at least one inertial measurement unit located on the human foot or lower leg, the system detects a first moment when the amplitude or rate of change of the acceleration signal in the sensing data exceeds a first threshold, and a second moment when the angular velocity signal undergoes a sudden change in direction.

[0046] The acceleration signal amplitude or rate of change refers to the magnitude (amplitude) or the rate of change (rate of change) of the acceleration signal output by the inertial measurement unit in a specific direction; for example, the vertical acceleration measured by the foot inertial measurement unit reaches a peak of 150 m / s² at the moment of impact. 2 Furthermore, its rate of change within 0.01 s exceeds 10000 m / s. 3The first threshold refers to a pre-set threshold value for the amplitude or rate of change of an acceleration signal used to detect motion events; for example, setting the first threshold to 120 m / s². 2 When acceleration exceeds this value, a significant impact event is considered to have occurred. The first moment refers to the specific time point when the amplitude or rate of change of the acceleration signal in the sensor data first exceeds the first threshold; for example, foot acceleration exceeding 120 m / s² at 2.149 seconds. 2 This point in time is recorded as the first moment. A sudden change in the direction of the angular velocity signal refers to a change in the sign of the angular velocity signal output by the inertial measurement unit along a specific axis, or the appearance of an extreme turning point; for example, the angular velocity of the ankle joint's sagittal axis measured by the lower leg inertial measurement unit abruptly changes from positive (dorsiflexion) to negative (plantarflexion) at the moment of liftoff. The second moment refers to the specific point in time at which the angular velocity signal in the sensor data undergoes a sudden change in direction; for example, the lower leg angular velocity undergoes a sudden change from positive to negative at 2.151 seconds, and this point in time is recorded as the second moment.

[0047] Based on the sensing data of the multiple inertial measurement units, the differences or phase relationships between the angular velocity signals of the corresponding inertial measurement units in different segments are calculated to obtain the coordination index.

[0048] The coordination index is a quantitative index obtained by calculating the difference or phase relationship between the angular velocity signals of different segments of the inertial measurement unit. It is used to evaluate the synchronicity of movement of various parts of the body. For example, the cross-correlation coefficient of the angular velocity signals of the thigh and the calf is calculated, and the coordination index is 0.92, which indicates that the two are highly synchronized in movement.

[0049] Based on the first time point, the second time point, and the first set of preset conditions satisfied by the coordination index, it is determined that an off-ground event has occurred, and the time corresponding to the off-ground event is determined as the off-ground time.

[0050] The first set of preset conditions refers to a set of logical rules or threshold combinations set to determine an off-ground event. These rules comprehensively assess whether the first moment, the second moment, and the coordination index together satisfy the off-ground characteristics. For example, the first set of preset conditions might be: if the difference between the first and second moments is less than 0.02 seconds, and the coordination index is higher than 0.85, then an off-ground event is determined to have occurred. An off-ground event is defined as the point of transition in the human body's motion state that the algorithm identifies, based on sensor data and the preset conditions, marking the beginning of the off-ground movement. For example, after comprehensive judgment, the system confirms an off-ground event at 2.150 seconds.

[0051] Based on the first time point, the second time point, and the second set of preset conditions satisfied by the coordination index, a landing event is determined to have occurred, and the time corresponding to the landing event is determined as the landing time.

[0052] The second set of preset conditions refers to another set of logical rules or threshold combinations set to determine the landing event, used to comprehensively judge whether the first moment, the second moment, and the coordination index jointly meet the landing characteristics; for example, the second set of preset conditions is: the peak acceleration at the first moment exceeds 140 m / s². 2 If the sudden change in angular velocity at the second moment exceeds a certain threshold, a landing event is determined to have occurred. A landing event is defined as the point of transition in the human body's motion state that the algorithm identifies based on sensor data and preset conditions, marking the point where the human body makes contact with the ground again; for example, after comprehensive judgment, a landing event is confirmed to have occurred at 2.450 seconds.

[0053] Among the above-mentioned optional methods, the peak acceleration and abrupt changes in angular velocity direction are further captured by the foot or lower leg inertial measurement unit. Combined with multi-segment coordination indicators, the accuracy of the determination of the moment of takeoff and the moment of landing is improved, and the detection error caused by motion variation is reduced.

[0054] In one alternative approach, S3 specifically includes: Based on the sensing data from the multiple inertial measurement units, the acceleration sequence of the human body's center of mass in the vertical direction is calculated.

[0055] The human center of mass refers to the average position of the entire mass of the human body, and its trajectory can be used to represent the overall motion of the human body. For example, by using data from multiple segmental inertial measurement units and human morphological parameters, the vertical trajectory of the center of mass during a vertical jump can be estimated. An acceleration sequence refers to a set of data where the acceleration values ​​of the human center of mass in the vertical direction are arranged chronologically. For example, from the start to the end of a vertical jump, the vertical acceleration values ​​of the center of mass are calculated at 0.001 s intervals, forming a data sequence of length 3000.

[0056] Based on the acceleration sequence and human body mass, the basic ground reaction force sequence is calculated.

[0057] Here, body mass refers to the test subject's weight, a key parameter for calculating ground reaction force; for example, the test subject weighs 70 kg. The basic ground reaction force sequence refers to the preliminary ground reaction force time sequence calculated directly from the human body's center-of-mass acceleration sequence and body mass, according to Newton's second law; for example, adding the gravitational acceleration g (9.81 m / s²) to the center-of-mass vertical acceleration sequence. 2 Multiply by 70 kg to obtain a set of basic force values.

[0058] Based on the sensing data from the multiple inertial measurement units, a feature set containing the kinematic parameters of each segment is extracted.

[0059] The feature set refers to a set of structured parameters extracted from the sensing data of multiple inertial measurement units to describe the motion state; for example, the feature set includes 50 features such as the mean acceleration, variance of angular velocity, and joint angles of each segment.

[0060] The feature set is input into a pre-trained force mapping model to obtain an initial ground reaction force sequence.

[0061] In this context, a force mapping model refers to a mathematical model trained using machine learning methods that maps an input set of kinematic features to a sequence of ground reaction forces. For example, a well-trained long short-term memory neural network model takes a feature set as input and outputs an estimated force sequence. The initial ground reaction force sequence refers to the time series of ground reaction forces directly output by the force mapping model after the feature set is input, without adjustment for physical constraints. For example, the force mapping model outputs an initial force sequence of length 3000 based on the feature set of the current jump.

[0062] Based on the basic ground reaction force sequence and the initial ground reaction force sequence, a fused ground reaction force sequence is generated.

[0063] Among them, the fused ground reaction force sequence refers to the new sequence generated by combining the basic ground reaction force sequence and the initial ground reaction force sequence through a specific algorithm; for example, the basic sequence and the initial sequence are fused with a weight of 6:4 to generate a new force curve.

[0064] In the fused ground reaction force sequence, a zero-reduction constraint is applied to the force value corresponding to the target time period between the takeoff time and the landing time, so that the ground reaction force in the target time period approaches zero, thus obtaining the ground reaction force time sequence.

[0065] The target time period refers to the continuous time interval from the moment of takeoff to the moment of landing in the force sequence; for example, in the fused ground reaction force sequence, the 0.30 s time period from the 2.15 second to the 2.45 second is identified as the target time period.

[0066] In the above-mentioned optional methods, the initial sequence output by the basic ground reaction force calculated by the centroid acceleration and the force mapping model is further integrated, and a zero-reset constraint is applied to the airborne period, so that the time series estimation of reaction force is more in line with physical laws and individual dynamic characteristics.

[0067] In one alternative approach, the step of calculating the estimated first vertical jump height based on the ground reaction force time series includes: Extract the ground reaction force data corresponding to the force stage before the moment of liftoff from the ground reaction force time series.

[0068] The force-exertion phase refers to the main period during a vertical jump, from the start of the squatting exertion to the moment of liftoff, during which the human body exerts force on the ground. For example, the 0.20-second time interval from 1.95 seconds (start of exertion) to 2.15 seconds (liftoff) is defined as the force-exertion phase. Ground reaction force data refers to the force values ​​extracted from the ground reaction force time series corresponding to the force-exertion phase. For example, extracting all force values ​​from timestamps 1.95 seconds to 2.15 seconds from the complete force series constitutes the ground reaction force data for the force-exertion phase.

[0069] The ground reaction force data is integrated to obtain the corresponding impulse.

[0070] Impulse refers to the integral of the ground reaction force data over time during the force action phase. Physically, it represents the cumulative effect of the force over a period of time. For example, numerical integration of the ground reaction force data during the force action phase yields a net impulse of 140 N·s.

[0071] Based on the impulse, body mass, and gravitational acceleration components, the takeoff velocity at the moment of takeoff is calculated.

[0072] The gravitational acceleration component refers to the force corresponding to the body weight that needs to be subtracted from the total ground reaction force when calculating net impulse or takeoff velocity. Its magnitude is the body mass multiplied by the gravitational acceleration g. For example, if the test subject weighs 70 kg, the corresponding gravitational component is 70 kg * 9.81 m / s². 2 = 686.7 N.

[0073] Based on the takeoff speed and gravitational acceleration, the estimated value of the first vertical jump height is calculated.

[0074] Take-off speed refers to the instantaneous velocity of the human body's center of mass in the vertical direction at the moment of take-off. It can be obtained by dividing the net impulse during the force phase by the human body mass. For example, dividing the net impulse of 140 N·s by the human body mass of 70 kg gives a take-off speed of 2.0 m / s.

[0075] In the above-mentioned optional methods, the pre-leap momentum data is further extracted from the ground reaction force time series, and the take-off velocity is calculated by combining the human body mass and gravitational acceleration components to achieve the estimation of the first vertical jump height based on the momentum theorem.

[0076] In one alternative approach, the step of calculating the estimated second vertical jump height based on the takeoff time and the landing time includes: The initial flight time is obtained by calculating the time difference between the landing time and the takeoff time.

[0077] The initial flight time refers to the uncorrected takeoff time calculated by directly subtracting the detected takeoff time from the landing time; for example, subtracting the takeoff time of 2.15 seconds from the landing time of 2.45 seconds gives an initial flight time T of 0.30 seconds.

[0078] Based on the sensing data from the multiple inertial measurement units, the characteristics of human posture changes during the takeoff phase are identified.

[0079] Among them, human posture change characteristics refer to the quantitative characteristics extracted from data of multiple inertial measurement units during the airborne phase that can describe the changes in the relative position or angle of the limbs; for example, calculating the average rate of change of the angle between the thigh and the lower leg during the airborne phase as a human posture change characteristic.

[0080] The initial flight time is corrected based on the human posture change characteristics to obtain the effective flight time.

[0081] The effective flight time refers to the value that is closer to the actual center of mass time after correcting the initial flight time based on the characteristics of human posture changes. For example, if a significant leg retraction action is detected during the takeoff period, the initial flight time of 0.30 s is corrected to an effective flight time of 0.28 s.

[0082] Based on the effective flight time and gravitational acceleration, the estimated value of the second vertical jump height is calculated.

[0083] Among the above-mentioned optional methods, the characteristics of human posture changes during the takeoff phase are further identified based on inertial data, and the initial flight time is corrected to obtain the effective flight time, thereby improving the adaptability of the second vertical jump height estimate to limb movements.

[0084] In one alternative approach, the motion characteristics include: event detection reliability characteristics and airborne attitude characteristics; S5 specifically includes: Calculate the difference in vertical jump height between the first vertical jump height estimate and the second vertical jump height estimate.

[0085] The vertical jump height difference refers to the arithmetic difference between the first vertical jump height estimate and the second vertical jump height estimate; for example, subtracting the second vertical jump height estimate of 0.44 m from the first vertical jump height estimate of 0.40 m results in a vertical jump height difference of -0.04 m.

[0086] From the sensing data of the multiple inertial measurement units, features reflecting the stability of the identification of takeoff and landing events are extracted as the event detection reliability features, and features reflecting the relative motion of limbs during the takeoff phase are extracted as the takeoff posture features.

[0087] Among them, the event detection reliability feature refers to the quantitative indicators used to evaluate the credibility of the recognition results of the takeoff time and landing time; for example, calculating the matching score of the first moment, the second moment and the coordination index used in the takeoff event detection as the event detection reliability feature. The airborne posture feature refers to the quantitative characteristics that specifically describe the relative movement patterns of human limbs, especially the lower limbs, during the airborne phase; for example, calculating the maximum bending angle of the knee joint during the airborne phase and the time point at which this angle is reached as the airborne posture feature.

[0088] The vertical jump height difference, the event detection reliability characteristics, and the take-off attitude characteristics are input into the error compensation model to determine the height error compensation amount.

[0089] Among them, the error compensation model refers to a model that establishes a mathematical relationship between the input variables and the output variables, specifically the height error compensation amount. The input variables include the vertical jump height difference, event detection reliability characteristics, and take-off posture characteristics. For example, a linear regression model takes these characteristics as input and outputs the predicted compensation amount.

[0090] It should be noted that the error compensation model establishes a mapping relationship between the vertical jump height difference, the event detection reliability characteristics, the take-off posture characteristics, and the height error compensation amount based on training data.

[0091] In this context, the mapping relationship refers to the functional correspondence between the input feature space and the output compensation amount defined in the error compensation model. For example, the error compensation model establishes a linear mapping relationship between "vertical jump height difference", "event detection reliability feature" and "airborne attitude feature" and "height error compensation amount" by learning the determined weight parameters.

[0092] In the above-mentioned optional methods, the difference between the first vertical jump height estimate and the second vertical jump height estimate is further calculated, and the error compensation model is integrated with the event detection reliability characteristics and the takeoff attitude characteristics to determine the height error compensation amount and improve the correction accuracy.

[0093] In one alternative approach, S6 specifically includes: Obtain the confidence assessment result corresponding to the height error compensation amount.

[0094] The confidence assessment result refers to the result of a quantitative assessment of the credibility of the high error compensation amount output by the error compensation model under the current input conditions; for example, based on the similarity between the input features and the distribution of the model training data, the confidence of the current compensation amount is assessed as 85%.

[0095] Based on the confidence assessment results, the height error compensation amount is weighted and assigned to obtain a weighted compensation amount.

[0096] The weighted compensation amount refers to the value obtained by scaling the original height error compensation amount according to the corresponding confidence level assessment result; for example, if the original height error compensation amount is 0.05 m and the confidence level is 80%, then the weighted compensation amount is 0.05 m * 80% = 0.04 m.

[0097] The second vertical jump height estimate is corrected and calculated based on the weighted compensation amount to obtain the compensated vertical jump height.

[0098] The correction calculation refers to the process of applying the weighted compensation amount to the estimated second vertical jump height and obtaining the compensated vertical jump height through arithmetic operations; for example, subtracting the weighted compensation amount of 0.04 m from the estimated second vertical jump height of 0.44 m yields a compensated vertical jump height of 0.40 m through subtraction.

[0099] In the above-mentioned optional methods, the confidence assessment result of the height error compensation amount is further obtained, and a weighted compensation amount is generated based on the confidence level. The correction intensity of the second vertical jump height estimate is dynamically adjusted to improve the robustness of the result.

[0100] The multi-sensor fusion method for estimating vertical jump force and compensating height in this embodiment includes multiple sequentially executed data processing and calculation stages. The complete process of the method covers data acquisition, signal calibration and preprocessing, vertical jump event identification, time series estimation of ground reaction force, vertical jump height calculation and error compensation, and result output.

[0101] The data acquisition process is accomplished by deploying multiple inertial measurement units (IMUs) across different segments of the human body. At least two IMUs are used, installed in key segments such as the pelvis, torso, thigh, lower leg, or dorsum of the foot. Each IMU simultaneously acquires triaxial acceleration and triaxial angular velocity data, transmitting the sensor data to a computing device for further processing via wired or wireless communication.

[0102] The acquired sensor data needs to be calibrated, synchronized, and preprocessed. Calibration and synchronization include time synchronization of each inertial measurement unit (IMU), static zero-bias correction, and transformation and unification of the local coordinate system of each sensor to a global coordinate system based on the human body model. Preprocessing includes denoising filtering of the sensor data, separation of gravitational acceleration components, attitude calculation based on quaternions or direction cosine matrices, and resampling of the data sequence to ultimately obtain the linear acceleration and angular kinematics of each segment of the human body in the global coordinate system.

[0103] Vertical jump event recognition is performed based on preprocessed sensor data. The recognition process primarily utilizes data from the distal segment inertial measurement units (IMUs) located in the foot or lower leg to detect whether the amplitude or rate of change of the acceleration signal exceeds a preset threshold, and to detect whether the angular velocity signal undergoes a sudden change in direction. By combining coordination indices calculated from angular velocity signals from multiple IMUs, and based on two sets of preset conditions set separately for takeoff and landing events, a comprehensive judgment is made to determine the takeoff and landing times. This process can identify the preparation phase, crouching eccentric phase, concentric force exertion phase, takeoff time, airborne phase, and landing time of the vertical jump.

[0104] Estimating the ground reaction force time series is the core step of the method. The estimation process integrates data features from multiple inertial measurement units and introduces physical constraints. One implementation includes three technical paths. Path A is a physics-inspired path, which estimates the vertical acceleration of the human body's center of mass by fusing multi-segment vertical acceleration and attitude information. Given the human body mass m, calculate the sequence of ground reaction forces according to Newton's second law: ,in This represents the vertical ground reaction force at time t. This represents gravitational acceleration. This path forces an airtime period. Approaching zero, quiescent period Approaching The physical constraints are as follows: Path B is a data-driven path, constructing a mapping model from the feature set of multiple inertial measurement units to the ground reaction force waveform. The feature set includes vertical acceleration, angular velocity, motion phase labels, and joint relative attitude change features of each segment. The model incorporates physical consistency constraints during training and inference. Path C is a fusion correction path, which merges the basic ground reaction force sequence obtained from Path A with the initial ground reaction force sequence obtained from Path B through an algorithm to generate a fused ground reaction force sequence. Finally, in the fused sequence, the force value corresponding to the airborne period between takeoff and landing is explicitly set to approach zero, resulting in a final ground reaction force time series that conforms to physical laws, from which peak force, impulse, and force rate indicators can be extracted.

[0105] Vertical jump height calculation and error compensation are another core aspect of the method. Height calculation employs multi-path parallel estimation. The first path is an impulse-momentum path based on ground reaction force, calculating the takeoff velocity at the moment of takeoff by integrating the net force value during the centripetal phase before ground separation. The calculation formula is: The integration interval is the time [t1, t2] during the centripetal force exertion period. Then, the estimated height of the first vertical jump is calculated: ,in The first path represents the altitude estimate based on the impulse-momentum theorem. The second path is the time-of-flight path, based on the time of takeoff. With landing time Calculate the initial flight time By combining the human posture change characteristics identified from the takeoff sensor data, T is corrected to obtain the effective flight time, and then the estimated value of the second vertical jump height is calculated. To improve the accuracy of height measurement, an error compensation mechanism is introduced. This mechanism aims to improve the accuracy of height measurement using methods with stronger physical consistency. As a reference benchmark, calculate its relationship with The vertical jump height difference between other path estimates is calculated. Simultaneously, event detection reliability features are extracted from the sensor data to evaluate event detection reliability, along with airborne posture features describing limb movements during the airborne phase. The vertical jump height difference, event detection reliability features, and airborne posture features are input into a pre-trained error compensation model, which establishes a relationship between these input features and the height error compensation amount. The mapping relationship between them, and output. Ultimately, by utilizing Estimate of the second vertical jump height Make corrections to obtain the compensated vertical jump height: This compensation mechanism aims to overcome systematic errors caused by factors such as event recognition bias and mid-air leg retraction.

[0106] The results output stage is responsible for integrating, presenting, and storing all analysis results, including ground reaction force time series waveforms, key dynamic parameters, duration of each stage of vertical jump, original height estimates, and compensated vertical jump height, serving the monitoring and evaluation of sports training.

[0107] like Figure 2 As shown, the solution in this embodiment acquires data through multiple inertial measurement units, goes through data synchronization preprocessing, key event identification, ground reaction force estimation, multi-path height calculation, error modeling and compensation, and finally outputs analysis results.

[0108] In another embodiment of the multi-sensor fusion method for estimating vertical jump force and compensating height according to the present invention, the specific steps include: S10. Collect sensor data from multiple inertial measurement units set in different segments of the human body, and perform sensor calibration and initial attitude alignment after collection, including calibrating the zero bias of each inertial measurement unit based on static posture, and converting the measurement data of all inertial measurement units to a unified global coordinate system.

[0109] S20. Based on the sensing data of at least one inertial measurement unit located on the human foot or lower leg, detect the first moment when the amplitude or rate of change of the acceleration signal exceeds a first threshold, and the second moment when the angular velocity signal undergoes a sudden change in direction; simultaneously, calculate the coordination index between angular velocity signals of different segments based on the sensing data of multiple inertial measurement units; combining the first moment, the second moment, and the coordination index, determine the moment of takeoff and the moment of landing during the vertical jump process according to the preset takeoff event determination conditions and landing event determination conditions.

[0110] S30. Based on the sensing data of multiple inertial measurement units transformed to the global coordinate system, calculate the acceleration sequence of the human body's center of mass in the vertical direction, and combine it with the input human body mass to calculate the basic ground reaction force sequence; simultaneously, extract the kinematic features of each segment based on the sensing data of multiple inertial measurement units to form a feature set, and input the feature set into a pre-trained force mapping model to obtain the initial ground reaction force sequence; fuse the basic ground reaction force sequence and the initial ground reaction force sequence to generate a fused ground reaction force sequence; in the fused ground reaction force sequence, apply a force value zeroing constraint to the time period between the time of takeoff and the time of landing, so that the ground reaction force approaches zero during this time period, and obtain the final ground reaction force time sequence.

[0111] S40. Extract the ground reaction force data corresponding to the force phase before takeoff from the ground reaction force time series, integrate the data to obtain the net impulse, combine the human body mass and gravitational acceleration components to calculate the takeoff velocity at takeoff, and then calculate the estimated value of the first vertical jump height; at the same time, calculate the initial flight time based on the takeoff and landing times, correct the initial flight time according to the human body posture change characteristics identified from the sensor data of the takeoff phase, obtain the effective flight time, and calculate the estimated value of the second vertical jump height based on the effective flight time and gravitational acceleration.

[0112] S50. Calculate the vertical jump height difference between the first vertical jump height estimate and the second vertical jump height estimate; extract event detection reliability features and airborne attitude features from the sensor data of multiple inertial measurement units as motion features; input the vertical jump height difference, event detection reliability features, and airborne attitude features into the error compensation model, which establishes a mapping relationship between the input features and the height error compensation amount based on the training data, and outputs the height error compensation amount; before performing error compensation, evaluate the confidence of the output of the error compensation model under the current input, and dynamically adjust the height error compensation amount according to the confidence evaluation result to obtain the weighted compensation amount.

[0113] S60. Use the weighted compensation amount to correct the estimated value of the second vertical jump height to obtain the compensated vertical jump height; output the compensated vertical jump height, the time series of ground reaction force, and key dynamic indicators.

[0114] This embodiment collects and fuses data from multi-segment inertial measurement units of the human body, performs coordinate unification and event robust recognition, estimates the ground reaction force time series by combining physical constraints and data-driven models, and corrects the error by using a dual-height estimation and confidence-weighted error compensation mechanism. This solves the technical problems in the prior art, such as insufficient information dimension of single sensors, accuracy decay caused by integral drift, susceptibility of height measurement to interference from action strategies, and poor portability of high-precision equipment. It achieves a significant improvement in the accuracy, scene adaptability, and robustness of vertical jump ground reaction force and height measurement.

[0115] Figure 3 This diagram illustrates a structural schematic of an embodiment of a multi-sensor fusion vertical jump estimation and height compensation system 200 provided by the present invention. Figure 3 As shown, the multi-sensor fusion vertical jump estimation and height compensation system 200 includes: The acquisition module 201 is used to acquire sensing data from multiple inertial measurement units installed in different segments of the human body; The acquisition module 202 is used to determine the takeoff time and landing time during the vertical jump based on the sensing data of the plurality of inertial measurement units; The estimation module 203 is used to estimate the time series of ground reaction force from before takeoff to after landing based on the sensing data of the multiple inertial measurement units, the takeoff time and the landing time, and by applying the physical constraint that the ground reaction force during takeoff approaches zero. The calculation module 204 is used to calculate a first vertical jump height estimate based on the ground reaction force time series, and to calculate a second vertical jump height estimate based on the takeoff time and the landing time. The determining module 205 is used to determine the height error compensation amount based on the first vertical jump height estimate and the second vertical jump height estimate, combined with the motion features extracted from the sensing data of the plurality of inertial measurement units; The compensation module 206 is used to correct the second vertical jump height estimate based on the height error compensation amount to obtain the compensated vertical jump height.

[0116] In an alternative embodiment, the acquisition module 202 is specifically used for: Based on sensing data from at least one inertial measurement unit located on the human foot or lower leg, the system detects a first moment when the amplitude or rate of change of the acceleration signal in the sensing data exceeds a first threshold, and a second moment when the angular velocity signal undergoes a sudden change in direction. Based on the sensing data of the multiple inertial measurement units, the differences or phase relationships between the angular velocity signals of the corresponding inertial measurement units in different segments are calculated to obtain the coordination index. Based on the first time point, the second time point, and the first set of preset conditions satisfied by the coordination index, it is determined that an off-ground event has occurred, and the time corresponding to the off-ground event is determined as the off-ground time. Based on the first time point, the second time point, and the second set of preset conditions satisfied by the coordination index, a landing event is determined to have occurred, and the time corresponding to the landing event is determined as the landing time.

[0117] In an alternative embodiment, the estimation module 203 is specifically used for: Based on the sensing data from the multiple inertial measurement units, the acceleration sequence of the human body's center of mass in the vertical direction is calculated; Based on the acceleration sequence and human body mass, calculate the basic ground reaction force sequence; Based on the sensing data from the multiple inertial measurement units, a feature set containing the kinematic parameters of each segment is extracted; The feature set is input into a pre-trained force mapping model to obtain an initial ground reaction force sequence; Based on the basic ground reaction force sequence and the initial ground reaction force sequence, a fused ground reaction force sequence is generated; In the fused ground reaction force sequence, a zero-reduction constraint is applied to the force value corresponding to the target time period between the takeoff time and the landing time, so that the ground reaction force in the target time period approaches zero, thus obtaining the ground reaction force time sequence.

[0118] In an alternative embodiment, the computing module 204 is specifically used for: Extract the ground reaction force data corresponding to the force stage before the moment of liftoff from the ground reaction force time series; The ground reaction force data is integrated to obtain the corresponding impulse; Based on the impulse, human body mass, and gravitational acceleration components, the takeoff velocity at the moment of takeoff is calculated. Based on the takeoff speed and gravitational acceleration, the estimated value of the first vertical jump height is calculated.

[0119] In an alternative embodiment, the computing module 204 is specifically used for: Calculate the time difference between the landing time and the takeoff time to obtain the initial flight time; Based on the sensing data from the multiple inertial measurement units, the characteristics of human posture changes during the takeoff phase are identified. The initial flight time is corrected based on the human posture change characteristics to obtain the effective flight time; Based on the effective flight time and gravitational acceleration, the estimated value of the second vertical jump height is calculated.

[0120] In one alternative approach, the motion features include: event detection reliability features and airborne posture features; the determining module 205 is specifically used for: Calculate the difference in vertical jump height between the first vertical jump height estimate and the second vertical jump height estimate; From the sensing data of the multiple inertial measurement units, features reflecting the stability of the identification of takeoff and landing events are extracted as the event detection reliability features, and features reflecting the relative motion of limbs during the takeoff phase are extracted as the takeoff posture features. The vertical jump height difference, the event detection reliability characteristics, and the take-off attitude characteristics are input into the error compensation model to determine the height error compensation amount; The error compensation model establishes a mapping relationship between the vertical jump height difference, the event detection reliability characteristics, the take-off posture characteristics, and the height error compensation amount based on training data.

[0121] In an alternative embodiment, the compensation module 206 is specifically used for: Obtain the confidence assessment result corresponding to the height error compensation amount; Based on the confidence assessment results, the height error compensation amount is weighted and assigned to obtain a weighted compensation amount; The second vertical jump height estimate is corrected and calculated based on the weighted compensation amount to obtain the compensated vertical jump height.

[0122] It should be noted that the beneficial effects of the multi-sensor fusion vertical jump estimation and height compensation system 200 provided in the above embodiments are the same as those of the multi-sensor fusion vertical jump estimation and height compensation method described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0123] The multi-sensor fusion vertical jump force estimation and height compensation system 200 of the present invention can be a computer program (including program code) running on a computer device. For example, the multi-sensor fusion vertical jump force estimation and height compensation system 200 of the present invention is an application software that can be used to execute the corresponding steps in the multi-sensor fusion vertical jump force estimation and height compensation method of the present invention.

[0124] In some embodiments, the multi-sensor fusion vertical jump force estimation and height compensation system 200 of the present invention can be implemented in a combination of hardware and software. As an example, the multi-sensor fusion vertical jump force estimation and height compensation system 200 of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the multi-sensor fusion vertical jump force estimation and height compensation method of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0125] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0126] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned multi-sensor fusion methods for estimating vertical jump force and compensating height. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the multi-sensor fusion method for estimating vertical jump force and compensating height as shown in any embodiment of the present invention by calling the computer program.

[0127] In one alternative embodiment, an electronic device is provided, such as Figure 4 As shown, Figure 4 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0128] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0129] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0130] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0131] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0132] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0133] It should be noted that, Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0134] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned multi-sensor fusion methods for estimating vertical jump force and compensating height.

[0135] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0136] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned multi-sensor fusion method for estimating vertical force and compensating height.

[0137] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0138] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0139] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0140] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0141] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0142] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0143] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0144] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A multi-sensor fusion method for estimating vertical jump force and compensating for height, characterized in that, include: Collect sensor data from multiple inertial measurement units installed in different segments of the human body; Based on the sensing data from the multiple inertial measurement units, the takeoff time and landing time during the vertical jump are determined. Based on the sensing data of the multiple inertial measurement units, the time of takeoff and the time of landing, and with the physical constraint that the ground reaction force during takeoff approaches zero, the time series of ground reaction force from before takeoff to after landing is estimated. Based on the ground reaction force time series, the first vertical jump height estimate is calculated, and based on the takeoff time and the landing time, the second vertical jump height estimate is calculated. Based on the first vertical jump height estimate and the second vertical jump height estimate, and combined with the motion features extracted from the sensing data of the plurality of inertial measurement units, the height error compensation amount is determined; The second vertical jump height estimate is corrected based on the height error compensation amount to obtain the compensated vertical jump height.

2. The multi-sensor fusion method for estimating vertical jump force and compensating height according to claim 1, characterized in that, The steps for determining the takeoff and landing times during a vertical jump based on the sensing data from the multiple inertial measurement units include: Based on sensing data from at least one inertial measurement unit located on the human foot or lower leg, the system detects a first moment when the amplitude or rate of change of the acceleration signal in the sensing data exceeds a first threshold, and a second moment when the angular velocity signal undergoes a sudden change in direction. Based on the sensing data of the multiple inertial measurement units, the differences or phase relationships between the angular velocity signals of the corresponding inertial measurement units in different segments are calculated to obtain the coordination index. Based on the first time point, the second time point, and the first set of preset conditions satisfied by the coordination index, it is determined that an off-ground event has occurred, and the time corresponding to the off-ground event is determined as the off-ground time. Based on the first time point, the second time point, and the second set of preset conditions satisfied by the coordination index, a landing event is determined to have occurred, and the time corresponding to the landing event is determined as the landing time.

3. The multi-sensor fusion method for estimating vertical jump force and compensating height according to claim 1, characterized in that, Based on the sensing data from the multiple inertial measurement units, the takeoff time, and the landing time, and applying the physical constraint that the ground reaction force during takeoff approaches zero, the step of estimating the time series of ground reaction force from before takeoff to after landing includes: Based on the sensing data from the multiple inertial measurement units, the acceleration sequence of the human body's center of mass in the vertical direction is calculated; Based on the acceleration sequence and human body mass, calculate the basic ground reaction force sequence; Based on the sensing data from the multiple inertial measurement units, a feature set containing the kinematic parameters of each segment is extracted; The feature set is input into a pre-trained force mapping model to obtain an initial ground reaction force sequence; Based on the basic ground reaction force sequence and the initial ground reaction force sequence, a fused ground reaction force sequence is generated; In the fused ground reaction force sequence, a zero-reduction constraint is applied to the force value corresponding to the target time period between the takeoff time and the landing time, so that the ground reaction force in the target time period approaches zero, thus obtaining the ground reaction force time sequence.

4. The multi-sensor fusion method for estimating vertical jump force and compensating height according to claim 3, characterized in that, The step of calculating the estimated value of the first vertical jump height based on the ground reaction force time series includes: Extract the ground reaction force data corresponding to the force stage before the moment of liftoff from the ground reaction force time series; The ground reaction force data is integrated to obtain the corresponding impulse; Based on the impulse, human body mass, and gravitational acceleration components, the takeoff velocity at the moment of takeoff is calculated. Based on the takeoff speed and gravitational acceleration, the estimated value of the first vertical jump height is calculated.

5. The multi-sensor fusion method for estimating vertical jump force and compensating height according to claim 4, characterized in that, The step of calculating the estimated value of the second vertical jump height based on the takeoff time and the landing time includes: Calculate the time difference between the landing time and the takeoff time to obtain the initial flight time; Based on the sensing data from the multiple inertial measurement units, the characteristics of human posture changes during the takeoff phase are identified. The initial flight time is corrected based on the human posture change characteristics to obtain the effective flight time; Based on the effective flight time and gravitational acceleration, the estimated value of the second vertical jump height is calculated.

6. The multi-sensor fusion method for estimating vertical jump force and compensating height according to claim 5, characterized in that, The motion characteristics include: event detection reliability characteristics and airborne attitude characteristics; the step of determining the height error compensation amount based on the first vertical jump height estimate and the second vertical jump height estimate, combined with the motion characteristics extracted from the sensor data of the plurality of inertial measurement units, includes: Calculate the difference in vertical jump height between the first vertical jump height estimate and the second vertical jump height estimate; From the sensing data of the multiple inertial measurement units, features reflecting the stability of the identification of takeoff and landing events are extracted as the event detection reliability features, and features reflecting the relative motion of limbs during the takeoff phase are extracted as the takeoff posture features. The vertical jump height difference, the event detection reliability characteristics, and the take-off attitude characteristics are input into the error compensation model to determine the height error compensation amount; The error compensation model establishes a mapping relationship between the vertical jump height difference, the event detection reliability characteristics, the take-off posture characteristics, and the height error compensation amount based on training data.

7. The multi-sensor fusion method for estimating vertical jump force and compensating height according to claim 6, characterized in that, The step of correcting the second vertical jump height estimate based on the height error compensation amount to obtain the compensated vertical jump height includes: Obtain the confidence assessment result corresponding to the height error compensation amount; Based on the confidence assessment results, the height error compensation amount is weighted and assigned to obtain a weighted compensation amount; The second vertical jump height estimate is corrected and calculated based on the weighted compensation amount to obtain the compensated vertical jump height.

8. A multi-sensor fusion system for estimating vertical jump force and compensating height, characterized in that, include: The data acquisition module is used to collect sensor data from multiple inertial measurement units installed in different segments of the human body. The acquisition module is used to determine the takeoff time and landing time during the vertical jump based on the sensing data of the multiple inertial measurement units. The estimation module is used to estimate the time series of ground reaction forces from before takeoff to after landing, based on the sensing data of the multiple inertial measurement units, the takeoff time and the landing time, and by applying the physical constraint that the ground reaction force during takeoff approaches zero. The calculation module is used to calculate a first vertical jump height estimate based on the ground reaction force time series, and to calculate a second vertical jump height estimate based on the takeoff time and the landing time; The determination module is used to determine the height error compensation amount based on the first vertical jump height estimate and the second vertical jump height estimate, combined with the motion features extracted from the sensing data of the plurality of inertial measurement units; The compensation module is used to correct the second vertical jump height estimate based on the height error compensation amount to obtain the compensated vertical jump height.

9. An electronic device, characterized in that, The electronic device includes a processor coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor to enable the electronic device to implement the multi-sensor fusion method for estimating vertical jump force and compensating height as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which, when executed by a processor, implements the multi-sensor fusion method for estimating vertical jump force and compensating height as described in any one of claims 1 to 7.

Images