Reconstruction method and system for multi-stage motion trails of trampoline competitive actions, electronic equipment and storage medium

Abstract

The invention belongs to the field of motion track reconstruction, and discloses a multi-stage motion track reconstruction method and system for trampoline competitive actions, electronic equipment and a storage medium, and the method comprises the following steps: obtaining multi-source motion data of an athlete in a trampoline motion process, and extracting action features based on the multi-source motion data; on the basis of the action features, the complete movement track is divided into a take-off stage, a soaring stage and a net touching stage; respectively constructing a take-off stage motion model, a soaring stage motion model and a net touching stage motion model based on different stages to obtain a multi-stage motion model, and generating a take-off trajectory segment, a soaring trajectory segment and a net touching trajectory segment based on the multi-stage motion model; and track splicing is carried out on the take-off track section, the air track section and the net touching track section according to time continuity, and a complete motion track is obtained. The reconstructed high-fidelity trajectory can directly generate multi-dimensional technical indexes, and core technical support is provided for scientific training, automatic scoring and virtual training systems.

Description

Technical Field

[0001] This invention relates to the field of motion trajectory reconstruction technology, specifically to a method, system, electronic device, and storage medium for reconstructing multi-stage motion trajectories of trampoline sports movements. Background Technology

[0002] High-precision reconstruction of motion trajectories in trampoline sports is crucial for competitive training, but existing methods have significant limitations. Traditional single models (such as pure vision or inertial navigation) struggle to adapt to the multi-stage heterogeneous dynamics of trampolines: the contact phase involves strong nonlinear impacts to the net (including Hertz contact effects and viscoelastic hysteresis); the takeoff phase requires accurate capture of parabolic center-of-mass motion and high-speed flipping posture; and the take-off phase requires coupling the net rebound force with the active push-off force. Single models are prone to trajectory jumps in the transition zones between phases, with measured center-of-mass position errors exceeding 8 cm. Existing multi-source fusion solutions (vision / IMU / net sensor) mostly focus on data alignment without deeply exploring physical correlations—vision is easily obscured by motion blur, IMU saturates under impact and exhibits significant take-off drift, and net sensor data is not transformed into effective dynamic constraints, leading to occlusion or failure in high-dynamic scene reconstruction. Phase segmentation relies on empirical thresholds (such as peak acceleration), and the identification error for microsecond-level events such as the "net rebound start point" often exceeds 30 ms, causing subsequent model initialization errors. Segmented trajectory stitching only performs simple time alignment, ignoring the physical continuity of position, velocity, and attitude. This results in boundary velocity jumps exceeding 0.5 m / s, violating the laws of rigid body motion. The industry urgently needs a reconstruction method that can deeply integrate multi-source data, accurately segment stages, adapt to dynamic characteristics, and ensure continuity. Summary of the Invention

[0003] To address the above technical problems, this invention provides a method for reconstructing the multi-stage motion trajectory of trampoline athletic movements, comprising the following steps:

[0004] Acquire multi-source motion data of athletes during trampoline exercise, and extract motion features based on the multi-source motion data;

[0005] Based on the aforementioned motion characteristics, the complete motion trajectory is divided into the take-off phase, the flight phase, and the net-touch phase.

[0006] Based on different stages, a motion model for the take-off stage, a motion model for the flight stage, and a motion model for the net touch stage are constructed to obtain a multi-stage motion model. Based on the multi-stage motion model, a take-off trajectory segment, a flight trajectory segment, and a net touch trajectory segment are generated.

[0007] The take-off trajectory segment, the airborne trajectory segment, and the net-touching trajectory segment are spliced ​​together according to time continuity to obtain a complete motion trajectory.

[0008] Preferably, the method for obtaining the motion features includes:

[0009] The multi-source motion data is obtained by acquiring video data, IMU data, and net surface data through several high-speed cameras deployed in the trampoline training area, IMU sensors installed on key parts of the athlete's body, and a sensor array installed under the trampoline net.

[0010] The multi-source motion data is denoised and filtered, and aligned on a time scale to obtain processed video data, processed IMU data, and processed mesh data.

[0011] The processed video data is processed using computer vision algorithms to extract the athlete's body contour features;

[0012] The processed data is processed using a posture calculation algorithm to detect specific action event features;

[0013] The processed mesh data is then processed to calculate the mesh contact characteristics;

[0014] The body contour features, the action event features, and the touch screen features are fused together to obtain the action features.

[0015] Preferably, the method for constructing the motion model of the take-off phase includes:

[0016] A parameterized nonlinear spring-damped system model is established to describe the dynamic relationship between the trampoline net surface deformation and the trampoline rebound force:

[0017]

[0018] Among them, F bed δ represents the trampoline rebound force, t represents the trampoline net surface deformation, and t represents the time variable.

[0019] Based on the aforementioned body contour features, the athlete is simplified into a multi-rigid-body system containing several body segments, and the active muscle torques of the ankle, knee, and hip joints are calculated.

[0020] Based on the aforementioned active muscle torque and the aforementioned dynamic relationship, a motion model for the take-off phase is constructed:

[0021]

[0022] Where M represents the mass matrix, q represents the body posture, C represents the Coriolis force and centripetal force terms, G represents the gravity term, J represents the Jacobian matrix at the contact point, T represents the transpose of the matrix, and τ active τ represents the active muscle torque. passive It indicates the passive organizing torque.

[0023] Preferably, the method for constructing the motion model during the takeoff phase includes:

[0024] Construct motion constraints, which include center of mass trajectory constraints and angular momentum conservation constraints;

[0025] Based on the aforementioned motion constraints, the 3D rotational posture of the entire body and each limb segment is represented using quaternions to obtain the motion model for the airborne phase:

[0026]

[0027] Where θ represents the rotation angle, I represents the moment of inertia tensor, and ω represents the angular velocity.

[0028] Preferably, the method for constructing the motion model during the touch-the-net phase includes:

[0029] The local deformation field distribution of the trampoline surface is obtained by using the sensor array located below the trampoline surface, and a spatially distributed rebound force model is established.

[0030] By utilizing the difference in force-deformation relationship during mesh sinking and mesh rebound, a hysteresis effect model is constructed.

[0031] By combining the rebound force model and the hysteresis effect model, the motion model of the touch-the-net stage is constructed.

[0032] Preferably, the method for obtaining the complete motion trajectory includes:

[0033] The take-off trajectory segment, the take-off trajectory segment, and the net-touch trajectory segment are time-aligned using time-shift interpolation, and the data of the three trajectory segments are resampled at the same time resolution to obtain the aligned trajectory segments.

[0034] Construct boundary state continuity constraints, which include: position continuity constraints, velocity continuity constraints, and attitude angle continuity constraints;

[0035] Based on the boundary state continuity constraint, the take-off trajectory segment, the airborne trajectory segment, and the net-touching trajectory segment are sequentially connected in chronological order to obtain the complete motion trajectory.

[0036] The present invention also provides a multi-stage motion trajectory reconstruction system for trampoline sports movements. The system is used to implement the above-mentioned method and includes: a feature extraction module, a stage division module, a multi-stage trajectory generation module, and a trajectory stitching module.

[0037] The feature extraction module is used to acquire multi-source motion data of athletes during trampoline exercise, and extract motion features based on the multi-source motion data;

[0038] The phase segmentation module divides the complete motion trajectory into the take-off phase, the flight phase, and the net-touch phase based on the motion characteristics.

[0039] The multi-stage trajectory generation module constructs motion models for the take-off stage, the flight stage, and the net-touch stage based on different stages to obtain a multi-stage motion model, and generates take-off trajectory segments, flight trajectory segments, and net-touch trajectory segments based on the multi-stage motion model.

[0040] The trajectory splicing module is used to splice the take-off trajectory segment, the airborne trajectory segment, and the net-touching trajectory segment according to the time continuity to obtain a complete motion trajectory.

[0041] The present invention also provides an electronic device, characterized in that it includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for reconstructing the multi-stage motion trajectory of trampoline sports movements.

[0042] The present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, which, when executed, implements the above-described method for reconstructing the multi-stage motion trajectory of trampoline sports movements.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] This invention accurately segments the motion phases through multi-source information fusion and constructs specialized models for the dynamic characteristics of the contact, takeoff, and launch phases, significantly improving trajectory reconstruction accuracy. Based on nonlinear mesh interaction modeling, rigid body kinematic constraints, and muscle-force coupling solution mechanisms, it effectively overcomes the distortion problem in the transition zone of traditional single models. Deep integration of the physical characteristics of vision, inertia, and mesh sensing greatly enhances robustness under limb occlusion and impact scenarios. The boundary state consistency optimization algorithm strictly ensures the continuity of position, velocity, and attitude across phases, eliminating abrupt changes in kinematic parameters. The reconstructed high-fidelity trajectory can directly generate multi-dimensional technical indicators, providing core technical support for scientific training, automated scoring, and virtual training systems. Attached Figure Description

[0045] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention.

[0048] Explanation of reference numerals in the attached figures:

[0049] 1010, Processor; 1020, Memory; 1030, Input / Output Interface; 1040, Communication Interface; 1050, Bus. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0052] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Example 1

[0054] In this embodiment, as Figure 1 As shown, a method for reconstructing the multi-stage motion trajectory of trampoline sports movements includes the following steps:

[0055] S1. Acquire multi-source motion data of athletes during trampoline exercise, and extract motion features based on the multi-source motion data.

[0056] The method for obtaining motion characteristics includes: acquiring video data, IMU data, and net surface data respectively through several high-speed cameras deployed on the trampoline training field, IMU sensors placed on key parts of the athlete's body, and a sensor array placed under the trampoline net, thus obtaining multi-source motion data. In this embodiment, all data acquisition devices (high-speed cameras, IMU sensors, and sensor array) are strictly synchronized using a unified high-precision time source (such as GPS time or hardware trigger signal) to ensure that all data streams have consistent timestamps. The multi-source motion data is denoised and filtered, and aligned on a time scale to obtain processed video data, processed IMU data, and processed mesh data. In this embodiment, the acquired video data is denoised, distortion corrected (using calibration parameters), and image enhanced (e.g., adjusting contrast) to improve the accuracy of subsequent analysis. The IMU data is filtered (e.g., low-pass filtering to remove high-frequency noise, high-pass filtering to remove the influence of gravity offset), zero-bias correction, and scale factor correction to improve the accuracy and reliability of sensor data. The pressure or strain signals acquired by the sensor array are filtered and denoised, and spatial interpolation may be performed to obtain more continuous mesh deformation field information. Based on time synchronization, it may be necessary to perform fine time alignment on all preprocessed data according to the initial moment or specific marker point (e.g., the moment of takeoff).

[0057] Computer vision algorithms are used to process the processed video data and extract the athlete's body contour features. In this embodiment, computer vision algorithms are used to automatically identify and track the 2D or 3D coordinates (if multi-view reconstruction is used) of key anatomical joints (such as the top of the head, shoulder, elbow, wrist, hip, knee, ankle, toe, etc.) of the athlete's body in the video sequence, and extract the athlete's body contour, center of mass position, spatial orientation angles (pitch, yaw, roll) of each limb segment, etc., to obtain the athlete's body contour features.

[0058] The processed data is processed using attitude calculation algorithms to detect specific motion event features. In this embodiment, attitude calculation is performed using IMU data (usually combined with filtering algorithms such as Kalman filtering, complementary filtering, or optimization-based methods) to estimate the three-dimensional attitude (Eulerian angles or quaternions) of the sensor attachment site (and thus infer the relevant limb segments) in the global or relative coordinate system. The linear velocity, angular velocity, and displacement changes of the limbs are estimated by integration (drift problems need to be handled carefully) or by combining with a dynamic model (especially when vision is limited or obstructed). Specific motion events are detected, such as the moment of take-off (the point of sudden change in acceleration / angular velocity), the highest point (the point where the vertical velocity crosses zero), and the moment of contact with the net (the peak of impact acceleration), etc., to obtain motion event features.

[0059] The processed net surface data is processed to calculate the net contact characteristics. In this embodiment, the pressure / strain data is analyzed to accurately identify the start time of net contact (when the pressure begins to rise significantly), the end time of net contact (when the pressure drops below the threshold), and the moment of maximum sinking depth (pressure peak or deformation peak). Information such as the center position of the contact area between the net surface and the athlete's foot and the direction of the net surface rebound force vector are calculated to obtain the net contact characteristics.

[0060] The motion features are obtained by fusing body contour features, action event features, and web touch features.

[0061] S2. Based on motion characteristics, the complete motion trajectory is divided into the take-off phase, the flight phase, and the net-touching phase.

[0062] In this embodiment, the take-off phase is defined as the moment when the net's rebound force begins to generate a significant upward net acceleration on the athlete and the athlete begins to actively push off. The moment when the net pressure begins to rise significantly and steadily from its lowest point (maximum sinking depth) is also selected. The moment of net exit is defined as the end boundary of the take-off phase. The take-off phase is obtained through these two boundaries. The airborne phase is defined as the situation where the athlete is completely off the net and only subject to gravity, with the next net touch as the end boundary. The airborne phase is obtained through these two boundaries. The net-touching phase is defined as the start boundary of the net-touch phase, with the moment of net exit as the end boundary. The net-touch phase is obtained through these two boundaries.

[0063] S3. Construct motion models for the take-off phase, the flight phase, and the net-touch phase based on different phases to obtain a multi-stage motion model, and generate take-off trajectory segments, flight trajectory segments, and net-touch trajectory segments based on the multi-stage motion model.

[0064] The method for constructing the motion model of the take-off phase includes: establishing a parameterized nonlinear spring-damped system model to describe the dynamic relationship between the trampoline net deformation and the trampoline rebound force.

[0065]

[0066] Among them, F bed Let δ represent the trampoline rebound force, δ represent the trampoline net surface shape variable, and t represent the time variable. Based on the body contour features, the athlete is simplified into a multi-rigid-body system containing several body segments, and the active muscle torques of the ankle, knee, and hip joints are calculated. Based on the active muscle torques and dynamic relationships, a motion model for the take-off phase is constructed.

[0067]

[0068] Where M represents the mass matrix, q represents the body posture, C represents the Coriolis force and centripetal force terms, G represents the gravity term, J represents the Jacobian matrix at the contact point, T represents the transpose of the matrix, and τ active τ represents the active muscle torque. passive It indicates the passive organizing torque.

[0069] In this embodiment, by solving the motion model of the take-off phase, the 3D trajectory of the athlete's whole body center of mass, the 3D trajectory of each major joint, and the change of the overall body posture (Euler angles or quaternions) over time are obtained, which constitute the take-off trajectory segment.

[0070] The method for constructing the motion model during the airborne phase includes: constructing motion constraints, including center-of-mass trajectory constraints and angular momentum conservation constraints; based on the motion constraints, using quaternions to represent the 3D rotational posture of the whole body and each limb segment, the motion model of the airborne phase is obtained.

[0071]

[0072] Where θ represents the rotation angle, I represents the moment of inertia tensor, and ω represents the angular velocity.

[0073] In this embodiment, the high-precision, smooth 3D parabolic trajectory of the athlete's whole body center of mass (CoM), the 3D trajectory of each major joint, and the detailed body posture (rotation of each limb segment) sequence obtained by the airborne phase motion model constitute the airborne trajectory segment.

[0074] The method for constructing the motion model of the touch-the-net phase includes: using a sensor array set below the trampoline net to obtain the local deformation field distribution of the net and establishing a spatially distributed rebound force model; using the difference in force-deformation relationship during net sinking and net rebound to construct a hysteresis effect model; and combining the rebound force model and the hysteresis effect model to construct the motion model of the touch-the-net phase.

[0075] In this embodiment, the 3D trajectory of the athlete's center of mass during the net touch (presenting a typical "V" or "U" shaped sinking-rebound path), the 3D trajectory of each major joint (especially the cushioning-extension movement of the lower limb joints), the sequence of body posture changes, and the key net-foot interaction force / torque time history are reconstructed to form the net touch trajectory segment.

[0076] S4. The take-off trajectory segment, the flight trajectory segment, and the net-touch trajectory segment are spliced ​​together according to the time continuity to obtain the complete motion trajectory.

[0077] The method for obtaining the complete motion trajectory includes: aligning the takeoff trajectory segment, flight trajectory segment, and net-touch trajectory segment using time-shift interpolation, and resampling the data of the three trajectory segments at the same time resolution to obtain the aligned trajectory segments. Boundary state continuity constraints are constructed, including position continuity constraints, velocity continuity constraints, and attitude angle continuity constraints. In this embodiment, the position continuity constraint is: the end position of the takeoff / flight / net-touch segment must be equal to the starting position of the next segment; the velocity continuity constraint is: the end linear velocity of the takeoff / flight / net-touch segment must be equal to the starting linear velocity of the next segment; the attitude angle continuity constraint includes: the end attitude of the takeoff / flight / net-touch segment must be equal to the starting attitude of the next segment, and the end angular velocity of the takeoff / flight / net-touch segment must be equal to the starting angular velocity of the next segment. Based on the boundary state continuity constraints, the takeoff trajectory segment, flight trajectory segment, and net-touch trajectory segment are sequentially connected in chronological order to obtain the complete motion trajectory.

[0078] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0079] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the sequence number of each step in the above embodiments does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The actions or steps recorded in the claims can be performed in a different order than that in the above embodiments and can still achieve the desired result. In addition, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] Example 2

[0081] In this embodiment, a multi-stage motion trajectory reconstruction system for trampoline sports includes: a feature extraction module, a stage division module, a multi-stage trajectory generation module, and a trajectory stitching module.

[0082] The feature extraction module acquires multi-source motion data of athletes during trampoline exercise and extracts motion features based on the multi-source motion data. The phase segmentation module divides the complete motion trajectory into the take-off phase, the flight phase, and the net-touch phase based on the motion features. The multi-stage trajectory generation module constructs motion models for the take-off phase, the flight phase, and the net-touch phase based on different phases to obtain a multi-stage motion model, and generates take-off trajectory segments, flight trajectory segments, and net-touch trajectory segments based on the multi-stage motion model. The trajectory stitching module stitches the take-off trajectory segments, flight trajectory segments, and net-touch trajectory segments according to temporal continuity to obtain the complete motion trajectory.

[0083] The system described in the above embodiments is used to implement the corresponding multi-stage motion trajectory reconstruction method for trampoline sports movements in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0084] It should be noted that the aforementioned multi-stage motion trajectory reconstruction system for trampoline sports movements is embodied in the form of functional units. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0085] For example, a "module" can be a software program, hardware circuit, or a combination of both that implements the above functions. Hardware circuits may include application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0086] Example 3

[0087] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the multi-stage motion trajectory reconstruction method for trampoline sports movements described in any of the above embodiments.

[0088] Figure 2 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0089] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0090] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0091] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0092] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0093] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0094] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0095] The system described in the above embodiments is used to implement the corresponding multi-stage motion trajectory reconstruction method for trampoline sports movements in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0096] Example 4

[0097] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the multi-stage motion trajectory reconstruction method for trampoline sports movements as described in any of the above embodiments.

[0098] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0099] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the multi-stage motion trajectory reconstruction method for trampoline sports movements as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0100] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0101] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuitry) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0102] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0103] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0104] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for reconstructing the multi-stage motion trajectory of trampoline athletic movements, characterized in that, Includes the following steps: Acquire multi-source motion data of athletes during trampoline exercise, and extract motion features based on the multi-source motion data; Based on the aforementioned motion characteristics, the complete motion trajectory is divided into the take-off phase, the flight phase, and the net-touch phase. Based on different stages, a motion model for the take-off stage, a motion model for the flight stage, and a motion model for the net touch stage are constructed to obtain a multi-stage motion model. Based on the multi-stage motion model, a take-off trajectory segment, a flight trajectory segment, and a net touch trajectory segment are generated. The take-off trajectory segment, the airborne trajectory segment, and the net-touching trajectory segment are spliced ​​together according to time continuity to obtain a complete motion trajectory.

2. The method for reconstructing the multi-stage motion trajectory of trampoline athletic movements according to claim 1, characterized in that, The methods for obtaining the action features include: The multi-source motion data is obtained by acquiring video data, IMU data, and net surface data through several high-speed cameras deployed in the trampoline training area, IMU sensors installed on key parts of the athlete's body, and a sensor array installed under the trampoline net. The multi-source motion data is denoised and filtered, and aligned on a time scale to obtain processed video data, processed IMU data, and processed mesh data. The processed video data is processed using computer vision algorithms to extract the athlete's body contour features; The processed data is processed using a posture calculation algorithm to detect specific action event features; The processed mesh data is then processed to calculate the mesh contact characteristics; The body contour features, the action event features, and the touch screen features are fused together to obtain the action features.

3. The method for reconstructing the multi-stage motion trajectory of trampoline athletic movements according to claim 2, characterized in that, The method for constructing the motion model of the take-off phase includes: A parameterized nonlinear spring-damped system model is established to describe the dynamic relationship between the trampoline net surface deformation and the trampoline rebound force: Among them, F bed δ represents the trampoline rebound force, t represents the trampoline net surface deformation, and t represents the time variable. Based on the aforementioned body contour features, the athlete is simplified into a multi-rigid-body system containing several body segments, and the active muscle torques of the ankle, knee, and hip joints are calculated. Based on the aforementioned active muscle torque and the aforementioned dynamic relationship, a motion model for the take-off phase is constructed: Where M represents the mass matrix, q represents the body posture, C represents the Coriolis force and centripetal force terms, G represents the gravity term, J represents the Jacobian matrix at the contact point, T represents the transpose of the matrix, and τ active τ represents the active muscle torque. passive It indicates the passive organizing torque.

4. The method for reconstructing the multi-stage motion trajectory of trampoline athletic movements according to claim 1, characterized in that, The method for constructing the motion model during the takeoff phase includes: Construct motion constraints, which include center of mass trajectory constraints and angular momentum conservation constraints; Based on the aforementioned motion constraints, the 3D rotational posture of the entire body and each limb segment is represented using quaternions to obtain the motion model for the airborne phase: Where θ represents the rotation angle, I represents the moment of inertia tensor, and ω represents the angular velocity.

5. The method for reconstructing the multi-stage motion trajectory of trampoline athletic movements according to claim 2, characterized in that, The method for constructing the motion model during the touch-the-net phase includes: The local deformation field distribution of the trampoline surface is obtained by using the sensor array located below the trampoline surface, and a spatially distributed rebound force model is established. By utilizing the difference in force-deformation relationship during mesh sinking and mesh rebound, a hysteresis effect model is constructed. By combining the rebound force model and the hysteresis effect model, the motion model of the touch-the-net stage is constructed.

6. The method for reconstructing the multi-stage motion trajectory of trampoline athletic movements according to claim 1, characterized in that, The methods for obtaining the complete motion trajectory include: The take-off trajectory segment, the take-off trajectory segment, and the net-touch trajectory segment are time-aligned using time-shift interpolation, and the data of the three trajectory segments are resampled at the same time resolution to obtain the aligned trajectory segments. Construct boundary state continuity constraints, which include: position continuity constraints, velocity continuity constraints, and attitude angle continuity constraints; Based on the boundary state continuity constraint, the take-off trajectory segment, the airborne trajectory segment, and the net-touching trajectory segment are sequentially connected in chronological order to obtain the complete motion trajectory.

7. A multi-stage motion trajectory reconstruction system for trampoline sports movements, said system being used to implement the method described in any one of claims 1-6, characterized in that, include: The module includes a feature extraction module, a stage division module, a multi-stage trajectory generation module, and a trajectory stitching module. The feature extraction module is used to acquire multi-source motion data of athletes during trampoline exercise, and extract motion features based on the multi-source motion data; The phase segmentation module divides the complete motion trajectory into the take-off phase, the flight phase, and the net-touch phase based on the motion characteristics. The multi-stage trajectory generation module constructs motion models for the take-off stage, the flight stage, and the net-touch stage based on different stages to obtain a multi-stage motion model, and generates take-off trajectory segments, flight trajectory segments, and net-touch trajectory segments based on the multi-stage motion model. The trajectory splicing module is used to splice the take-off trajectory segment, the airborne trajectory segment, and the net-touching trajectory segment according to the time continuity to obtain a complete motion trajectory.

8. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method for reconstructing the multi-stage motion trajectory of trampoline sports movements as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method for reconstructing the multi-stage motion trajectory of trampoline sports movements as described in any one of claims 1 to 6.

Images