Method and system for spatial depth perception and action coupling evaluation and training based on mixed reality
Patent Information
- Application Number
- CN202610963540.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-30
- Publication Date
- 2026-10-20
Smart Images
Figure FT_1 
Figure FT_2 
Figure FT_3
Abstract
Description
Technical Field
[0001] This application belongs to the field of spatial depth perception technology, specifically relating to a spatial depth perception and action coupling training method and system based on mixed reality. Background Technology
[0002] Spatial depth perception is a fundamental ability for athletes to judge the distance, speed, orientation, and relationships of targets in three-dimensional space. For open sports like football, athletes not only need to "see" objects in space, but also need to quickly generate realistic physical actions such as pressing forward, retreating, intercepting, blocking, or maintaining distance based on the object's direction of movement, approach speed, relative distance, and threat attributes. This process requires athletes to couple spatial depth perception with physical actions.
[0003] To achieve the coupling between spatial depth perception and physical action, it is necessary to evaluate and train athletes' spatial depth perception abilities. Existing depth perception assessment and training methods largely focus on static or quasi-static depth judgment, target alignment, and position reproduction. However, in real open sports, such as spatial blocking, defensive positioning, and dynamic threat response in football, it's not simply about "reproducing the position of a target after seeing it." Athletes must respond with actual body displacement based on changes in depth and trajectory while the target is still in motion. For example, when an opponent or ball approaches rapidly, an athlete needs to decide whether to press forward; when a threatening target passes or moves away, an athlete needs to decide whether to retreat; when a target moves laterally or diagonally, an athlete needs to maintain an appropriate distance and defensive line. The key to these abilities lies in the coupling between dynamic spatial depth perception and physical action.
[0004] Existing depth perception assessment and training methods often lack the involvement of real body displacement, making it difficult to assess a subject's ability to perceive spatial depth. Even VR-based depth perception assessment and training methods, while capable of presenting dynamic targets, often only record clicks, selections, or simple collision results, lacking a mixed reality closed loop that combines dynamic targets, response areas, body displacement, and assessment metrics. This makes it difficult to form stable, repeatable, and exportable perception-action coupled assessment or training data. Summary of the Invention
[0005] This application aims to provide a spatial depth perception and action coupling evaluation and training method and system based on mixed reality. It seeks to address the problems in existing technologies where the evaluation and training process struggles to accurately determine the subject's action response, lacks automatically quantifiable action evaluation indicators, and suffers from a mixed reality closed loop, resulting in difficulties in forming stable, repeatable, and exportable perception-action coupling evaluation or training data.
[0006] According to a first aspect of this application, this application provides a spatial depth perception and action coupling training method based on mixed reality, including: Obtain the subject's initial position and orientation in real physical space; Based on the starting position and orientation, a task coordinate system for dynamic spatial depth perception tasks is established, and at least one task response area is generated in the task coordinate system to obtain a mixed reality environment. In a mixed reality environment, dynamic virtual targets with preset motion trajectories and spatial depth variations are generated; Collect body displacement data of subjects in response to dynamic virtual targets; Based on the spatiotemporal relationship between body displacement data and the task response area and / or the spatiotemporal relationship with dynamic virtual targets, the subject's action response results are generated; Based on one or more assessment indicators from a multidimensional assessment framework and action response results, assessment results or training feedback on the subject's spatial depth perception and action coupling ability are generated.
[0007] Preferably, in the above method, a task coordinate system for dynamic spatial depth perception tasks is established based on the starting position and orientation, and at least one task response region is generated in the task coordinate system to obtain a mixed reality environment, including: Lock the starting position and orientation; The starting position is used as the origin of the coordinate system, and the direction of the target threat is taken as the direction of the source of the target or the dynamic virtual target. Determine the target protection direction and lateral direction based on the target threat direction; Establish a mission coordinate system based on the origin and the direction of the target threat; In the mission coordinate system, at least one mission response region is generated based on the dynamic virtual target and one or more of the target threat direction, target protection direction, and lateral direction, and the boundary range of the mission response region is determined.
[0008] Preferably, in the above method, generating a dynamic virtual target with a preset motion trajectory and spatial depth changes in a mixed reality environment includes: Select the task type for dynamic spatial depth perception, and generate dynamic virtual targets in the mixed reality environment according to the task type and task response area; Determine the preset motion range and task difficulty corresponding to the task type, and randomly generate the position and motion parameters of the dynamic virtual target based on the preset motion range and task difficulty; The dynamic virtual target is controlled to move in the mixed reality environment according to the position and motion parameters in order to obtain the preset motion trajectory and spatial depth changes.
[0009] Preferably, in the above method, the task type of the dynamic spatial depth perception task includes one or more of the following: forward-pushing task, backward-pushing task, and distance-maintaining task.
[0010] Preferably, in the above method, the subject's action response results are generated based on the spatiotemporal relationship between body displacement data and the task response area and / or with the spatiotemporal relationship with the dynamic virtual target, including: From the moment the dynamic virtual target appears, the body displacement data of the subjects is continuously collected; Based on the task type, the action initiation time is determined according to the relationship between body displacement data and preset displacement thresholds or preset speed thresholds; The action response result is determined based on the positional relationship between body displacement data and the target task response area, as well as the dwell time. And / or, According to the task type, based on the body displacement data and the position of the dynamic virtual target, the distance error and position error between the subject and the dynamic virtual target are detected, and the sampling rate that meets the standard is recorded. Based on distance error, position error, and the qualified sampling ratio, the action response result is generated.
[0011] Preferably, in the above method, based on one or more assessment indicators from a multidimensional assessment index and the action response result, an assessment result or training feedback on the subject's spatial depth perception and action coupling ability is generated, including: Each time a subject completes a task trial, the trial data for that task trial is recorded. The trial data includes measured data of multidimensional assessment indicators and action response results. Select the corresponding scoring strategy based on the type of task the subject enters; According to the scoring strategy, the corresponding evaluation indicators and action response results are selected from the trial data; The ability score for each task trial is calculated by weighting the measured data of the evaluation indicators and the action response results.
[0012] Preferably, in the above method, the ability score for each task trial is calculated by weighting the measured index data of the evaluation index and the action response results, including: For forward-looking or backward-looking tasks, a capability score is generated using the action response result, action start time, action completion time and regional error, according to the corresponding scoring strategy. For distance-keeping tasks, a capability score is generated using distance error, position error, and the percentage of time taken to achieve the target, based on the corresponding scoring strategy.
[0013] Preferably, in the above method, based on one or more assessment indicators from a multidimensional assessment index and the action response result, an assessment result or training feedback on the subject's spatial depth perception and action coupling ability is generated, including: Based on the assessment and training mode entered by the subject, an assessment result or training feedback on the spatial depth perception and action coupling ability is generated; the assessment and training mode includes an assessment mode and a training mode. In the assessment mode, task trials are generated in a fixed or balanced task type order to obtain stable baseline data; the stable baseline data and body displacement data are used to assess the subject's baseline task performance level. In training mode, the evaluation metrics, action response results, and ability scores of the previous task trial or multiple recent task trials are obtained; based on the evaluation metrics, action response results, and ability scores, the mixed reality environment parameters in training mode are dynamically adjusted.
[0014] Preferably, in the above method, the multidimensional evaluation indicators include: Action start time, action completion time, total reaction time, spatial error, distance error, defensive position error, percentage of time to achieve target, movement distance, and average movement speed.
[0015] According to a second aspect of this application, this application also provides a mixed reality-based spatial depth perception and action coupling training system for use with the spatial depth perception and action coupling training method provided by any of the above technical solutions. The mixed reality-based spatial depth perception and action coupling training system includes: The mixed reality display module is used to overlay and display virtual targets, task areas, prompts and feedback information in real physical space, and to obtain the subject's starting position and orientation in real physical space; The task coordinate system construction module is used to establish a task coordinate system for dynamic spatial depth perception tasks based on the starting position and orientation. The response region generation module is used to generate at least one task response region in the task coordinate system. The dynamic target generation module is used to generate dynamic virtual targets with preset motion trajectories and spatial depth changes according to the task type of the dynamic spatial depth perception task. The body displacement acquisition module is used to collect body displacement data of the subject in response to a dynamic virtual target; The motion response generation module is used to generate the subject's motion response results based on the spatiotemporal relationship between body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target. The feedback and training module is used to generate assessment results or training feedback on the subject's spatial depth perception and action coupling ability based on one or more assessment indicators from a multidimensional assessment index and action response results.
[0016] The technical solution of this application has at least the following technical effects: The spatial depth perception and action coupling evaluation and training method and system provided in this application, based on mixed reality, establishes a task coordinate system for a dynamic spatial depth perception task based on the subject's starting position and orientation in real physical space, and generates at least one task response region in this task coordinate system, thus obtaining a task coordinate system and response region construction mechanism; in addition, it generates a dynamic virtual target with a preset motion trajectory and spatial depth changes, thus establishing a dynamic virtual target generation mechanism; based on the spatiotemporal relationship between the body displacement data and the task response region and / or the spatiotemporal relationship with the dynamic virtual target, it generates the subject's action response result, thus obtaining an action response judgment mechanism; finally, it constructs a multi-index quantification mechanism, in which multi-dimensional evaluation indicators are calculated based on the dynamic virtual target trajectory and the subject's body displacement data, generating evaluation results or training feedback for evaluating the subject's spatial depth perception and action coupling ability. The above approach combines dynamic virtual targets, task response areas, body displacement data, and multidimensional evaluation indicators to form a mixed reality closed loop. This extends depth perception training from "observation-judgment-reproduction" to "dynamic spatial perception-real body movement response," enabling direct assessment and training of athletes' spatial depth perception-action coupling ability in real space. This results in stable, repeatable, and exportable spatial depth perception-action coupling assessment or training data. Attached Figure Description
[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a mixed reality-based spatial depth perception and action coupling training method provided in this application embodiment; Figure 2 for Figure 1 The illustrated embodiment provides a flowchart of a method for establishing a task coordinate system and a task response region; Figure 3 for Figure 1 The illustrated embodiment provides a flowchart of a method for generating dynamic virtual targets; Figure 4 for Figure 1 The illustrated embodiment provides a flowchart of a method for generating action response results; Figure 5 for Figure 1The illustrated embodiment provides a flowchart of the first method for generating evaluation results or training feedback of a subject's spatial depth perception and action coupling ability. Figure 6 for Figure 1 The illustrated embodiment provides a flowchart of a second method for generating evaluation results or training feedback on a subject's spatial depth perception and action coupling ability. Figure 7 for Figure 1 The illustrated embodiment provides a schematic diagram of the structure of a mixed reality-based spatial depth perception and action coupling training system; Figure 8-1 A schematic diagram of the calibration state of a task coordinate system provided in an embodiment of this application; Figure 8-2 A schematic diagram of the calibration state of a dynamic virtual target provided in an embodiment of this application. Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0018] To more clearly illustrate the overall concept of this application, a detailed explanation is provided below with reference to the accompanying drawings.
[0019] Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below. It should be noted that, unless otherwise specified, the embodiments of this application and the features thereof can be combined with each other.
[0020] In this application, unless otherwise expressly specified and limited, the terms "above" and "below" the second feature can refer to direct contact between the first and second features, or indirect contact between the first and second features through an intermediate medium. In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples.
[0021] Existing depth perception evaluation and training methods typically suffer from the following problems: (1) Traditional depth perception instruments and two-dimensional screen training tools usually lack real body displacement, making it difficult to assess the subject’s ability to make forward, backward, blocking or distance-maintaining actions based on changes in spatial depth.
[0022] (2) Although ordinary VR training can present dynamic targets, it often only records the results of clicks, selections or simple collisions. It cannot accurately determine the subject's action response based on the task response area such as the starting point, direction, area or target distance in the real physical space.
[0023] (3) Existing sports training assessments rely heavily on manual observation and subjective scoring, making it difficult to automatically quantify assessment indicators such as action start time, action completion time, area entry, area stay, distance error, defensive position error, and the percentage of time to reach the target.
[0024] (4) Existing methods lack a mixed reality closed loop that combines dynamic virtual targets, task response areas, body displacement and evaluation indicators, making it difficult to form stable, repeatable and deriveable evaluation or training data for spatial depth perception-action coupling.
[0025] To address the aforementioned technical problems, this application proposes a mixed reality-based spatial depth perception and action coupling evaluation and training method and system. This scheme establishes a task coordinate system based on the subject's initial position and orientation in real space, generating a task response area (e.g., for football, generating the starting zone, forward pressing zone, retreat zone, defensive direction, and / or boundary range, etc.). Dynamic virtual targets with different movement trajectories and spatial depth variations are generated within this task coordinate system. Real body displacement data generated by the subject in response to the dynamic virtual targets is collected. Action response results are judged based on area entry, area stay, distance maintenance, spatial error, and time threshold. Multidimensional evaluation indicators of the action response results are calculated and output, providing evaluation results or training feedback.
[0026] To achieve the above technical objectives, see [link to relevant documentation]. Figure 1 . Figure 1 This is a flowchart illustrating a mixed reality-based spatial depth perception and action coupling training method provided in an embodiment of this application. Figure 1 As shown, this mixed reality-based spatial depth perception and action coupling training method includes: S110: Obtain the subject's starting position and orientation in real physical space.
[0027] First, virtual targets, task areas, prompts, and feedback are overlaid and displayed in the real physical space to create a mixed reality environment and construct a mixed reality task. This can be achieved using devices such as head-mounted displays or holographic glasses. After entering the mixed reality task, the subject is prompted to stand at the starting point and face the direction of the incoming ball, the direction of attack, or other task reference directions to determine the subject's "orientation." The subject locks in their current starting position and orientation through input signals such as "confirmation input."
[0028] S120: Based on the starting position and orientation, establish a task coordinate system for dynamic spatial depth perception tasks, and generate at least one task response area in the task coordinate system to obtain a mixed reality environment.
[0029] A task coordinate system refers to a local spatial coordinate system established based on the subject's starting position, facing direction, incoming ball direction, or target direction. This application's embodiments construct a task coordinate system and response area construction mechanism based on the subject's starting position and orientation. By establishing a task coordinate system based on the subject's starting position and orientation, and generating a task response area and dynamic target trajectory within this coordinate system, the assessment or training tasks under different subjects, different venues, and different training difficulties can be made repeatable and quantifiable.
[0030] Combination Figure 8-1 As shown in the schematic diagram of the calibration status of the task coordinate system, the specific details are as follows: Figure 2 As shown, in a preferred embodiment, step S120 above includes: establishing a task coordinate system for dynamic spatial depth perception tasks based on the starting position and orientation, and generating at least one task response region in the task coordinate system to obtain a mixed reality environment, including: S121: Lock the starting position and orientation.
[0031] This application's embodiments allow the system to interact with the subject's commands to lock the starting position and orientation. Specifically, as... Figure 8-1 As shown, after switching to the mixed reality task, the system prompts the subject to stand at the starting point and face the direction of the incoming ball, the direction of attack, or other task reference directions. The subject locks their current starting position and orientation by "confirming input".
[0032] S122: The origin of the coordinate system is the starting position, and the direction of the target threat is the direction of the direction towards or from the source of the dynamic virtual target. See also Figure 8-1 The arrows shown indicate the direction.
[0033] S123: Determine the target protection direction and lateral direction based on the target threat direction.
[0034] Taking soccer as an example, the starting position of the subject is taken as the origin of the task coordinate system, and the direction the subject is facing or the direction of the incoming ball is taken as the target threat direction. From this, the target protection direction (e.g., the direction of the goal) and the lateral direction are calculated. Through these directions, the athlete's depth perception space can be determined, and a mixed reality environment that fits the real sports scene can be established.
[0035] S124: Establish the mission coordinate system based on the origin and the direction of the target threat.
[0036] like Figure 8-1 As shown, the task coordinate system is a local spatial coordinate system established based on the subject's starting position, facing direction, incoming ball direction, or target direction. In this embodiment, the task coordinate system is established based on the coordinate origin and the target threat direction (usually the subject's orientation), thereby accurately locating the subject's position and the coordinate trajectory of the dynamic virtual target, thus enabling the assessment or testing of the subject's spatial depth perception ability.
[0037] S125: In the mission coordinate system, generate at least one mission response region based on one or more of the dynamic virtual target and the target threat direction, the target protection direction, and the lateral direction, and determine the boundary range of the mission response region.
[0038] Within this task coordinate system, the following task response region or object is specifically generated: Starting zone: This is used to require the subject to return to a fixed position and remain stable before the start of each trial.
[0039] Forward pressure zone: Located on the side facing the threat, used to determine whether the subject has completed a forward pressing or grabbing action.
[0040] Retreat zone: Located on one side of the target protection direction, used to determine whether the subject has completed the retreat or protective space action.
[0041] Target direction or defensive target: used to establish subjects, dynamic virtual targets (e.g.) Figure 8-2 The virtual soccer ball that is constantly approaching (as shown) and the protected target (e.g.) Figure 8-2 The spatial relationship between virtual goals in the mixed reality environment shown.
[0042] Boundary range: Used to define the actual physical activity area during task execution.
[0043] The size, location, and threshold of the aforementioned areas can be configured based on the size of the venue, the level of training, the ability of the subjects, or the task objectives.
[0044] The technical solution provided in this application establishes a local task coordinate system based on the subject's starting position and facing direction in real space, and generates task response areas such as the starting area, forward pressure area, backward withdrawal area, target direction, and boundary range, which can construct a training / evaluation task space based on the tracking results.
[0045] Figure 1 The technical solution provided in the illustrated embodiment, after step S120: establishing a task coordinate system for dynamic spatial depth perception tasks based on the starting position and orientation, and generating at least one task response region in the task coordinate system to obtain the mixed reality environment, further includes: S130: In a mixed reality environment, generate dynamic virtual targets with preset motion trajectories and spatial depth variations.
[0046] Combination Figure 8-2 As shown in the schematic diagram of the calibration state of the dynamic virtual target, the task type of the spatial depth perception task can be randomly selected or selected according to preset rules in each trial, and a dynamic virtual target can be generated according to the task type. Here, the dynamic virtual target can be represented as a sphere (e.g., Figure 8-2 The virtual objects include a red ball, a capsule, a character model, an arrow, a cursor, or other virtual objects. As the distance between the dynamic virtual target and the subject changes, the size of the target changes in the mixed reality environment, thus simulating changes in spatial depth. Furthermore, the dynamic virtual target can simulate real-world motion scenes and move along a preset trajectory, such as simulating the arc of a soccer ball.
[0047] The technical solution provided in this application can establish a task coordinate system based on the subject's starting position and orientation, and generate the task response area and the motion trajectory and spatial depth change of the dynamic virtual target in the task coordinate system, which can make the tasks under different subjects, different venues and different training difficulties repeatable and quantifiable.
[0048] The dynamic virtual target is generated based on the task type of the dynamic spatial depth perception task. In the technical solution provided in this application embodiment, the task type of the dynamic spatial depth perception task includes one or more of the following: forward pressure task, backward retreat task, and distance maintenance task.
[0049] Specifically, such as Figure 3 As shown, in a preferred embodiment, the method for generating dynamic virtual targets is as follows: In step S130 above: In a mixed reality environment, generating dynamic virtual targets with preset motion trajectories and spatial depth variations includes: S131: Select the task type for dynamic spatial depth perception task, and generate dynamic virtual targets in the mixed reality environment according to the task type and task response area.
[0050] In the technical solution provided in this application embodiment, the dynamic virtual target is generated according to the task type of the dynamic spatial depth perception task and has predetermined trajectory parameters and spatial depth changes.
[0051] In one implementation, the task types for dynamic spatial depth perception tasks include forward-pushing tasks, retreating tasks, and distance-maintaining tasks. The generation of dynamic virtual targets corresponding to these task types is as follows: Forward pressure type tasks: A dynamic target appears in front of or diagonally in front of the subject and moves toward a pre-set forward pressure area or threat area, requiring the subject to move forward in time and enter the forward pressure area.
[0052] Retreat-type tasks: A dynamic target appears from the front or side front and points towards a retreat / protection space situation, requiring the subject to enter the retreat zone in a timely manner.
[0053] Distance-keeping tasks: A dynamic virtual target moves laterally, diagonally, or irregularly within the task area, requiring the subject to maintain a preset distance from the target and stay as close as possible to the defensive line or ideal defensive position.
[0054] S132: Determine the preset motion range and task difficulty corresponding to the task type, and randomly generate the position and motion parameters of the dynamic virtual target based on the preset motion range and task difficulty.
[0055] Once the task type is determined, the preset motion range corresponding to the task type can be determined. According to the preset motion range (including but not limited to preset distance range, angle range, height range and / or speed range) and task difficulty, the position and motion parameters such as the starting point, target point, motion direction and speed of the dynamic virtual target can be calculated.
[0056] S133: Control the dynamic virtual target to move in the mixed reality environment according to the position and motion parameters to obtain the preset motion trajectory and spatial depth changes.
[0057] For example, for distance-keeping tasks, dynamic virtual targets can employ irregular movements (e.g., turning) and generate continuous trajectories within the task area based on boundaries, turning intervals, speed ranges, and the subject's position. Embodiments of this application can also adjust the target speed, target generation distance, response area size, target distance, duration, or task type ratio of the dynamic virtual target according to positional motion parameters, thereby adjusting the motion trajectory and spatial depth changes.
[0058] According to the task type, target direction, preset movement range (e.g., distance range, angle range, speed range) and task difficulty, the embodiments of this application generate dynamic virtual targets with preset or irregular trajectories in the task coordinate system, which can induce subjects to press forward, retreat, or maintain distance.
[0059] Figure 1 The technical solution provided in the illustrated embodiment, after step S130: generating a dynamic virtual target with a preset motion trajectory and spatial depth changes in a mixed reality environment, further includes: S140: Collect body displacement data generated by the subject's response to the dynamic virtual target.
[0060] The subject's body displacement data includes, but is not limited to, forward pressing, backward retreating, and distance-maintaining behaviors. The technical solution provided in this application, after collecting and setting body displacement data in response to the aforementioned dynamic virtual target, can automatically determine whether the subject has entered the target area, whether they remain there continuously, whether they maintain the target distance, and whether they are near an ideal defensive position, thereby reducing errors caused by manual observation and subjective scoring.
[0061] S150: Generate the subject's action response results based on the spatiotemporal relationship between body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target.
[0062] Specifically, based on the spatiotemporal relationship between the subject's body displacement data and the task response area and / or dynamic virtual target, the system can automatically determine whether the subject's action meets the standard. This determination result is the subject's action response result. The spatiotemporal relationship between the body displacement data and the dynamic virtual target includes, but is not limited to, the relationship between the distance to the target, the time spent in the area, the action initiation threshold, and the timeout threshold, thereby automatically determining whether the subject's action meets the standard.
[0063] Through the above methods, the technical solution of this application can automatically determine whether the subject has entered the target area, whether the subject has stayed there for a long time, whether the subject has maintained the target distance, and whether the subject is near the ideal defensive position, thereby constructing an action response judgment mechanism to reduce errors from manual observation and subjective scoring.
[0064] Specifically, such as Figure 4 As shown, in a preferred embodiment, in the above method, S150: based on the spatiotemporal relationship between body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target, the subject's action response result is generated, including: S151: From the moment the dynamic virtual target appears, continuously collect the subject's body displacement data. The collected body displacement data includes parameters such as the subject's horizontal displacement relative to the starting point and the subject's average moving speed.
[0065] S152: Determine the start time of the action based on the relationship between body displacement data and preset displacement threshold or preset speed threshold, according to the task type.
[0066] S153: Determine the action response result based on the positional relationship between body displacement data and the target task response area, as well as the dwell time. The action response result includes the judgment result of whether the action meets the standard. For example, if the subject stays in the target task response area for a continuous time that reaches a preset time threshold, the action is judged to have met the standard. If the subject exceeds the time limit, fails to enter the target task response area, enters the wrong area, or crosses the boundary, it is recorded as failing the standard or an abnormal trial.
[0067] And / or, S154: Based on body displacement data and the position of a dynamic virtual target, and according to the task type, detect the distance error and position error between the subject and the dynamic virtual target, and record the pass rate. Here, distance error includes the distance error between the subject and the dynamic virtual target, and position error includes the defensive position error between the subject's position and the ideal defensive position.
[0068] S155: Generate action response results based on distance error, position error, and compliance sampling ratio.
[0069] The technical solution provided in this application continuously collects the subject's body displacement data after the appearance of a dynamic virtual target. Different action response results are generated for different task types; specifically, for forward-pushing and backward-pushing tasks, the system first detects whether the subject has initiated a valid action, determined by horizontal displacement and average movement speed. Specifically, when the subject's horizontal displacement relative to the starting point exceeds a preset displacement threshold, or the average movement speed exceeds a preset speed threshold, that moment is recorded as the action initiation moment.
[0070] Subsequently, the success of the action is determined based on whether the subject's position has entered the target task response area. To avoid misjudgment due to accidental crossing of the area, the subject can be required to remain continuously within the target task response area for a preset time threshold before the action is considered complete. If the subject exceeds the time limit, fails to enter the target task response area, enters the wrong area, or crosses the boundary, it is recorded as a failure or an abnormal attempt.
[0071] For distance-maintaining tasks, the positions of the subject and the dynamic virtual target are recorded at a preset sampling frequency throughout the task duration, and the current distance, distance error, ideal defensive position, and defensive position error are calculated. Based on the current distance and distance error, if the distance error between the subject and the dynamic virtual target is determined to be within the target range, and the subject's position is determined to be near the defensive line or ideal defensive area based on the ideal defensive position and defensive position error, the sampling point is recorded as having met the standard. After the trial ends, the success rate of the distance-maintaining task is determined based on the percentage of successful samples, the average distance error, and the average defensive position error.
[0072] Figure 1The technical solution provided in the illustrated embodiment, after step S150: generating the subject's action response result based on the spatiotemporal relationship between body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target, further includes: S160: Based on one or more assessment indicators from a multidimensional assessment framework and action response results, generate assessment results or training feedback on the subject's spatial depth perception and action coupling ability.
[0073] In this embodiment, the multidimensional evaluation indicators include action initiation time, action completion time, total reaction time, spatial error, distance error, defensive position error, percentage of time to achieve target, movement distance, and average movement speed. When evaluating action response results and generating evaluation results or training feedback, one or more of the above multidimensional evaluation indicators can be selected for evaluation.
[0074] The technical solution provided in this application calculates multi-dimensional evaluation indicators such as action initiation time, action completion time, total reaction time, area error, distance error, defensive position error, percentage of time to achieve target, movement distance, and average movement speed based on the trajectory parameters of a dynamic virtual target and the subject's body displacement data, and generates evaluation or training results. This enables a multi-indicator quantification mechanism, through which the evaluation or training feedback of the subject's depth perception and action coupling ability can be achieved.
[0075] Specifically, such as Figure 5 As shown, in a preferred embodiment, step S160 above: based on one or more evaluation indicators from the multidimensional evaluation indicators and the action response results, generating evaluation results or training feedback on the subject's spatial depth perception and action coupling ability, including: S161: When the subject completes each task trial, the trial data of the task trial is recorded. The trial data includes the measured index data of the multidimensional assessment indicators and the action response results. For each task trial completed by the subject, the following trial data were recorded: Task type; Dynamic target starting position, target position, velocity, and trajectory parameters; Task coordinate system name, target direction, subject's starting position; The moment when the dynamic target appears; Whether the timeout has occurred, whether the boundary has been crossed, or whether the target area has been entered; Duration of stay in the target area; Action initiation time, action completion time, total reaction time; Final location of the subject; Regional distance error or target distance error; Retreat distance, total movement distance, average movement speed; Maintain the average distance error, maximum distance error, standard deviation of error, and percentage of time spent within the target distance range in the distance task; Error in ideal defensive positioning; percentage of time spent within defensive lines; Trial score, session mode, trial number, and timestamp.
[0076] The above data refers to the measured index data and action response results of the multidimensional evaluation indicators.
[0077] S162: Select the corresponding scoring strategy based on the type of task the subject enters; S163: According to the scoring strategy, select the corresponding evaluation indicators and action response results from the trial data; S164: Using measured index data and action response results of the evaluation indicators, a weighted score is calculated for each task trial.
[0078] As a preferred embodiment, step S164: using the measured index data of the evaluation index and the action response results, a weighted calculation of the capability score for the task trial is performed. Specifically, this includes: for forward-pushing or backward-pushing tasks, a capability score is generated based on the corresponding scoring strategy, using the action response results, action start time, action completion time, and regional error; for distance-maintaining tasks, a capability score is generated based on the corresponding scoring strategy, using distance error, position error, and the percentage of time to reach the target.
[0079] The technical solution provided in this application allows for the selection of different scoring strategies based on the task type. Following these strategies, corresponding evaluation indicators and action response results are selected from trial data to calculate a weighted capability score for each trial. For example, for forward-pressing and retreating tasks, the capability score can be generated based on the correctness of the action response (e.g., whether the action met the standard, whether an attempt was made in the forward-pressing or retreating task), action initiation time, action completion time, and area error. Furthermore, for distance-maintaining tasks, a score can be generated based on average distance error, defensive position error, and the percentage of time taken to meet the standard. The score calculation can employ a weighted approach, using a large amount of actual evaluation data to set and calibrate scoring weights and thresholds.
[0080] Other examples Figure 6 As shown, in a preferred embodiment, step S160 above: based on one or more evaluation indicators from the multidimensional evaluation indicators and the action response results, generating evaluation results or training feedback on the subject's spatial depth perception and action coupling ability, including: S165: Based on the assessment and training mode entered by the subject, generate assessment results or training feedback on spatial depth perception and action coupling ability; wherein, the assessment and training mode includes assessment mode and training mode.
[0081] S166: In the assessment mode, task trials are generated in a fixed or balanced task type order to obtain stable baseline data; based on the stable baseline data and body displacement data, the baseline task performance level of the subjects is assessed.
[0082] S167: In training mode, obtain the evaluation metrics, action response results, and ability scores of the previous task trial or multiple recent task trials; dynamically adjust the mixed reality environment parameters in training mode based on the evaluation metrics, action response results, and ability scores. These mixed reality environment parameters include, but are not limited to, dynamic target velocity, target generation distance, response area size, target distance, duration, and task type ratio.
[0083] The evaluation and training modes provided in this application include an evaluation mode and a training mode. In the evaluation mode, trials are generated in a fixed or balanced order of task types to obtain stable baseline data. The stable baseline data can include various evaluation index data obtained in this test. Using these evaluation index data, the athlete's baseline task performance level can be accurately determined and evaluated, facilitating subsequent analysis of the athlete's spatial depth perception and behavioral coupling ability. In the training mode, mixed reality environment parameters such as dynamic target speed, target generation distance, response area size, target distance, duration, or task type ratio can be adjusted based on the action initiation time, spatial error, achievement time ratio, and score of the previous trial or multiple recent trials.
[0084] In summary, the mixed reality-based spatial depth perception and action coupling training method provided in this application establishes a task coordinate system for a dynamic spatial depth perception task based on the subject's starting position and orientation in real physical space, and generates at least one task response region within this task coordinate system, thus obtaining a task coordinate system and response region construction mechanism; in addition, it generates a dynamic virtual target with a preset motion trajectory and spatial depth changes, thus establishing a dynamic virtual target generation mechanism; based on the spatiotemporal relationship between the body displacement data and the task response region and / or the dynamic virtual target, it generates the subject's action response result, thus obtaining an action response judgment mechanism; finally, it constructs a multi-index quantification mechanism, in which multi-dimensional evaluation indicators are calculated based on the dynamic virtual target trajectory and the subject's body displacement data, generating evaluation results or training feedback for evaluating the subject's spatial depth perception and action coupling capabilities. The above approach combines dynamic virtual targets, task response areas, body displacement data, and multidimensional evaluation indicators to form a mixed reality closed loop. This extends depth perception training from "observation-judgment-reproduction" to "dynamic spatial perception-real body movement response," enabling direct assessment and training of athletes' spatial depth perception-action coupling ability in real space. This results in stable, repeatable, and exportable spatial depth perception-action coupling assessment or training data.
[0085] In addition, the following embodiments of this application provide product embodiments, which have the same beneficial effects as the mixed reality-based spatial depth perception and action coupling training method provided in the above embodiments, and other technical features in the product embodiments are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.
[0086] See Figure 7 , Figure 7 This application provides a schematic diagram of a mixed reality-based spatial depth perception and action coupling training system. The system is used in any of the above embodiments of the spatial depth perception and action coupling training method. The mixed reality-based spatial depth perception and action coupling training system includes: The mixed reality display module 110 is used to overlay and display virtual targets, task areas, prompts and feedback information in real physical space, and to obtain the subject's starting position and orientation in real physical space; The task coordinate system construction module 120 is used to establish a task coordinate system for dynamic spatial depth perception tasks based on the starting position and orientation. The response region generation module 130 is used to generate at least one task response region in the task coordinate system. The dynamic target generation module 140 is used to generate dynamic virtual targets with preset motion trajectories and spatial depth changes according to the task type of the dynamic spatial depth perception task. The body displacement acquisition module 150 is used to acquire body displacement data of the subject in response to a dynamic virtual target. The motion response generation module 160 is used to generate the subject's motion response results based on the spatiotemporal relationship between body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target. The feedback and training module 170 is used to generate assessment results or training feedback on the subject's spatial depth perception and action coupling ability based on one or more assessment indicators from a multidimensional assessment index and action response results.
[0087] In summary, the spatial depth perception and action coupling training scheme based on mixed reality provided in the above embodiments of this application has at least the following technical effects: (1) This application extends the depth perception training from “observation-judgment-reproduction” to “dynamic spatial perception-real body action response”, which can more directly assess the athlete’s perception-action coupling ability in real space.
[0088] (2) This application uses mixed reality to overlay dynamic virtual targets onto real physical space, requiring subjects to complete forward pressing, backward retreating or distance maintenance tasks with real body displacement, thereby improving the ecological validity of training tasks.
[0089] (3) This application establishes a task coordinate system based on the subject’s starting position and orientation, and generates a response area and dynamic target trajectory in it, so that the task under different subjects, different venues and different training difficulties is repeatable and quantifiable.
[0090] (4) This application can automatically determine whether the subject has entered the target area, whether the subject has stayed there, whether the subject has maintained the target distance, and whether the subject is near the ideal defensive position, thereby reducing errors in manual observation and subjective scoring.
[0091] (5) This application can simultaneously record the start time of the action, the completion time of the action, the total reaction time, the area error, the distance error, the defensive position error, the percentage of time to reach the target, the moving distance and the average moving speed, providing fine-grained data for scientific research analysis and individualized training.
[0092] (6) This application can be extended to football defense, basketball defense, ice hockey defense, driving obstacle avoidance, rehabilitation training, spatial cognitive assessment and other scenarios that require dynamic spatial response capabilities.
[0093] See last. Figure 9 , Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 As shown, the electronic device includes: At least one processing device 1001; and a storage device 1003 communicatively connected to the at least one processing device 1001; wherein the storage device 1003 stores instructions executable by the at least one processing device, the instructions being executed by the at least one processing device 1001 to enable the at least one processing device 1001 to execute the mixed reality-based spatial depth perception and action coupling training method of any of the above embodiments. Reference is made below. Figure 9 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of this application. The electronic devices in these embodiments can include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 9 The device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application. This electronic device can include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only storage device ROM 1002 or a program loaded from storage device 1003 into a random access storage device RAM 1004. The RAM 1004 also stores various programs and data required for the operation of the aforementioned electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 is capable of operating the aforementioned electronic equipment to exchange data wirelessly or wiredly with other devices. Although the figures show a model device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems can be implemented alternatively.
[0094] The modules described in the embodiments of this application can be implemented in software or hardware. The module names, in some cases, do not constitute a limitation on the unit itself.
[0095] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
[0096] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A training method for spatial depth perception and action coupling based on mixed reality, characterized in that, include: Obtain the subject's initial position and orientation in real physical space; Based on the starting position and orientation, a task coordinate system for dynamic spatial depth perception tasks is established, and at least one task response area is generated in the task coordinate system to obtain a mixed reality environment. In the mixed reality environment, dynamic virtual targets with preset motion trajectories and spatial depth variations are generated; Collect the body displacement data of the subject in response to the dynamic virtual target; Based on the spatiotemporal relationship between the body displacement data and the task response area and / or the dynamic virtual target, the subject's action response results are generated; Based on one or more of the multidimensional evaluation indicators and the action response results, an evaluation result or training feedback on the subject's spatial depth perception and action coupling ability is generated.
2. The method as described in claim 1, characterized in that, Based on the starting position and orientation, a task coordinate system for dynamic spatial depth perception tasks is established, and at least one task response region is generated in the task coordinate system to obtain a mixed reality environment, including: Lock the starting position and orientation; The starting position is taken as the origin of the coordinate system, and the orientation or the source direction of the dynamic virtual target is taken as the target threat direction. Determine the target protection direction and lateral direction based on the target threat direction; The task coordinate system is established based on the origin of the coordinate system and the direction of the target threat. In the task coordinate system, at least one task response region is generated based on the dynamic virtual target and one or more of the target threat direction, target protection direction, and lateral direction, and the boundary range of the task response region is determined.
3. The method as described in claim 1, characterized in that, The process of generating a dynamic virtual target with a preset motion trajectory and spatial depth changes in the mixed reality environment includes: Select the task type of the dynamic spatial depth perception task, and generate a dynamic virtual target in the mixed reality environment according to the task type and the task response area; Determine the preset motion range and task difficulty corresponding to the task type, and randomly generate the position and motion parameters of the dynamic virtual target based on the preset motion range and task difficulty; The dynamic virtual target is controlled to move in the mixed reality environment according to the position and motion parameters to obtain the preset motion trajectory and spatial depth changes.
4. The method as described in claim 1, characterized in that, The task types of the dynamic spatial depth perception task include one or more of the following: forward-pushing task, backward-pushing task, and distance-maintaining task.
5. The method as described in claim 4, characterized in that, The generation of the subject's action response result based on the spatiotemporal relationship between the body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target includes: From the moment the dynamic virtual target appears, the subject's body displacement data is continuously collected; According to the task type, the action initiation time is determined based on the relationship between the body displacement data and a preset displacement threshold or a preset speed threshold; The action response result is determined based on the positional relationship between the body displacement data and the target task response area, as well as the time spent in the area. And / or, According to the task type, based on the body displacement data and the position of the dynamic virtual target, the distance error and position error between the subject and the dynamic virtual target are detected, and the sampling rate that meets the standard is recorded. The action response result is generated based on the distance error, position error, and the qualified sampling ratio.
6. The method as described in claim 1 or 4, characterized in that, The process of generating assessment results or training feedback on the subject's spatial depth perception and action coupling ability based on one or more of the multidimensional assessment indicators and the action response results includes: Each time a subject completes a task trial, the trial data for that task trial is recorded, wherein the trial data includes the measured index data of the multidimensional evaluation index and the action response results; Select the corresponding scoring strategy based on the type of task the subject enters; According to the scoring strategy, the corresponding evaluation indicators and action response results are selected from the trial data; The ability score for each task trial is calculated by weighting the measured data of the evaluation indicators and the action response results.
7. The method as described in claim 6, characterized in that, The ability score for each task trial is calculated by weighting the measured index data and the action response results using the evaluation indicators, including: For forward-looking or backward-looking tasks, the capability score is generated using the action response result, action start time, action completion time and regional error, according to the corresponding scoring strategy. For distance-keeping tasks, the ability score is generated using distance error, position error, and the percentage of time taken to achieve the target, according to the corresponding scoring strategy.
8. The method as described in claim 1, characterized in that, The process of generating assessment results or training feedback on the subject's spatial depth perception and action coupling ability based on one or more of the multidimensional assessment indicators and the action response results includes: Based on the evaluation and training mode entered by the subject, an assessment result or training feedback on the spatial depth perception and action coupling ability is generated; wherein, the evaluation and training mode includes an assessment mode and a training mode. In the assessment mode, task trials are generated in a fixed or balanced task type order to obtain stable baseline data; the stable baseline data and body displacement data are used to assess the subject's baseline task performance level. In the training mode, the evaluation indicators, action response results, and ability scores of the previous task trial or multiple recent task trials are obtained; based on the evaluation indicators, action response results, and ability scores, the mixed reality environment parameters in the training mode are dynamically adjusted.
9. The method as described in claim 1, characterized in that, The multidimensional evaluation indicators include: Action start time, action completion time, total reaction time, spatial error, distance error, defensive position error, percentage of time to achieve target, movement distance, and average movement speed.
10. A spatial depth perception and action coupling evaluation and training system based on mixed reality, characterized in that, The spatial depth perception and action coupling evaluation and training method according to any one of claims 1 to 9, wherein the mixed reality-based spatial depth perception and action coupling evaluation and training system comprises: The mixed reality display module is used to overlay and display virtual targets, task areas, prompts and feedback information in real physical space, and to obtain the subject's starting position and orientation in real physical space; The task coordinate system construction module is used to establish a task coordinate system for dynamic spatial depth perception tasks based on the starting position and orientation. The response region generation module is used to generate at least one task response region in the task coordinate system. The dynamic target generation module is used to generate dynamic virtual targets with preset motion trajectories and spatial depth changes according to the task type of the dynamic spatial depth perception task. The body displacement acquisition module is used to acquire body displacement data of the subject in response to the dynamic virtual target; The motion response generation module is used to generate the subject's motion response results based on the spatiotemporal relationship between the body displacement data and the task response area and / or the spatiotemporal relationship with the dynamic virtual target; The feedback and training module is used to generate assessment results or training feedback on the subject's spatial depth perception and action coupling ability based on one or more of the multidimensional assessment indicators and the action response results.