Multi-dimensional mixed reality evaluation and training method and system for spatial depth perception

Abstract

The application provides a multi-dimension mixed reality evaluation and training method and system for spatial depth perception, and belongs to the technical field of spatial depth perception. The method comprises the following steps: dividing multiple ability dimensions of spatial depth perception ability according to cognitive behavior states; the multiple ability dimensions comprise a peripheral visual depth capture dimension, a dynamic spatial memory reconstruction dimension, and a dynamic depth perception and action coupling dimension; a virtual reality task or a mixed reality task is configured for each ability dimension; a virtual reality task and / or a mixed reality task is loaded for a subject in a preset task order, spatial depth perception evaluation or training of multiple ability dimensions under corresponding tasks is performed, spatial depth perception performance indexes under each ability dimension in corresponding tasks are obtained, and evaluation results or training results of corresponding ability dimensions are generated according to the spatial depth perception performance indexes. The application can solve the problem that the complete use chain of spatial depth perception ability in real sports projects cannot be covered by the prior art.

Description

Technical Field

[0001] This application belongs to the field of spatial depth perception technology, specifically involving a multi-dimensional mixed reality training method and system for spatial depth perception. Background Technology

[0002] In open, dynamic, and competitive sports, athletes need to continuously assess the spatial relationships between multiple targets and respond accordingly. For example, football, as an open, dynamic, and competitive sport, requires athletes to continuously assess the three-dimensional relationships between the ball, teammates, opponents, and available space, and to perform actions such as passing, positioning, receiving, defending, blocking, and intercepting. To perform these responses and accurately assess the spatial relationships between multiple targets, a strong underlying visual ability is required; and spatial depth perception is an indispensable underlying visual ability for these actions.

[0003] Spatial depth perception refers to an individual's ability to judge the distance, relative distance, direction of movement, speed changes, and spatial hierarchy of targets in three-dimensional space. Traditional depth perception training often treats spatial depth perception as a single ability, measuring subjects' ability to judge the distance of targets through static instruments, two-dimensional screen tasks, or single VR scenes. However, spatial depth perception in real sports (such as football matches) is not a static judgment in a single state, but a complex ability that occurs continuously in multiple cognitive and behavioral states. Specifically, athletes need to face at least the following three typical states during a competition: (1) Pay attention to the load status. The athlete is dealing with the current main task, such as dribbling forward, observing the defensive pressure in front, or performing central operations, while also needing to use peripheral vision to detect the depth of teammates, opponents, or open spaces.

[0004] (2) Spatial memory state. After obtaining spatial situation information through brief scanning, the target position may be temporarily invisible due to body turning, receiving the ball, confrontation or switching of line of sight. At this time, it is necessary to rely on spatial working memory to reconstruct the depth position of the target.

[0005] (3) Action response state. When facing a ball, opponent or threatening target that is still in motion, the athlete needs to quickly perform physical actions such as pressing forward, retreating, blocking or maintaining distance according to changes in its speed, direction and depth.

[0006] Existing assessment and training systems for spatial perception (including evaluation and training) often target only one cognitive behavioral state, making it difficult to cover the complete chain of spatial depth perception in real sports events. The evaluation or training results of a single task or state may only reflect the subject's performance in static judgment, location reproduction, or simple reactions, and cannot explain their comprehensive performance when facing attentional load, spatial memory, and motor response simultaneously in real competition. Summary of the Invention

[0007] This application aims to provide a multi-dimensional mixed reality assessment and training method and system for spatial depth perception. It seeks to address the limitations of existing technologies in covering the complete application chain of spatial depth perception capabilities in real-world sports. Assessments or training results for single tasks or states may only reflect a subject's performance in static judgment, location reproduction, or simple reactions, failing to explain their comprehensive performance when simultaneously facing attentional loads, spatial memory, and motor response in real-world competitions.

[0008] To address the aforementioned issues, this application proposes a multi-dimensional mixed reality training method for spatial depth perception, comprising: Based on cognitive behavior states, spatial depth perception ability is divided into multiple capability dimensions; among them, multiple capability dimensions include the peripheral visual depth capture dimension under attentional load state, the dynamic spatial memory reconstruction dimension under spatial memory state, and the dynamic depth perception and action coupling dimension under action response state. Configure virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions; Virtual reality tasks and / or mixed reality tasks are loaded onto the subjects according to the preset task sequence, and spatial depth perception assessments or training are performed on multiple ability dimensions under the corresponding tasks. Obtain the spatial depth perception performance indicators for each capability dimension in the corresponding task. Based on spatial depth perception performance metrics, generate evaluation results or training results for the corresponding capability dimensions.

[0009] Preferably, in the above-mentioned multi-dimensional mixed reality assessment and training method, virtual reality tasks or mixed reality tasks are configured for each of the multiple capability dimensions, including: To capture the peripheral visual depth dimension, a central dynamic task is presented in a virtual reality environment and the subject's performance on the central task is recorded. At the same time, spatial stimuli with spatial depth are presented in the subject's peripheral field of vision. After the spatial stimulus is hidden, the subjects' depth or spatial location reproduction results of the spatial stimulus are collected.

[0010] Preferably, the above-mentioned multi-dimensional mixed reality evaluation method obtains spatial depth perception performance indicators for each capability dimension in the corresponding task, including: Regarding the peripheral visual depth capture dimension, the collected spatial depth perception performance indicators include the spatial motion parameters of spatial stimuli, the central task performance of the subjects, and the subjects' depth reproduction or spatial location reproduction results of spatial stimuli. The depth reproduction error of the subject is calculated based on the spatial parameters and the depth reproduction or spatial location reproduction results. Based on the performance of the central task and the results of deep reproduction or spatial location reproduction, the success rate of the central task and the damage status of the dual tasks are calculated.

[0011] Preferably, in the above-mentioned multi-dimensional mixed reality assessment and training method, virtual reality tasks or mixed reality tasks are configured for each of the multiple capability dimensions, including: For the dynamic spatial memory reconstruction dimension, multiple dynamic targets are generated in the virtual reality environment, and the movement of multiple dynamic targets within a preset spatial range is controlled. After the dynamic target finishes moving or the motion hides for a preset time, one or more dynamic targets are selected as memory targets from multiple dynamic targets. The memory targets include the target's depth position and spatial position. During the recall phase of the memory target, the subject's recall results of the target's depth or spatial location were obtained.

[0012] Preferably, in the above-mentioned multi-dimensional mixed reality evaluation and training method, spatial depth perception performance indicators are obtained for each capability dimension in the corresponding task, including: For the dynamic spatial memory reconstruction dimension, based on the target parameters and spatial location of the memory objective, as well as the subject's location reproduction results, the subject's memory reconstruction performance index is calculated; among them, Memory reconstruction performance metrics include: target position error, depth error, planar error, first response time, completion time, and one or more of the following: accuracy or performance score.

[0013] Preferably, in the above-mentioned multi-dimensional mixed reality assessment and training method, virtual reality tasks or mixed reality tasks are configured for each of the multiple capability dimensions, including: For the dynamic depth perception and action coupling dimension, a task coordinate system is established based on the subject's starting position and orientation in a mixed reality environment, and at least one task response region is generated in the coordinate system; Based on the task response area, a dynamic virtual target with preset trajectory parameters and depth changes is generated, and the body displacement data generated by the subject in response to the dynamic virtual target is collected.

[0014] Preferably, in the above-mentioned multi-dimensional mixed reality evaluation and training method, spatial depth perception performance indicators are obtained for each capability dimension in the corresponding task, including: For the dynamic depth perception and action coupling dimension, based on the preset trajectory parameters and depth changes of the dynamic virtual target, as well as the subject's body displacement data, the subject's action response results are calculated; the action response results include: The target area entry determination result, area stay time, distance error, position error, percentage of time to reach the target, total movement distance and average movement speed are one or more of the following: target area entry determination result, area stay time, distance error, position error, percentage of time to reach the target, total movement distance and average movement speed.

[0015] Preferably, in the above-mentioned multi-dimensional mixed reality assessment and training method, virtual reality tasks and / or mixed reality tasks are loaded for the subject according to a preset task sequence, and spatial depth perception assessment or training of multiple ability dimensions under the corresponding tasks is performed, including: Tasks across multiple capability dimensions are organized and executed in a fixed order, random order, phased order, or training plan order; among them, The tasks are organized and executed in a fixed order, including: sequential execution of the surrounding visual depth capture dimension, the dynamic spatial memory reconstruction dimension, and the dynamic depth perception and action coupling dimension. The tasks corresponding to multiple capability dimensions are organized and executed in a random order, including: randomly selecting any two capability dimensions to combine and execute the corresponding tasks.

[0016] Preferably, in the above-mentioned multi-dimensional mixed reality assessment and training method, the assessment results or training results for the corresponding capability dimensions are generated based on the spatial depth perception performance indicators, including: The evaluation results or training results are output separately according to the capability dimensions, and are not combined into a single comprehensive score; Based on the assessment results or training results, identify the shortcomings of the subjects in the ability dimensions of the spatial depth perception ability chain; Develop testing or training plans based on weaknesses in each competency dimension to balance the subject's multiple competency dimensions.

[0017] According to a second aspect of this application, this application also provides a multi-dimensional mixed reality training and evaluation system for spatial depth perception, comprising: The dimension division module is used to divide the spatial depth perception ability into multiple capability dimensions according to the cognitive behavior state. Among them, the multiple capability dimensions include the peripheral visual depth capture dimension under the attention load state, the dynamic spatial memory reconstruction dimension under the spatial memory state, and the dynamic depth perception and action coupling dimension under the action response state. The multi-task configuration module is used to configure virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions. The task execution module is used to load virtual reality tasks and / or mixed reality tasks for the subject according to a preset task sequence, and to perform spatial depth perception assessment or training for multiple ability dimensions under the corresponding task. The dimensionality index calculation module is used to obtain the spatial depth perception performance index of the subject in each ability dimension in the corresponding task. The evaluation and testing module is used to generate evaluation results or training results for the corresponding capability dimensions based on spatial depth perception performance indicators.

[0018] The technical solution of this application has at least the following technical effects: This application provides a multi-dimensional mixed reality assessment and training method and system for spatial depth perception. By breaking down spatial depth perception ability from a single depth judgment into multiple capability dimensions under real-world competition conditions, and transforming these capability dimensions into executable, measurable, and trainable task flows through virtual reality or mixed reality technologies, it better reflects the complexity of spatial information processing in real-world competition. These multiple capability dimensions include peripheral visual depth capture under attentional load conditions, dynamic spatial memory reconstruction under spatial memory conditions, and dynamic depth perception and action coupling under action response conditions. This allows for the comprehensive assessment of athletes' spatial depth perception ability from three dimensions: peripheral visual capture, spatial memory reconstruction, and perception-action coupling. By configuring virtual reality or mixed reality tasks for each capability dimension, abstract spatial cognitive abilities can be transformed into executable tasks through virtual reality or mixed reality technologies. By acquiring spatial depth perception performance indicators for each capability dimension under each task, objective indicators can be output, reducing subjective human evaluation. Furthermore, this solution is closer to real-world sports. By setting tasks for various task states, it can simulate and test complex depth perception abilities occurring continuously under multiple cognitive and behavioral states, exhibiting higher ecological validity. This solution can be used for both training and assessment. Based on spatial depth perception performance indicators, it generates corresponding assessment or training results for different ability dimensions, thereby identifying athletes' weaknesses in different ability dimensions and improving the targeting of training. Finally, this solution is not only applicable to football but can also be extended to other open sports, thus adapting to scenarios requiring multi-state spatial depth perception. In summary, the technical solution of this application can solve the problem of existing technologies failing to cover the complete usage chain of spatial depth perception in real sports, and can explain the comprehensive performance issues of athletes simultaneously facing attentional load, spatial memory, and motor response in real competitions. Attached Figure Description

[0019] 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 multi-dimensional mixed reality training method for spatial depth perception provided in an embodiment of this application; Figure 2 for Figure 1 The illustrated embodiment provides a flowchart of the task configuration method for the first capability dimension. Figure 3 for Figure 1The illustrated embodiment provides a flowchart of a method for obtaining spatial depth perception performance indicators; Figure 4 for Figure 1 A flowchart illustrating the task configuration method for the second capability dimension provided in the illustrated embodiment; Figure 5 for Figure 1 The flowchart of the task configuration method for the third capability dimension provided in the embodiment shown is illustrated. Figure 6 for Figure 1 The illustrated embodiment provides a flowchart of a spatial depth perception evaluation or training execution method; Figure 7 for Figure 1 The illustrated embodiment provides a flowchart of a method for evaluating or generating training results for a capability dimension. Figure 8 A schematic diagram of the structure of a multi-dimensional mixed reality training and evaluation system for spatial depth perception provided in this application embodiment; Figure 9-1 This application provides a schematic diagram of a surrounding visual depth capture scene. Figure 9-2 This is a schematic diagram of a dynamic spatial memory reconstruction scenario provided in an embodiment of this application; Figure 9-3 This application provides a schematic diagram of a dynamic depth perception and action coupling scene. Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] To more clearly illustrate the overall concept of this application, a detailed explanation is provided below with reference to the accompanying drawings.

[0021] 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 described below. It should be noted that, unless otherwise specified, the embodiments of this application and the features thereof can be combined with each other.

[0022] 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.

[0023] The existing technology has the following drawbacks: Traditional depth perception training often treats spatial depth perception as a single ability, measuring subjects' ability to judge the distance of targets through static instruments, 2D screen tasks, or single VR scenes. However, spatial depth perception in real sports (such as football) is not a static judgment in a single state, but a complex ability that occurs continuously in multiple cognitive and behavioral states. Existing assessment and training systems for spatial perception ability (including evaluation and training) mostly target one cognitive and behavioral state, making it difficult to cover the complete chain of use of spatial depth perception ability in real sports. The evaluation or training results of a single task or state may only reflect the subject's performance in static judgment, location reproduction, or simple reactions, and cannot explain their comprehensive performance when facing attentional load, spatial memory, and motor response simultaneously in real competition.

[0024] To address the aforementioned technical problems, the following embodiments of this application provide a multi-dimensional mixed reality evaluation and training method for spatial depth perception, and a multi-state task paradigm for spatial depth perception capabilities. This method breaks down the same core capability into multiple capability dimensions under real-world competition conditions, and uses VR / MR technology to transform these capability dimensions into executable, measurable, and trainable task flows. It can collect objective performance indicators under different conditions and output evaluation or training results according to capability dimensions, thus more closely reflecting actual competition (e.g., a football match).

[0025] See details Figure 1 , Figure 1 This is a flowchart illustrating a multi-dimensional mixed reality training method for spatial depth perception, provided as an embodiment of this application. Figure 1 As shown, this multi-dimensional mixed reality training method for spatial depth perception includes: S110: Based on cognitive behavior states, spatial depth perception ability is divided into multiple capability dimensions; among them, multiple capability dimensions include the peripheral visual depth capture dimension under attentional load state, the dynamic spatial memory reconstruction dimension under spatial memory state, and the dynamic depth perception and action coupling dimension under action response state.

[0026] This application no longer treats spatial depth perception as a single indicator, but rather breaks it down into three complementary capability dimensions, configuring corresponding virtual reality (VR) / mixed reality (MR) tasks according to cognitive behavioral states. During spatial depth perception assessment or training, at least two of these capability dimensions are selected for evaluation or training. The division of capability dimensions is based on cognitive behavioral states, which include attentional load state, spatial memory state, and action response state. By covering attentional load state, spatial memory state, and action response state respectively, the athlete's spatial depth perception ability can be assessed from three dimensions: peripheral visual capture, spatial memory reconstruction, and perception-action coupling.

[0027] S120: Configure virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions.

[0028] In the configured virtual reality or mixed reality tasks, each task includes at least two capability dimensions to assess or train the subject's spatial depth perception ability. For example, the peripheral visual depth capture dimension under attentional load and the dynamic spatial memory reconstruction dimension under spatial memory state can be configured into virtual reality tasks.

[0029] S130: Load virtual reality tasks and / or mixed reality tasks for the subject according to a preset task sequence, and perform spatial depth perception assessments or training for multiple ability dimensions under the corresponding tasks. The corresponding tasks are virtual reality tasks and / or mixed reality tasks, specifically set according to the preset task sequence mentioned above.

[0030] The preset task sequence here includes a fixed sequence, a random sequence, a phased sequence, or a training plan sequence. Subjects can complete the corresponding tasks sequentially, or choose to combine at least two tasks based on the training plan, assessment goals, or subject performance. Data generated from each task is categorized into the corresponding ability dimension to form multi-dimensional assessment or training results. This application's embodiments can configure a combination paradigm of virtual reality or mixed reality tasks based on ability dimensions; that is, it does not simply stack multiple training scenarios, but rather configures corresponding virtual reality or mixed reality tasks for different ability dimensions according to the performance of depth perception ability under different competition conditions.

[0031] S140: Obtain the spatial depth perception performance metrics for each capability dimension in the corresponding task. Spatial depth perception performance metrics include reaction time, error, completion time, accuracy, and distance retention rate.

[0032] By using virtual reality (VR) / mixed reality (MR) technology, abstract spatial cognition ability is transformed into executable tasks, and objective spatial depth perception performance indicators such as reaction time, error, completion time, accuracy, and distance retention ratio are output. The embodiments of this application can reduce subjective human evaluation and enhance the objectivity of the evaluation of the subject's spatial depth perception ability by collecting objective indicators under multi-state tasks.

[0033] S150: Based on the spatial depth perception performance indicators, generate evaluation results or training results for the corresponding capability dimensions.

[0034] The technical solution of this application covers the complete application chain of spatial depth perception ability in real sports projects. Based on spatial depth perception performance indicators, it trains and evaluates subjects' abilities in multiple dimensions. Specifically, the evaluation mode can be used to identify the weaknesses of athletes in different ability dimensions; the training mode can assign corresponding tasks to address these weaknesses, improving the targeting of training. Through this approach, the spatial depth perception ability in open sports (such as football) can be extended from single-depth judgment to multi-state, multi-task training reflexes, better reflecting the complexity of spatial information processing in real competitions.

[0035] The multi-dimensional mixed reality assessment method for spatial depth perception provided in this application breaks down spatial depth perception ability from a single depth judgment into multiple ability dimensions under real competition conditions. These ability dimensions are then transformed into executable, measurable, and trainable task flows using virtual reality or mixed reality technologies, better reflecting the complexity of spatial information processing in real competition. The multiple ability dimensions include peripheral visual depth capture under attentional load conditions, dynamic spatial memory reconstruction under spatial memory conditions, and dynamic depth perception and action coupling under action response conditions. This comprehensively assesses athletes' spatial depth perception ability from three dimensions: peripheral visual capture, spatial memory reconstruction, and perception-action coupling. By configuring virtual reality or mixed reality tasks for each of the multiple ability dimensions, abstract spatial cognitive abilities can be transformed into executable tasks using virtual reality or mixed reality technologies. Furthermore, by acquiring spatial depth perception performance indicators for each ability dimension under each task, objective indicators can be output, reducing subjective human evaluation. In addition, this solution is closer to real sports; by setting tasks for various task states, it can simulate and test complex depth perception abilities occurring continuously under multiple cognitive and behavioral states, exhibiting higher ecological validity. This solution can be used for both training and assessment. Based on spatial depth perception performance indicators, it generates corresponding assessment or training results for different ability dimensions, thereby identifying athletes' weaknesses in different ability dimensions and improving the targeting of training. Finally, this solution is not only applicable to football but can also be extended to other open sports, thus adapting to scenarios requiring multi-state spatial depth perception. In summary, the technical solution of this application can solve the problem of existing technologies failing to cover the complete usage chain of spatial depth perception in real sports, and can explain the comprehensive performance issues of athletes simultaneously facing attentional load, spatial memory, and motor response in real competitions.

[0036] Among them, for the peripheral visual depth capture dimension under attentional load, as a preferred embodiment, such as... Figure 2 As shown, in the above multi-dimensional mixed reality training method, S120: Virtual reality tasks or mixed reality tasks are configured for each of the multiple capability dimensions, including: S121: For the peripheral visual depth capture dimension, present the central dynamic task in the virtual reality environment and record the subject's central task performance, while presenting spatial stimuli with spatial depth in the subject's peripheral vision. S122: After the spatial stimulus is hidden, collect the subject's results on the depth or spatial location reproduction of the spatial stimulus.

[0037] In the technical solution provided in this application embodiment, the peripheral visual depth capture dimension under attentional load is the ability of athletes in open sports (such as football) to perceive spatial depth using peripheral vision when the central dynamic task is present.

[0038] Combination Figure 9-1 As illustrated in the schematic diagram of a peripheral visual depth capture scenario, in one exemplary embodiment, a central dynamic task is first generated in the virtual reality environment, such as multiple target movements, directional signals, prohibition signals, or other attentional load tasks. The subject needs to continuously process this central dynamic task. Simultaneously, a spatial stimulus with a depth parameter is briefly presented in the subject's peripheral visual field. After a preset time, the spatial stimulus is hidden, and the subject reproduces the depth or spatial position of the stimulus through a controller, gestures, or other input methods. At this time, the subject's depth reproduction or spatial position reproduction results are collected through a VR device, thereby achieving peripheral visual depth capture under attentional load.

[0039] Combination Figure 9-1 As shown in the schematic diagram of the peripheral visual depth capture scenario, corresponding to the peripheral visual depth capture dimension under attentional load, it is necessary to obtain the spatial depth perception performance index under this capability dimension.

[0040] Therefore, as a preferred embodiment, such as Figure 3 As shown, step S140 above involves obtaining the spatial depth perception performance metrics for each capability dimension in the corresponding task, including: S141: For the peripheral visual depth capture dimension, the collected spatial depth perception performance indicators include the spatial motion parameters of spatial stimuli, the central task performance of the subjects, and the subjects' depth reproduction or spatial location reproduction results of spatial stimuli. S142: Calculate the depth reproduction error of the subject based on the spatial parameters and the depth reproduction or spatial location reproduction results; S143: Based on the performance of the central task and the results of depth reproduction or spatial location reproduction, the success rate of the central task and the damage status of the dual tasks are calculated.

[0041] Combination Figure 9-1 In the scenario shown, for the peripheral visual depth capture dimension under attentional load, the spatial depth perception performance indicators and calculated parameters that can be collected in this embodiment are as follows: 1. Eccentricity, orientation angle, and set depth of the peripheral stimulus; 2. The depth or location of repetition in the subject; 3. Depth error, three-dimensional position error, or relative error; 4. The reaction time from the disappearance of the stimulus to the initiation of the action; 5. The motion execution time from initiation to confirmation of reproduction; 6. The success rate of the central task or the status of both tasks being compromised.

[0042] Specifically, in football, this peripheral visual depth capture dimension can be used to simulate a football player's ability to capture the depth positions of teammates, opponents, and open spaces through peripheral vision when dribbling, observing defensive pressure, or processing positive information.

[0043] In addition, combined Figure 9-2 As shown in the schematic diagram of the dynamic spatial memory reconstruction scenario, regarding the dimensions of dynamic spatial memory reconstruction in the spatial memory state, such as... Figure 4 As shown in a preferred embodiment, in the above multi-dimensional mixed reality training method, S120: configuring virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions, including: S123: For the dynamic spatial memory reconstruction dimension, multiple dynamic targets are generated in the virtual reality environment, and the movement of multiple dynamic targets within a preset spatial range is controlled. S124: After the dynamic target finishes moving or the motion hides for a preset time, select one or more dynamic targets as memory targets, wherein the memory targets include the target's depth position and spatial position; S125: During the recall phase of the memory target, obtain the subject's results of recalling the target's depth or spatial location.

[0044] In the technical solutions provided in this application, attention is paid to the peripheral visual depth capture dimension under load conditions, corresponding to the athlete's ability to maintain and reconstruct the dynamic spatial situation after a brief scan. In one exemplary embodiment, multiple dynamic targets are generated in a virtual reality environment, and their movement is controlled within a preset spatial range. After the dynamic target's movement ends or the hiding time after the dynamic target's movement reaches a preset time, one or more targets are selected as memory targets, and the subject is prompted to remember their spatial positions. Subsequently, the target is hidden or the scene enters a delay phase. During the reproduction phase, the subject reproduces the target's depth position or spatial position through a controller, reproduction markers, or other input methods. The subject's position reproduction results for the target's depth position or spatial position are obtained during this reproduction phase, thereby evaluating and training the subject's dynamic spatial memory reconstruction ability.

[0045] Combination Figure 9-2 As shown in the schematic diagram of the dynamic spatial memory reconstruction scenario, corresponding to the dynamic spatial memory reconstruction dimension in the spatial memory state, it is necessary to obtain the spatial depth perception performance index under this capability dimension. As a preferred embodiment, in the above multi-dimensional mixed reality training method, S140: Obtain the spatial depth perception performance index under each capability dimension in the corresponding task, including: S144: For the dynamic spatial memory reconstruction dimension, based on the target parameters and spatial location of the memory objective, as well as the subject's location reproduction results, the subject's memory reconstruction performance index is calculated; among which, The target parameters for memory objectives include the number of dynamic targets, speed, movement time, and target depth range; spatial location includes the actual spatial location of the target object; and the subject's location reproduction results include the subject's reproduced location. Memory reconstruction performance indicators include one or more of the following: target location error, depth error, planar error, first response time, completion time, and accuracy or performance score.

[0046] The parameters that can be collected and calculated, as well as the memory reconstruction performance indicators, in this application embodiment include: 1. Dynamic target quantity, speed, movement time, and target depth range; 2. The actual spatial location of the target object; 3. Location of subject re-enactment; 4. Positional error, depth error, or planar error; 5. Initial response time; 6. Completion time; 7. Accuracy or score.

[0047] Specifically, in the sport of football, this dynamic spatial memory reconstruction dimension can be used to simulate the ability of football players to maintain the spatial relationship between teammates, opponents, and other players in their brains after scanning, turning, turning their backs, or switching their gaze before receiving the ball.

[0048] In addition, combined Figure 9-3 As shown in the schematic diagram of the dynamic depth perception and action coupling scenario, for the dynamic depth perception and action coupling capability in the action response state, as a preferred embodiment, such as... Figure 5 As shown, in the above multi-dimensional mixed reality training method, S120: Virtual reality tasks or mixed reality tasks are configured for each of the multiple capability dimensions, including: S126: For the dynamic depth perception and action coupling dimension, establish a task coordinate system based on the subject's initial position and orientation in a mixed reality environment, and generate at least one task response region in the coordinate system. The task response region includes, but is not limited to, a forward pressure zone, a backward withdrawal zone, a starting zone, a target direction, or a response region.

[0049] S127: Based on the task response area, generate a dynamic virtual target with preset trajectory parameters and depth changes, and collect the body displacement data generated by the subject in response to the dynamic virtual target.

[0050] like Figure 9-3The illustrated dynamic depth perception and action coupling scenario corresponds to an athlete's ability to respond with realistic body movements based on changes in the speed, direction, and depth of a dynamic target. In one exemplary implementation, a task coordinate system is established in a mixed reality environment based on the subject's starting position and orientation, and at least one task response region is generated within this coordinate system, such as a forward pressure zone, a backward pressure zone, a starting zone, a target direction, or a response region. Then, a dynamic virtual target with preset trajectory parameters and depth variations is generated within this task response region. The subject needs to perform body displacement within the corresponding task response region based on the target's motion characteristics, such as forward pressure, backward pressure, or maintaining distance. At this time, body displacement data generated by the subject in response to the dynamic virtual target is collected.

[0051] Corresponding to the mixed reality task under the dynamic depth perception-action coupling dimension, as a preferred embodiment, the spatial depth perception performance index under each capability dimension of the corresponding task is obtained, including: S145 targets the dynamic depth perception and action coupling dimension, and calculates the subject's action response results based on the preset trajectory parameters and depth changes of the dynamic virtual target, as well as the subject's body displacement data. The action response results include one or more of the following: target area entry determination result, area dwell time, distance error, position error, percentage of time to reach the target, total movement distance, and average movement speed.

[0052] The following parameters can be collected and calculated during the calculation of the subject's action response: 1. Dynamic target's initial position, target position, velocity, and trajectory; 2. The subject's starting and ending positions; 3. Action start time; 4. Action completion time; 5. Have you entered the target area? 6. Duration of stay in the area; 7. Distance error, average distance error, or defensive positioning error; 8. Percentage of time required to meet the target; 9. Total distance traveled and average speed traveled.

[0053] This dynamic depth perception and action coupling dimension is used to simulate the ability of athletes in open-ended sports (such as football) to perform body movements based on depth changes and velocity estimation when facing approaching, moving away from, laterally moving or irregularly moving targets.

[0054] In addition, as a preferred embodiment, such as Figure 6As shown, in the above multi-dimensional mixed reality assessment and training method, S130: Virtual reality tasks and / or mixed reality tasks are loaded for the subject according to a preset task sequence, and spatial depth perception assessment or training is performed on multiple ability dimensions under the corresponding tasks, including: S131: Organize and execute corresponding tasks across multiple capability dimensions according to a fixed order, random order, phased order, or training plan order; among which, S132: Organize and execute corresponding tasks of multiple capability dimensions in a fixed order, including: sequential execution of the surrounding visual depth capture dimension, the dynamic spatial memory reconstruction dimension, and the dynamic depth perception and action coupling dimension; S133: Organize and execute corresponding tasks for multiple capability dimensions in a random order, including: randomly selecting two capability dimensions to combine and execute corresponding tasks.

[0055] The technical solution provided in this application can realize the combination of multi-state tasks (i.e., multiple capability dimensions). Specifically, the above tasks can be organized in a fixed order, a random order, a phased order, or a training plan order. Among them, the fixed order can be used for standardized assessment, the random order can be used to reduce the order effect, the phased order can be used for training intervention, and the training plan order can be used to arrange the key training dimensions according to the subject's performance.

[0056] In one exemplary implementation, to align with a real-world sports competition scenario (such as football), the process first involves performing a peripheral visual depth capture task, then a dynamic spatial memory reconstruction task, and finally a dynamic target perception-action coupling task. This sequence corresponds to the chain in a football match from "perceptual input" to "spatial retention" and then to "action output."

[0057] In another exemplary implementation, any two task dimensions can be selected for execution in combination, for example, all tasks can be executed in the pre-test, while the task dimensions in which the subject performs weaker are focused on during training.

[0058] In addition, as a preferred embodiment, such as Figure 7 As shown, in the above multi-dimensional mixed reality evaluation and training method, S150: Based on the spatial depth perception performance index, generate evaluation results or training results for the corresponding capability dimension, including: S151: Output evaluation results or training results separately according to the capability dimensions, and do not combine them into a single comprehensive score; This application's embodiments do not require merging the scores of the three capability dimensions into a single general score. Instead, they output evaluation results or training results separately for each capability dimension. This allows data generated from different tasks to be categorized into capability dimensions such as peripheral visual depth capture, dynamic spatial memory reconstruction, and spatial depth perception-action coupling. Specifically: Evaluation or training results for the peripheral visual depth capture dimension include: depth reproduction error, reaction time, motion execution time, dual-task success rate, etc. Evaluation or training results for the dynamic spatial memory reconstruction dimension include: target position error, first response time, completion time, accuracy, etc. Evaluation or training results for dynamic depth perception and action coupling include: action start time, action completion time, region achievement rate, distance error, and percentage of time to achieve the target.

[0059] S152: Based on the assessment results or training results, identify the shortcomings in the subject's ability dimensions in the spatial depth perception ability chain.

[0060] Based on the above-mentioned multi-dimensional assessment or training results, coaches, researchers, or evaluation systems can identify the specific weaknesses of subjects in the spatial depth perception chain and select corresponding tasks for targeted training and testing.

[0061] S153: Develop testing or training plans based on weaknesses in ability dimensions to balance multiple ability dimensions of the test taker.

[0062] In the technical solution provided in this application, by generating evaluation results or training plans dimensionally, the examiner or coach can determine the specific shortcomings in the subject's ability dimension within the football spatial depth perception chain. For example, if the subject's peripheral visual depth capture performance is weak, it indicates insufficient ability to utilize peripheral spatial information under primary task load; if spatial memory reconstruction performance is weak, it indicates insufficient ability to maintain spatial posture after saccades; if perception-action coupling performance is weak, it indicates insufficient ability to complete body movement responses based on dynamic spatial depth information. At this point, a test or training plan can be specified based on the shortcomings in each ability dimension to balance and improve the subject's multiple ability dimensions.

[0063] In addition, the following embodiments of this application provide product embodiments, which have the same beneficial effects as the multi-dimensional mixed reality training method for spatial depth perception 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.

[0064] See Figure 8 , Figure 8 This is a schematic diagram of the structure of a multi-dimensional mixed reality training and evaluation system for spatial depth perception, provided as an embodiment of this application. Figure 8 As shown, this multi-dimensional mixed reality assessment and training system includes: The dimension division module 110 is used to divide the spatial depth perception ability into multiple capability dimensions according to the cognitive behavior state; among them, the multiple capability dimensions include the peripheral visual depth capture dimension under the attention load state, the dynamic spatial memory reconstruction dimension under the spatial memory state, and the dynamic depth perception and action coupling dimension under the action response state. The multi-task configuration module 120 is used to configure virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions. The task execution module 130 is used to load virtual reality tasks and / or mixed reality tasks for the subject according to a preset task sequence, and to perform spatial depth perception assessment or training for multiple ability dimensions under the corresponding task. The dimensionality index calculation module 140 is used to obtain the spatial depth perception performance index of the subject in each ability dimension in the corresponding task. The evaluation and testing module 150 is used to generate evaluation results or training results for the corresponding capability dimensions based on spatial depth perception performance indicators.

[0065] The multi-dimensional mixed reality training and evaluation system for spatial depth perception provided in this application has at least the following technical effects: (1) This application extends the ability to perceive spatial depth in football from a single depth judgment to a multi-state, multi-task training paradigm, which is more in line with the complexity of spatial information processing in real games.

[0066] (2) This application covers attentional load state, spatial memory state and action response state respectively, and can evaluate the athlete’s spatial depth perception ability from three dimensions: peripheral visual capture, spatial memory reconstruction and perception-action coupling.

[0067] (3) This application uses VR / MR technology to transform abstract spatial cognitive ability of football into an executable task and outputs objective indicators such as reaction time, error, completion time, accuracy, and distance maintenance ratio, thereby reducing subjective human evaluation.

[0068] (4) This application is closer to football practice. Football players do not simply judge static depth during a match, but continuously use depth perception in states such as dribbling, scanning, receiving the ball, turning, defending, and blocking space. This application sets tasks corresponding to these states, and therefore has higher ecological validity.

[0069] (5) This application can be used for training and assessment. In the assessment mode, it can be used to identify the weaknesses of athletes in different ability dimensions; in the training mode, corresponding tasks can be arranged for the weakness dimensions to improve the training focus.

[0070] (6) This application can be extended to other open sports, such as basketball, rugby, ice hockey, tennis, badminton, driving obstacle avoidance and rehabilitation training, which require multi-state spatial depth perception capabilities.

[0071] See also: Figure 10 , Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 10 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 multi-dimensional mixed reality training method for spatial depth perception of any of the above embodiments. Reference is made below. Figure 10 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 10 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.

[0072] 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.

[0073] 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.

[0074] 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 multi-dimensional mixed reality assessment and training method for spatial depth perception, characterized in that, include: Based on cognitive behavior states, spatial depth perception ability is divided into multiple capability dimensions; among which, the multiple capability dimensions include the peripheral visual depth capture dimension under attentional load state, the dynamic spatial memory reconstruction dimension under spatial memory state, and the dynamic depth perception and action coupling dimension under action response state. Configure virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions; Virtual reality tasks and / or mixed reality tasks are loaded onto the subjects according to the preset task sequence, and spatial depth perception assessments or training are performed on multiple ability dimensions under the corresponding tasks. Obtain the spatial depth perception performance indicators for each capability dimension in the corresponding task. Based on the spatial depth perception performance indicators, evaluation results or training results corresponding to the capability dimensions are generated.

2. The method according to claim 1, characterized in that, The step of configuring virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions includes: Regarding the peripheral visual depth capture dimension, a central dynamic task is presented in a virtual reality environment and the subject's performance on the central task is recorded, while spatial stimuli with spatial depth are presented in the subject's peripheral visual field. After the spatial stimulus is hidden, the subject's depth reproduction or spatial location reproduction results of the spatial stimulus are collected.

3. The method according to claim 2, characterized in that, The step of obtaining the spatial depth perception performance index for each capability dimension in the corresponding task includes: Regarding the peripheral visual depth capture dimension, the collected spatial depth perception performance indicators include the spatial motion parameters of the spatial stimuli, the subject's central task performance, and the subject's depth reproduction or spatial location reproduction results of the spatial stimuli. Based on the spatial parameters and the depth reproduction or spatial location reproduction results, the depth reproduction error of the subject is calculated. Based on the performance of the central task and the results of the depth reproduction or spatial location reproduction, the success rate of the central task and the damage status of the dual tasks are calculated.

4. The method according to claim 1, characterized in that, The step of configuring virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions includes: For the aforementioned dynamic spatial memory reconstruction dimension, multiple dynamic targets are generated in the virtual reality environment, and the multiple dynamic targets are controlled to move within a preset spatial range; After the dynamic target finishes moving or the movement is hidden for a preset time, one or more of the multiple dynamic targets are selected as memory targets, wherein the memory targets include the target depth position and spatial position; During the recall phase of the memory target, the subject's recall results of the target's depth location or spatial location are obtained.

5. The method according to claim 4, characterized in that, The step of obtaining the spatial depth perception performance index for each capability dimension in the corresponding task includes: For the dynamic spatial memory reconstruction dimension, based on the target parameters and spatial location of the memory target and the location reproduction results of the subject, the subject's memory reconstruction performance index is calculated; wherein, The memory reconstruction performance metrics include one or more of the following: target position error, depth error, planar error, first response time, completion time, and accuracy or performance score.

6. The method according to claim 1, characterized in that, The step of configuring virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions includes: For the dynamic depth perception and action coupling dimension, a task coordinate system is established in the mixed reality environment based on the subject's starting position and orientation, and at least one task response region is generated in the coordinate system; Based on the task response area, a dynamic virtual target with preset trajectory parameters and depth changes is generated, and the body displacement data generated by the subject in relation to the dynamic virtual target is collected.

7. The method according to claim 6, characterized in that, The step of obtaining the spatial depth perception performance index for each capability dimension in the corresponding task includes: For the dynamic depth perception and action coupling dimension, based on the preset trajectory parameters and depth changes of the dynamic virtual target, and the subject's body displacement data, the subject's action response result is calculated; wherein, the action response result includes: The target area entry determination result, area stay time, distance error, position error, percentage of time to reach the target, total movement distance and average movement speed are one or more of the following: target area entry determination result, area stay time, distance error, position error, percentage of time to reach the target, total movement distance and average movement speed.

8. The method according to claim 1, characterized in that, The process of loading virtual reality tasks and / or mixed reality tasks onto the subject according to a preset task sequence, and performing spatial depth perception assessments or training for multiple ability dimensions under the corresponding tasks, includes: The preset task sequence includes a fixed sequence, a random sequence, a phased sequence, or a training plan sequence. The tasks corresponding to the multiple capability dimensions are organized and executed in a fixed order, a random order, a phased order, or a training plan order; wherein, The tasks corresponding to the multiple capability dimensions are organized and executed in a fixed order, including: sequential execution of the peripheral visual depth capture dimension, the dynamic spatial memory reconstruction dimension, and the dynamic depth perception and action coupling dimension. The tasks corresponding to the multiple capability dimensions are organized and executed in a random order, including: randomly selecting any two capability dimensions to combine and execute the corresponding tasks.

9. The method according to claim 1, characterized in that, The step of generating evaluation results or training results corresponding to the capability dimension based on the spatial depth perception performance index includes: The evaluation results or training results are output separately according to the aforementioned capability dimensions, and are not combined into a single comprehensive score; Based on the assessment or training results, identify the subject's weakness in the spatial depth perception capability chain. Test or training plans are developed based on the shortcomings in the aforementioned ability dimensions in order to balance the subject's multiple ability dimensions.

10. A multi-dimensional mixed reality assessment and training system for spatial depth perception, characterized in that, The method used in any one of claims 1 to 9; The multi-dimensional mixed reality assessment and training system includes: The dimension division module is used to divide the spatial depth perception ability into multiple capability dimensions according to the cognitive behavior state; wherein, the multiple capability dimensions include the peripheral visual depth capture dimension under the attention load state, the dynamic spatial memory reconstruction dimension under the spatial memory state, and the dynamic depth perception and action coupling dimension under the action response state. A multi-task configuration module is used to configure virtual reality tasks or mixed reality tasks for each of the multiple capability dimensions. The task execution module is used to load virtual reality tasks and / or mixed reality tasks for the subject according to a preset task sequence, and to perform spatial depth perception assessment or training for multiple ability dimensions under the corresponding task. The dimensionality index calculation module is used to obtain the spatial depth perception performance index of the subject in each ability dimension in the corresponding task. The evaluation and testing module is used to generate evaluation results or training results corresponding to the capability dimension based on the spatial depth perception performance indicators.

Images