Ball training device and method based on visual training

Abstract

The invention discloses a ball training device and method based on visual training. The device comprises a table top, a blocking net and a foot stool. First visual training modules are arranged at the upper end of the blocking net at intervals and used for sensing the position where a table tennis ball passes through the position above the blocking net and illuminating the table tennis ball. Second visual training modules are evenly arranged on the table top and used for sensing the falling point position of the table tennis ball on the table top and illuminating the table tennis ball. The system further comprises a control module and an input module. The control module is respectively connected with the input module, the first visual training module and the second visual training module, and is used for acquiring training information input by a user through the input module; and controlling the working state of the first visual training module and / or the second visual training module according to the training information. Visual training is more comprehensive, corresponding multi-level adjustment is carried out according to the use requirements of the user, and the visual training effect is improved.

Description

Technical Field

[0001] The invention relates to the technical field of sports, and in particular to a ball training device and method based on vision training. Background Art

[0002] Table tennis is a sport that combines fitness, competitiveness and entertainment. People who often play table tennis have great significance for the health of eye muscles. It can enhance the amplitude of eye adjustment function, increase the myopia resistance of the eyes, and reduce the risk of myopia. In the prior art, a number of luminous bodies are arranged on the barrier net. Based on the sensing device sensing the position of the table tennis ball passing through the net during training, when the sensing device senses that the table tennis ball passes a certain position above the barrier net, the sensing device triggers the control device to send a corresponding control signal, so that the luminous body in the area corresponding to the position of the table tennis ball passing through the net on the barrier net emits light and illuminates the table tennis ball. When the table tennis ball leaves the barrier net, the control device controls the luminous body in the aforementioned area to extinguish. The purpose of visual training of human eye muscles and color vision is achieved to a certain extent, and it adds interest to a certain extent. However, the visual training in the prior art is not comprehensive enough, as it only considers the state of the table tennis ball when it passes through the net, but does not consider the state of the table tennis ball after it falls on the table. It cannot make corresponding adjustments according to the user's usage needs, nor can it automatically match the correct training plan according to the user's training status. The effect of visual training is greatly reduced, and at the same time, it is not of much help to improve the user's playing skills during ball training. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the purpose of the present invention is to provide a ball training device based on visual training, which can provide more comprehensive visual training and perform corresponding multi-level adjustments according to the user's usage needs to improve the effect of visual training.

[0004] To achieve the above-mentioned purpose, the embodiment of the present invention provides a ball training device based on visual training, comprising a table, a net and a tripod; a first visual training module is arranged at intervals on the upper end of the net, which is used to sense the position of a table tennis ball passing above the net and illuminate the table tennis ball;

[0005] The table top is evenly provided with second visual training modules for sensing the landing position of the table tennis ball on the table top and illuminating the table tennis ball;

[0006] It also includes a control module and an input module; the control module is connected to the input module, the first visual training module, and the second visual training module, respectively, and is used to:

[0007] Obtain training information input by the user through the input module;

[0008] The working state of the first vision training module and / or the second vision training module is controlled according to the training information.

[0009] According to some embodiments of the present invention, a table tennis ball detector is also provided at the upper end of the barrier net for monitoring the motion state of the table tennis ball when passing through the barrier net; the motion state includes speed, angle and rotation information;

[0010] The control module is connected to the table tennis ball detector and is used to:

[0011] Determine the estimated landing point of the table tennis ball according to the motion state of the table tennis ball when passing through the net;

[0012] When it is determined that the estimated landing point position belongs to the table area, the second visual training module corresponding to the estimated landing point position is controlled to execute the action instruction.

[0013] According to some embodiments of the present invention, the first visual training module includes a first infrared sensor and a first light emitter;

[0014] The first infrared sensor is installed on the upper frame plate included in the barrier net; the horizontal sensing distance of the infrared sensor is consistent with the horizontal length of the upper frame plate, and the vertical sensing distance of the infrared sensor is 2-3m;

[0015] The first light-emitting bodies are evenly spaced along the length direction of the upper frame plate, and the first light-emitting bodies are red, yellow, blue, green, cyan, orange and purple light-emitting bodies that are spaced in sequence.

[0016] According to some embodiments of the present invention, the second visual training module includes a plurality of pressure sensors and a plurality of second light emitters;

[0017] The table top is divided into several sub-areas, each of which is provided with a pressure sensor and a second light-emitting body, and the light-emitting colors of the second light-emitting bodies in different sub-areas are different.

[0018] According to some embodiments of the present invention, the present invention further includes: a statistics module, configured to:

[0019] Counting the first light-emitting information of the first light-emitting body and the second light-emitting information of the corresponding second light-emitting body in a single training process;

[0020] The user's batting information is determined according to the first light-emitting information and the second light-emitting information, the batting weakness is determined according to the batting information, and the training information is determined according to the batting weakness.

[0021] According to some embodiments of the present invention, it further includes: an acquisition module, disposed on the blocking net, for acquiring an eye image of the user during the process according to the training information;

[0022] A recognition module, used to recognize eye images and determine the user's eye posture; the eye posture includes eye movement and rotation, eye stability and duration, eye closing state and duration, eye opening state and duration, eye blinking state and duration, and eye blinking frequency;

[0023] A matching module, used to query a preset eye posture-vision training program data table according to the user's eye posture, match the corresponding vision training program and transmit it to the control module;

[0024] The control module generates corresponding visual training control instructions and sends them to the first visual training module and / or the second visual training module.

[0025] According to some embodiments of the present invention, the identification module includes:

[0026] Pupil recognition module for:

[0027] Set the initial pupil binarization threshold;

[0028] Binarizing the eye image, performing a closing operation on the binarized eye image to connect the regions, and then removing the boundary regions to obtain a processed eye image;

[0029] Determine whether the boundaries of the connected areas in the processed eye image are elliptical and whether the size meets the initial pupil binarization threshold. If both conditions are met, take the center of the ellipse as the center of the pupil;

[0030] The first determination module is used to:

[0031] Generate eye movement trajectory based on pupil center position;

[0032] Normalize the eye movement trajectory to obtain a point sequence in a unified coordinate system;

[0033] The point sequence is smoothed by using a mean filter method to obtain a point sequence after removing noise caused by jitter, and the target eye movement trajectory is obtained;

[0034] Determine the user's eye gesture based on the target eye movement trajectory.

[0035] According to some embodiments of the present invention, the present invention further includes: a visual training detection module, which is used to:

[0036] During the visual training process, a detection image of the eye is obtained;

[0037] Analyze the detected image to determine the eye behavior; the eye behavior includes the dwelling of the gaze point, the turning point trajectory of the gaze point, the correction saccade and the nystagmus; the dwelling of the gaze point includes the order in which the gaze point dwells on each element; the gaze point is a point where the duration of the gaze is greater than a preset time; the elements include the opponent's serving action, the net crossing information and the landing point information of the table tennis ball; the turning point trajectory of the gaze point includes: two saccade trajectories are formed in any two consecutive eye movement movements, and when the angle between the two consecutive trajectories is greater than a preset angle, it is marked as the occurrence of the turning point trajectory; the correction saccade includes: when the user aims the eye gaze point at the interactive target, the 10% short distance is the correction saccade; the nystagmus includes: the pupil and the corneal limbus are displaced, and the nystagmus is generated when the eye movement reaches the target; the nystagmus is manifested as damped oscillation;

[0038] The preset eye behavior-training effect data table is queried according to the eye behavior, the corresponding training effect information is determined, and the training effect information is broadcast.

[0039] According to some embodiments of the present invention, the present invention further includes: a second determining module, configured to:

[0040] Query the target ball receiving position corresponding to the landing point of the table tennis ball on the table;

[0041] Detect the actual ball-catching position of the user when the table tennis ball lands on the table;

[0042] According to the target ball receiving position and the actual ball receiving position, the user's position adjustment information is determined as training information.

[0043] According to some embodiments of the present invention, a training method of a ball training device based on visual training includes:

[0044] The control module obtains the training information input by the user through the input module;

[0045] Control the working state of the first visual training module and / or the second visual training module according to the training information; the first visual training module is used to sense the position of the table tennis ball passing above the baffle and illuminate the table tennis ball; the second visual training module is used to sense the landing position of the table tennis ball on the table and illuminate the table tennis ball.

[0046] The present invention proposes a ball training device and method based on visual training, which is more comprehensive in visual training and can perform corresponding multi-level adjustments according to the user's usage needs to improve the effect of visual training. According to the user's training status, the correct training plan is automatically matched, which is of great help to improve the user's playing skills during ball training.

[0047] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 is a block diagram of a ball training device based on vision training according to one embodiment of the present invention;

[0051] Figure 2 The figure is a flow chart of a ball training method based on vision training according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0053] like Figure 1 As shown, the embodiment of the present invention provides a ball training device based on visual training, including a table, a barrier net and a tripod; a first visual training module is arranged at intervals on the upper end of the barrier net, which is used to sense the position of a table tennis ball passing above the barrier net and illuminate the table tennis ball;

[0054] The table top is evenly provided with second visual training modules for sensing the landing position of the table tennis ball on the table top and illuminating the table tennis ball;

[0055] It also includes a control module and an input module; the control module is connected to the input module, the first visual training module, and the second visual training module, respectively, and is used to:

[0056] Obtain training information input by the user through the input module;

[0057] The working state of the first vision training module and / or the second vision training module is controlled according to the training information.

[0058] The working principle of the above technical solution is as follows: the tabletop is a tabletop for table tennis, the tabletop is supported by a tripod, and the tabletop is divided into a first tabletop and a second tabletop based on a blocking net. The second visual training modules in the first tabletop and the second tabletop are symmetrically arranged. The first visual training modules are arranged at intervals on the upper end of the blocking net, which are used to sense the position of the table tennis ball passing above the blocking net and illuminate the table tennis ball, so as to facilitate observation of the state of the table tennis ball when passing the blocking net, and to conduct visual training. The second visual training modules are evenly arranged on the tabletop, which are used to sense the landing position of the table tennis ball on the tabletop and illuminate the table tennis ball, so as to facilitate observation of the state of the table tennis ball falling on the tabletop after passing the blocking net, and to conduct visual training. The input module can be implemented by physical key input, touch input, voice input, etc. The input training information includes primary training and secondary training. The primary training is that the first visual training module or the second visual training module is in a working state, and visual training is performed when the table tennis ball passes the blocking net or after the table tennis ball passes the blocking net. The secondary training is that the first visual training module and the second visual training module are in a working state at the same time, and visual training is performed on the table tennis ball in the entire radiation area of ​​the tabletop.

[0059] The beneficial effects of the above technical solution are: the visual training is more comprehensive, and corresponding multi-level adjustments are made according to the user's usage requirements to improve the effect of visual training.

[0060] According to some embodiments of the present invention, a table tennis ball detector is also provided at the upper end of the barrier net for monitoring the motion state of the table tennis ball when passing through the barrier net; the motion state includes speed, angle and rotation information;

[0061] The control module is connected to the table tennis ball detector and is used to:

[0062] Determine the estimated landing point of the table tennis ball according to the motion state of the table tennis ball when passing through the net;

[0063] When it is determined that the estimated landing point position belongs to the table area, the second visual training module corresponding to the estimated landing point position is controlled to execute the action instruction.

[0064] The working principle and beneficial effects of the above technical solution: a table tennis ball detector is also provided at the upper end of the retaining net, which is used to monitor the motion state of the table tennis ball when it passes through the retaining net; the motion state includes speed, angle and rotation information; the motion state is input into a pre-trained neural network model, and the estimated landing point of the table tennis ball is output; the neural network model is a model obtained by training through sample motion states and sample landing points, and adjusting the model parameters multiple times. When it is determined that the estimated landing point belongs to the table area, the second visual training module corresponding to the estimated landing point is controlled to execute the action instruction, and the second visual training module corresponding to the estimated landing point of the example is illuminated, so that the user can react in advance, adjust the position and action, and achieve the effect of table tennis training and hitting, and also carry out landing point visual training to improve the accuracy and comprehensiveness of visual training.

[0065] According to some embodiments of the present invention, the first visual training module includes a first infrared sensor and a first light emitter;

[0066] The first infrared sensor is installed on the upper frame plate included in the barrier net; the horizontal sensing distance of the infrared sensor is consistent with the horizontal length of the upper frame plate, and the vertical sensing distance of the infrared sensor is 2-3m;

[0067] The first light-emitting bodies are evenly spaced along the length direction of the upper frame plate, and the first light-emitting bodies are red, yellow, blue, green, cyan, orange and purple light-emitting bodies that are spaced in sequence.

[0068] The working principle and beneficial effects of the above technical solution are as follows: the infrared sensor emits infrared rays and receives infrared rays reflected by the ping-pong ball. When the ping-pong ball enters the detection range of the sensor, it reflects part of the infrared rays, which are received by the sensor and converted into electrical signals. By comparing the signal strength and time difference received by different sensors, the real-time position and speed of the ping-pong ball can be calculated. The coordinate values ​​of the ping-pong ball in the horizontal area and vertical direction are calculated using the spatial position area coordinate system and infrared sensing data. In particular, when the ping-pong ball passes the net, its position passing the net can be determined by analyzing the signal changes of adjacent sensors in the sensor array. Different first luminous bodies are set based on different past positions, and the ping-pong ball is illuminated by the first luminous body at the corresponding position, so that the user can accurately grasp the position of the ping-pong ball passing the net during training, and at the same time conduct corresponding visual training to increase interest.

[0069] According to some embodiments of the present invention, the second visual training module includes a plurality of pressure sensors and a plurality of second light emitters;

[0070] The table top is divided into several sub-areas, each of which is provided with a pressure sensor and a second light-emitting body, and the light-emitting colors of the second light-emitting bodies in different sub-areas are different.

[0071] The working principle and beneficial effects of the above technical solution are as follows: the table top is divided into several sub-areas, each sub-area is provided with a pressure sensor and a second light-emitting body, when the pressure sensor in the corresponding sub-area senses the pressure, the second light-emitting body in the same sub-area is controlled to illuminate, and the light-emitting colors of the second light-emitting bodies in different sub-areas are different, which is convenient for users to accurately grasp the landing position of the table tennis ball during ball training and conduct corresponding visual training.

[0072] According to some embodiments of the present invention, the present invention further includes: a statistics module, configured to:

[0073] Counting the first light-emitting information of the first light-emitting body and the second light-emitting information of the corresponding second light-emitting body in a single training process;

[0074] The user's batting information is determined according to the first light-emitting information and the second light-emitting information, the batting weakness is determined according to the batting information, and the training information is determined according to the batting weakness.

[0075] The working principle and beneficial effects of the above technical solution are as follows: the first light information of the first light emitter and the second light information of the corresponding second light emitter in a single training process are counted; the correspondence between the net crossing information and the landing point information is determined, and the user's batting information, including batting preferences, batting strengths, batting weaknesses, etc., is determined based on the first and second light information. The training information is determined based on the batting weaknesses, so that the corresponding targeted training information is generated for the batting weaknesses, so as to improve the user's batting level.

[0076] According to some embodiments of the present invention, it further includes: an acquisition module, disposed on the blocking net, for acquiring an eye image of the user during the process according to the training information;

[0077] A recognition module, used to recognize eye images and determine the user's eye posture; the eye posture includes eye movement and rotation, eye stability and duration, eye closing state and duration, eye opening state and duration, eye blinking state and duration, and eye blinking frequency;

[0078] A matching module, used to query a preset eye posture-vision training program data table according to the user's eye posture, match the corresponding vision training program and transmit it to the control module;

[0079] The control module generates corresponding visual training control instructions and sends them to the first visual training module and / or the second visual training module.

[0080] The working principle and beneficial effects of the above technical solution: an acquisition module is arranged on the blocking net, and is used to obtain the user's eye image during the process according to the training information; the recognition module is used to recognize the eye image and determine the user's eye posture; an eye posture-visual training program data table is preset according to the user's eye posture, and the corresponding visual training program is matched and transmitted to the control module, so as to facilitate timely adjustment of the visual training program, and make corresponding program adjustments according to the user's actual training situation, thereby improving the accuracy of visual training.

[0081] According to some embodiments of the present invention, the identification module includes:

[0082] Pupil recognition module for:

[0083] Set the initial pupil binarization threshold;

[0084] Binarizing the eye image, performing a closing operation on the binarized eye image to connect the regions, and then removing the boundary regions to obtain a processed eye image;

[0085] Determine whether the boundaries of the connected areas in the processed eye image are elliptical and whether the size meets the initial pupil binarization threshold. If both conditions are met, take the center of the ellipse as the center of the pupil;

[0086] The first determination module is used to:

[0087] Generate eye movement trajectory based on pupil center position;

[0088] Normalize the eye movement trajectory to obtain a point sequence in a unified coordinate system;

[0089] The point sequence is smoothed by using a mean filter method to obtain a point sequence after removing noise caused by jitter, and the target eye movement trajectory is obtained;

[0090] Determine the user's eye gesture based on the target eye movement trajectory.

[0091] The working principle of the above technical solution: In this embodiment, a gray value threshold is determined to divide the pixels in the eye image into two categories (foreground and background), and the pupil area is usually darker than the surrounding area. According to the overall brightness of the image and the contrast between the pupil and the background, a suitable gray value is manually or automatically selected as the threshold for binarization. The eye image is converted into an image containing only black and white colors to make it easier to identify the pupil area. Traverse each pixel in the image, and if its gray value is less than the set threshold, it is set to black (foreground), otherwise it is set to white (background). Use the closing operation in the morphological operation to connect adjacent black pixel areas (i.e., pupil areas), fill small holes and cracks, and make the pupil area more complete and continuous. By checking the distance between each black pixel area and the image boundary, remove those areas that are too close to the boundary, remove irrelevant areas that may be caused by image edges or noise, and only retain the internal area related to the pupil. Use a contour detection algorithm (such as Canny edge detection) to find the boundary of each area. Use an ellipse fitting algorithm (such as the least squares method) to try to fit the boundary into an ellipse. Check whether the shape parameters of the fitted ellipse (such as the ratio of the major and minor axes, area, etc.) meet the preset pupil characteristic conditions. For the ellipse that meets the conditions, directly use its geometric center as the center position of the pupil.

[0092] In this embodiment, the eye movement trajectory is generated by continuously capturing the position change of the pupil center. The position information is recorded in time sequence to form a series of points (x, y), where x and y represent the horizontal and vertical coordinates of the pupil center in the image coordinate system, respectively. These points are connected to form the eye movement trajectory. Since the scale of the eye movement trajectory may be different for different devices, different individuals and different experimental conditions, it is necessary to perform normalization processing to facilitate comparison and analysis under different conditions. Determine a reference range (such as the size of the image or the maximum range in which the pupil may move). Convert the coordinates of each point to a proportional coordinate relative to this reference range, that is, perform normalization processing. In this way, the eye movement trajectories under different conditions can be compared in a unified coordinate system. Due to factors such as device noise and small eye movements, there may be some jitter or noise in the eye movement trajectory, which will affect the accuracy of the analysis. Therefore, the trajectory needs to be smoothed. Use a mean filter (such as a sliding average filter) to process the point sequence. The mean filter calculates the average value of each point and its surrounding points, and uses this average value as the new coordinate of the point. The degree of smoothing can be controlled by adjusting the filter window size (i.e., the number of points involved in the average calculation). After smoothing, the jitter and noise in the trajectory will be effectively removed, resulting in a smoother target eye movement trajectory. The target eye movement trajectory is further analyzed and processed to extract its characteristic parameters (such as speed, acceleration, direction change, etc.). Based on these characteristic parameters, combined with the existing knowledge base or model, the user's eye posture is judged. For example, if the speed in the trajectory changes greatly and the direction changes suddenly, it may indicate that the user has made an eye saccade; if the trajectory remains relatively stable and the direction is consistent, it may indicate that the user is looking at a target.

[0093] The beneficial effects of the above technical solution are: realizing pupil recognition processing of eye images, generating eye movement trajectories based on the pupil center position, and performing normalization and smoothing processing to obtain the target eye movement trajectory, thereby accurately determining the user's eye posture.

[0094] According to some embodiments of the present invention, the present invention further includes: a visual training detection module, which is used to:

[0095] During the visual training process, a detection image of the eye is obtained;

[0096] Analyze the detected image to determine the eye behavior; the eye behavior includes the dwelling of the gaze point, the turning point trajectory of the gaze point, the correction saccade and the nystagmus; the dwelling of the gaze point includes the order in which the gaze point dwells on each element; the gaze point is a point where the duration of the gaze is greater than a preset time; the elements include the opponent's serving action, the net crossing information and the landing point information of the table tennis ball; the turning point trajectory of the gaze point includes: two saccade trajectories are formed in any two consecutive eye movement movements, and when the angle between the two consecutive trajectories is greater than a preset angle, it is marked as the occurrence of the turning point trajectory; the correction saccade includes: when the user aims the eye gaze point at the interactive target, the 10% short distance is the correction saccade; the nystagmus includes: the pupil and the corneal limbus are displaced, and the nystagmus is generated when the eye movement reaches the target; the nystagmus is manifested as damped oscillation;

[0097] The preset eye behavior-training effect data table is queried according to the eye behavior, the corresponding training effect information is determined, and the training effect information is broadcast.

[0098] The working principle and beneficial effects of the above technical solution: Analyze the detection image, determine the eye behavior, and the fixation point residence: the module will identify and track the fixation points of the eyes on various key elements (such as the opponent's serving action, the net crossing information of the table tennis ball, the landing point information, etc.), and record the order and duration of their residence. The inflection point trajectory of the fixation point: by continuously tracking the eye movement, the module will calculate the angle between two consecutive scanning trajectories. When the angle is greater than the preset angle, it will be marked as an inflection point trajectory, which usually indicates that the eyes are shifting focus quickly. Correction saccade: When the user aims at the interactive target through the eye fixation point, the module will calculate the distance the eye moves and compare it with the preset short-distance threshold. If the actual distance is less than 10% of the threshold, it is regarded as a correction saccade, which usually occurs when fine-tuning the fixation position. Nystagmus: The module monitors the displacement of the pupil and the corneal limbus, and identifies the damped oscillation phenomenon generated when the eye movement reaches the target, that is, nystagmus. According to the analyzed eye behavior, a preset data table is queried, which records the correspondence between different eye behaviors and training effects. By matching the eye behavior, the module can determine the current training effect information. The determined training effect information is broadcast to the user in the form of voice or text, so that they can understand their training status in time and make adjustments.

[0099] According to some embodiments of the present invention, the present invention further includes: a second determining module, configured to:

[0100] Query the target ball receiving position corresponding to the landing point of the table tennis ball on the table;

[0101] Detect the actual ball-catching position of the user when the table tennis ball lands on the table;

[0102] According to the target ball receiving position and the actual ball receiving position, the user's position adjustment information is determined as training information.

[0103] The working principle and beneficial effects of the above technical solution are as follows: query the target ball receiving position corresponding to the landing position of the table tennis ball on the table; record the corresponding relationship between the landing position and the target ball receiving position through a preset data table, and the target ball receiving position is a position with a high success rate of receiving the ball and a comfortable hitting position. Detect the actual ball receiving position of the user when the landing position of the table tennis ball on the table; determine the user's position adjustment information as training information based on the target ball receiving position and the actual ball receiving position. It is convenient for users to determine their own adjustment movement path, adjust the position during ball training, and improve the accuracy of hitting the ball.

[0104] In one embodiment, the second determination module detects the actual ball receiving position of the user when the table tennis ball lands on the table, including:

[0105] The second determination module includes a second infrared sensor, which is arranged on the blocking net. When determining the landing position of the table tennis ball on the table (that is, the pressure sensor senses the pressure), the second infrared sensor performs infrared sensing of the user to obtain infrared sensing information;

[0106] The distance between the user and the second infrared sensor is calculated based on the infrared sensing information when calculating the landing point of the table tennis ball on the table;

[0107]

[0108] Wherein, L is the distance information between the user and the second infrared sensor when the table tennis ball lands on the table; k1 is a correction coefficient selected according to the difference in human body temperature, and its value range is (0.9, 1.1); C is the correlation coefficient between the distance between the second infrared sensor and the user; U is the output signal strength of the second infrared sensor;

[0109]

[0110] Among them, W λ is the power of user radiation acquired by the second infrared sensor when the table tennis ball lands on the table; λ0 is the minimum operating wavelength of the second infrared sensor; λ1 is the maximum operating wavelength of the second infrared sensor; p is the sensitivity of the second infrared sensor; s is the infrared sensing area of ​​the second infrared sensor; z is the transmittance of the second infrared sensor;

[0111] The actual ball-catching position of the user when the table tennis ball lands on the table is determined according to the distance information between the user and the second infrared sensor.

[0112] The beneficial effect of the above technical solution is: based on the above algorithm, it is easy to accurately calculate the distance information between the user and the second infrared sensor, and then determine the actual ball catching position of the user when the table tennis ball lands on the table, so as to accurately determine the position adjustment information.

[0113] In one embodiment, the second determination module may also obtain image information of the environment where the user is located when the table tennis ball lands on the table, analyze the image information, and determine the actual ball receiving position of the user.

[0114] like Figure 2 As shown, according to some embodiments of the present invention, a training method of a ball training device based on visual training includes steps S1-S2:

[0115] S1, the control module obtains the training information input by the user through the input module;

[0116] S2. Control the working state of the first visual training module and / or the second visual training module according to the training information; the first visual training module is used to sense the position of the table tennis ball passing above the net and illuminate the table tennis ball; the second visual training module is used to sense the landing position of the table tennis ball on the table and illuminate the table tennis ball.

[0117] The beneficial effects of the above technical solution are: the visual training is more comprehensive, and corresponding multi-level adjustments are made according to the user's usage requirements to improve the effect of visual training.

[0118] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A ball training device based on visual training, characterized in that: It includes a table top, a barrier net and a tripod; a first visual training module is arranged at intervals on the upper end of the barrier net, which is used to sense the position of a table tennis ball passing above the barrier net and illuminate the table tennis ball; The table top is evenly provided with second visual training modules for sensing the landing position of the table tennis ball on the table top and illuminating the table tennis ball; It also includes a control module and an input module; the control module is connected to the input module, the first visual training module, and the second visual training module, respectively, and is used to: Obtain training information input by the user through the input module; The working state of the first vision training module and / or the second vision training module is controlled according to the training information.

2. The ball training device based on vision training as claimed in claim 1, characterized in that: A table tennis ball detector is also provided at the upper end of the barrier net for monitoring the motion state of the table tennis ball when it passes through the barrier net; the motion state includes speed, angle and rotation information; The control module is connected to the table tennis ball detector and is used to: Determine the estimated landing point of the table tennis ball according to the motion state of the table tennis ball when passing through the net; When it is determined that the estimated landing point position belongs to the table area, the second visual training module corresponding to the estimated landing point position is controlled to execute the action instruction.

3. The ball training device based on vision training as claimed in claim 1, characterized in that: The first visual training module includes a first infrared sensor and a first light emitter; The first infrared sensor is installed on the upper frame plate included in the barrier net; the horizontal sensing distance of the infrared sensor is consistent with the horizontal length of the upper frame plate, and the vertical sensing distance of the infrared sensor is 2-3m; The first light-emitting bodies are evenly spaced along the length direction of the upper frame plate, and the first light-emitting bodies are red, yellow, blue, green, cyan, orange and purple light-emitting bodies that are spaced in sequence.

4. The ball training device based on vision training as claimed in claim 3, characterized in that: The second visual training module includes a plurality of pressure sensors and a plurality of second light emitters; The table top is divided into several sub-areas, each of which is provided with a pressure sensor and a second light-emitting body, and the light-emitting colors of the second light-emitting bodies in different sub-areas are different.

5. The ball training device based on vision training as claimed in claim 4, characterized in that: Also includes: Statistics module for: Counting the first light-emitting information of the first light-emitting body and the second light-emitting information of the corresponding second light-emitting body in a single training process; The user's ball-hitting information is determined according to the first light-emitting information and the second light-emitting information, the ball-hitting weaknesses are determined according to the ball-hitting information, and the training information is determined according to the ball-hitting weaknesses.

6. The ball training device based on vision training as claimed in claim 5, characterized in that: Also includes: An acquisition module is arranged on the blocking net and is used to acquire the user's eye image in the process of performing training information; A recognition module, used to recognize eye images and determine the user's eye posture; The eye gestures include movement and rotation of the eyes, stable state and duration of the eyes, closed state and duration of the eyes, open state and duration of the eyes, blinking state and duration of the eyes, and frequency of blinking state of the eyes; A matching module, used to query a preset eye posture-vision training program data table according to the user's eye posture, match the corresponding vision training program and transmit it to the control module; The control module generates corresponding visual training control instructions and sends them to the first visual training module and / or the second visual training module.

7. The ball training device based on vision training as claimed in claim 6, characterized in that: The identification module comprises: Pupil recognition module for: Set the initial pupil binarization threshold; Binarizing the eye image, performing a closing operation on the binarized eye image to connect the regions, and then removing the boundary regions to obtain a processed eye image; Determine whether the boundaries of the connected areas in the processed eye image are elliptical and whether the size meets the initial pupil binarization threshold. If both conditions are met, take the center of the ellipse as the center of the pupil; The first determination module is used to: Generate eye movement trajectory based on pupil center position; Normalize the eye movement trajectory to obtain a point sequence in a unified coordinate system; The point sequence is smoothed by using a mean filter method to obtain a point sequence after removing noise caused by jitter, and the target eye movement trajectory is obtained; Determine the user's eye gesture based on the target eye movement trajectory.

8. The ball training device based on vision training as claimed in claim 1, characterized in that: Also includes: Visual training detection module for: During the visual training process, a detection image of the eye is obtained; Analyze the detected image to determine eye behavior; the eye behavior includes fixation point dwell, inflection point trajectory of fixation point, corrective saccade and nystagmus; the fixation point dwell includes the order in which the fixation point dwells on each element; the fixation point is a point whose duration of fixation is greater than a preset time; the elements include the opponent's serving action, table tennis ball passing the net information, and landing point information; The inflection point trajectory of the gaze point includes: two segments of scanning trajectories are formed in any two consecutive eye movements, and when the angle between the two consecutive trajectories is greater than a preset angle, it is marked as an inflection point trajectory; the correction saccade includes: when the user aligns the eye gaze point with the interactive target, the 10% short distance is the correction saccade; the nystagmus includes: the pupil and the corneal limbus are displaced, and the nystagmus is generated when the eye movement reaches the target; the nystagmus is manifested as damped oscillation; The preset eye behavior-training effect data table is queried according to the eye behavior, the corresponding training effect information is determined, and the training effect information is broadcast.

9. The ball training device based on vision training as claimed in claim 1, characterized in that: Also includes: The second determination module is used for: Query the target ball receiving position corresponding to the landing point of the table tennis ball on the table; Detect the actual ball-catching position of the user when the table tennis ball lands on the table; According to the target ball receiving position and the actual ball receiving position, the user's position adjustment information is determined as training information.

10. The training method of the ball training device based on vision training according to any one of claims 1 to 9, characterized in that: include: The control module obtains the training information input by the user through the input module; Controlling the working state of the first vision training module and / or the second vision training module according to the training information; The first visual training module is used to sense the position of the table tennis ball passing above the net and illuminate the table tennis ball; The second visual training module is used to sense the landing point of the ping-pong ball on the table and illuminate the ping-pong ball.

Images