CN114612522B - Table tennis sport parameter detection method and device and table tennis training auxiliary system - Google Patents
Table tennis sport parameter detection method and device and table tennis training auxiliary system Download PDFInfo
- Publication number
- CN114612522B CN114612522B CN202210498105.9A CN202210498105A CN114612522B CN 114612522 B CN114612522 B CN 114612522B CN 202210498105 A CN202210498105 A CN 202210498105A CN 114612522 B CN114612522 B CN 114612522B
- Authority
- CN
- China
- Prior art keywords
- table tennis
- image
- dimensional coordinate
- ball
- color
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012549 training Methods 0.000 title claims abstract description 50
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 20
- 239000003086 colorant Substances 0.000 claims abstract description 13
- 230000001133 acceleration Effects 0.000 claims description 21
- 238000010304 firing Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 241000288673 Chiroptera Species 0.000 claims description 2
- 230000006698 induction Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 14
- 230000009471 action Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000009527 percussion Methods 0.000 description 5
- 230000008485 antagonism Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B69/00—Training appliances or apparatus for special sports
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
- G01P3/36—Devices characterised by the use of optical means, e.g. using infrared, visible, or ultraviolet light
- G01P3/38—Devices characterised by the use of optical means, e.g. using infrared, visible, or ultraviolet light using photographic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2102/00—Application of clubs, bats, rackets or the like to the sporting activity ; particular sports involving the use of balls and clubs, bats, rackets, or the like
- A63B2102/16—Table tennis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30221—Sports video; Sports image
- G06T2207/30224—Ball; Puck
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Abstract
The application relates to a table tennis motion parameter detection method, a table tennis motion parameter detection device and a table tennis training auxiliary system, wherein the method comprises the following steps: shooting a table tennis table top image of a table tennis in the motion process through a high-speed camera and identifying the table tennis image; identifying a monochromatic color spot image arranged on the surface of the table tennis from the table tennis image, and determining the color of the monochromatic color spot and the distribution position of the monochromatic color spot relative to the table tennis image; respectively calculating a first three-dimensional coordinate value of the monochromatic color spots on a ping-pong three-dimensional coordinate system according to the distribution positions of the monochromatic color spot images of the colors, and associating the first three-dimensional coordinate value on the frame of ping-pong table image; and acquiring a plurality of frames of adjacent table tennis table surface images, and calculating the rotating direction and the rotating angular velocity of the table tennis according to the associated color and the first three-dimensional coordinate value of each frame of table tennis table surface image. According to the technical scheme, the image processing data volume can be reduced, the using number of the high-speed cameras is reduced, the frame rate requirement of the high-speed cameras is lowered, and the detection efficiency is improved.
Description
Technical Field
The application relates to the technical field of sports science and technology, in particular to a table tennis motion parameter detection method and device and a table tennis training auxiliary system.
Background
In the process of table tennis training assistance, table tennis training assistance systems are used for accurately detecting table tennis motion parameters, completing calculation in a very short time, accurately identifying, positioning and tracking the flight path of table tennis moving at a high speed and the like, and the system has important significance for guiding athletes to train; the table tennis motion parameters comprise a motion track, a motion speed and a rotation angular velocity, particularly the rapid rotation motion of the table tennis generated in the motion process, according to statistics, the rotation speed of the rotary ball played by a professional table tennis player can reach more than 50 revolutions per second, and under such a high rotation speed, the small motion change of the table tennis between adjacent image frames is captured in real time through a high-speed camera to calculate the rotation angular velocity of the table tennis.
Currently, there is a technology of recognizing a rotation direction by photographing and recognizing a mark (such as a ball marker) of a table tennis ball in combination with an included angle of a plane coordinate system, and then calculating a rotation angular velocity of the table tennis ball according to an angle difference and a time interval. In addition, because the mark of the table tennis cannot be shot when the shadow area of the high-speed camera rotates, the situation that the detection cannot be carried out can be caused, and in order to solve the problem, a common method is to simultaneously use at least two high-speed cameras to carry out image acquisition, so that the mark on the table tennis is ensured to be always in the visual field of the high-speed cameras.
Because the surface of the table tennis ball is circular, in the picture shot by the high-speed camera, the rotating path can be accurately detected only when the distance between the detection points of the front frame image and the rear frame image is short, so that the high-speed camera with a higher frame rate is required to be used, a large amount of image data needs to be processed, the calculation is quite complex, the requirements on the camera equipment and the image data processing equipment are higher, and the detection efficiency is influenced; moreover, in order to avoid the influence of the shadow area, more than two cameras need to be equipped, so that the equipment cost of the high-speed camera is increased, the auxiliary system equipment is difficult to popularize and apply in sports training, and the training auxiliary effect of the table tennis training auxiliary system is influenced.
Disclosure of Invention
In view of one of the above technical drawbacks, the present application provides a table tennis motion parameter detection method, device and table tennis training auxiliary system, which can reduce the image data processing amount, reduce the number of high-speed cameras used, and improve the detection efficiency.
In a first aspect:
the application provides a table tennis motion parameter detection method, which comprises the following steps:
shooting a table tennis table top image of a table tennis in the motion process by a high-speed camera arranged at a set height above the table tennis table, and analyzing each image frame of the table tennis table top image to identify the table tennis image;
identifying a monochromatic color spot image arranged on the surface of a table tennis from the table tennis image, and determining the color of the monochromatic color spot and the distribution position of the monochromatic color spot relative to the table tennis image; the table tennis bat comprises a table tennis ball, a table tennis ball cover, a table tennis ball, a color spot and a color spot, wherein the monochromatic color spot is arranged on the surface of the table tennis ball and is positioned at the vertex position of a built-in regular tetrahedron of the table tennis ball;
respectively calculating a first three-dimensional coordinate value of the monochromatic color spot on a ping-pong three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color, and associating the corresponding color and the first three-dimensional coordinate value thereof on the frame of ping-pong table image; the table tennis three-dimensional coordinate system is a three-dimensional coordinate system taking a table tennis center as an origin;
and acquiring a plurality of frames of adjacent table tennis table surface images, and calculating the rotating direction and the rotating angular velocity of the table tennis according to the associated color and the first three-dimensional coordinate value of each frame of table tennis table surface image.
In a second aspect:
the application provides a table tennis motion parameter detection device, includes:
the image acquisition module is used for shooting a table tennis table surface image of a table tennis in the motion process through a high-speed camera arranged at a set height above the table tennis table, and analyzing each image frame of the table tennis table surface image to identify the table tennis image;
the position determining module is used for identifying a monochromatic color spot image arranged on the surface of the table tennis from the table tennis image and determining the color of the monochromatic color spot and the distribution position of the monochromatic color spot relative to the table tennis image; the table tennis bat comprises a table tennis ball, a table tennis ball cover, a table tennis ball, a color spot and a color spot, wherein the monochromatic color spot is arranged on the surface of the table tennis ball and is positioned at the vertex position of a built-in regular tetrahedron of the table tennis ball;
the coordinate correlation module is used for calculating a first three-dimensional coordinate value of the monochromatic color spot on a ping-pong three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color respectively, and correlating the corresponding color and the first three-dimensional coordinate value thereof on the frame of ping-pong table image; the table tennis three-dimensional coordinate system is a three-dimensional coordinate system taking a table tennis center as an origin;
and the parameter calculation module is used for acquiring a plurality of frames of adjacent ping-pong table top images and calculating the rotating direction and the rotating angular velocity of the ping-pong according to the associated color and the first three-dimensional coordinate value of each frame of ping-pong table top image.
In a third aspect:
the application provides a table tennis training auxiliary system, includes: the system comprises high-speed cameras, posture cameras, sensing devices and a background server, wherein the high-speed cameras and the posture cameras are distributed above table tennis table tops;
the high-speed camera, the sensing device, the attitude camera and the contact sensing panel are connected to the background server through wireless network equipment;
the sensing device includes: the table tennis bat comprises an acceleration sensor, a touch induction layer stuck on a rubber of the table tennis bat, an MCU and a wireless communication module; the acceleration sensor is connected to the MCU, and the MCU is connected to the background server through the wireless communication module;
the posture camera is used for shooting real-time images of players, acquiring motion posture data of the players according to the real-time images and sending the motion posture data to the background server;
the background server is configured to execute the steps of the table tennis motion parameter detection method, and execute the following steps: receiving acceleration data of the table tennis bat detected by the acceleration sensor, receiving firing position data of a table tennis ball contacting the bat surface detected by the touch sensing layer, and receiving movement posture data of a player; and performing data analysis according to the rotation direction and the rotation angular velocity of the table tennis, the acceleration data of the table tennis bat, the firing position data and the motion posture data of the player, and generating auxiliary training reference information according to the analysis result.
The table tennis motion parameter detection method, the table tennis motion parameter detection device and the table tennis training auxiliary system are characterized in that firstly, monochromatic color spots are arranged on the surface of a table tennis ball positioned at the vertex position of a regular tetrahedron arranged in the table tennis ball, in the detection process, a high-speed camera above the table tennis table is used for shooting a table tennis table top image and identifying the table tennis ball image, then the monochromatic color spot image is identified from the table tennis ball image, and the color of the monochromatic color spots and the distribution position of the monochromatic color spots relative to the table tennis ball image are detected; and finally, calculating the three-dimensional coordinate value of the monochromatic color spot on a ping-pong three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color, associating the three-dimensional coordinate value with a ping-pong desktop image, and finally calculating the rotation direction and the rotation angular velocity of the ping-pong through a plurality of adjacent frames of ping-pong desktop images according to the associated color and the three-dimensional coordinate value of each frame of ping-pong desktop image. According to the technical scheme, the single-color spots are arranged on the surface of the table tennis ball at the vertex position of the built-in regular tetrahedron of the table tennis ball, so that on one hand, image identification processing is facilitated through the single-color spots, and accordingly, the image processing data volume can be reduced, on the other hand, the single-color spots are arranged at the vertex position of the built-in regular tetrahedron of the table tennis ball, and the three-dimensional coordinate positions of other single-color spots can be determined through at least one single-color spot; therefore, no matter how the table tennis rotates, at least one monochromatic color spot can be shot by the high-speed camera, and even if part of the monochromatic color spot is in a shadow area of the high-speed camera, each frame of table tennis image can ensure that the monochromatic color spot is detected, so that the using number of the high-speed cameras is reduced; by decomposing the one-dimensional tag information recognition process into a multi-dimensional tag information recognition process and converting a short-time recognition process into a long-time recognition process, the frame rate requirement for a high-speed camera can be greatly reduced, and the detection efficiency can be improved.
Furthermore, on the basis of detecting the rotating direction and the rotating angular velocity of the table tennis based on a single high-speed camera, the motion track of the table tennis can be detected, data analysis is carried out by utilizing acceleration data, percussion position data, motion posture data and the like, and auxiliary training reference information is generated according to the analysis result.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a table tennis motion parameter detection method according to an embodiment;
FIG. 2 is a schematic diagram of an exemplary high speed camera mounting location;
FIG. 3 is a schematic view of an exemplary table tennis ball surface with monochromatic color patches;
FIG. 4 is a schematic illustration of an exemplary location of a distribution for identifying a solid color patch;
FIG. 5 is a schematic diagram of an exemplary table tennis three-dimensional coordinate system;
FIG. 6 is a schematic diagram of an exemplary distribution of a table tennis image in a table tennis table image;
FIG. 7 is a schematic view of an exemplary ping-pong ball image projected in a ping-pong table image;
FIG. 8 is a schematic structural diagram of a table tennis motion parameter detecting device according to an embodiment;
fig. 9 is a schematic structural diagram of a table tennis training aid system of an embodiment.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, or operations, but do not preclude the presence or addition of one or more other features, integers, steps, operations, or groups thereof.
The technical scheme of the application can be applied to a table tennis training auxiliary system to assist players in training; according to the table tennis motion parameter detection method and device, the single high-speed camera is utilized, the parameter detection efficiency is improved, the use of the high-speed camera is reduced, and the table tennis rotation direction and the table tennis rotation angular velocity can be accurately detected at a relatively low frame rate. So that the auxiliary system equipment can be widely popularized and applied in the table tennis training.
Referring to fig. 1, fig. 1 is a flowchart of a table tennis motion parameter detection method according to an embodiment, and includes the following steps:
s10, shooting a table tennis table surface image of a table tennis in the motion process through a high-speed camera arranged at a set height above the table tennis table, and analyzing each image frame of the table tennis table surface image to identify the table tennis image.
Referring to fig. 2, fig. 2 is a schematic diagram illustrating an exemplary installation position of a high-speed camera, the high-speed camera is disposed at a position with a set height H above a central position of a central net of a table tennis table and faces a table tennis table, and the high-speed camera captures an image of the table tennis table during a movement of a table tennis; generally, the image of the table tennis table top is differentiated from the reference image of the table tennis table top when the table tennis table top is not used, the table tennis ball can form a circular color area, and the image of the table tennis ball can be identified after relatively simple picture data processing by identifying the color value of pixels and combining the circular shape of the table tennis ball.
S20, identifying a monochromatic color spot image arranged on the surface of the table tennis from the table tennis image, and determining the color of the monochromatic color spot and the distribution position of the monochromatic color spot relative to the table tennis image; the single-color spots are arranged on the surface of the table tennis ball and are positioned at the vertex positions of the built-in regular tetrahedrons of the table tennis ball.
In an embodiment, step S20 may specifically include the following:
s201, judging the pixel color value in the table tennis image range according to a preset color range threshold value of each color, and determining each single-color mottle image on the table tennis image and the corresponding color of the single-color mottle image.
S202, acquiring a pixel area where a monochromatic color spot image of each color is located, and determining the center position of the pixel area as the center position of the monochromatic color spot.
S203, calculating relative position parameters of the center position and the center of the table tennis image; the relative position parameter is a two-dimensional coordinate value of the center position on a table tennis section coordinate system with the table tennis image center as an origin.
And S204, obtaining the distribution position of the monochromatic color spot image relative to the ping-pong ball image according to the relative position parameter.
Referring to fig. 3, fig. 3 is a schematic diagram of an example of a table tennis ball surface with monochromatic color spots, since the table tennis ball is monochromatic, such as white, by identifying the table tennis ball image S, monochromatic color spot images S1, S2, S3, S4 on the table tennis ball surface are further identified; according to the set color of the monochromatic color spots, the color range threshold value of each color can be preset, so that each monochromatic color spot image on the table tennis image and the corresponding color of the image can be quickly identified.
Specifically, first, monochromatic color spots s1, s2, s3, s4 are set on the surface of the table tennis ball at the positions of vertices m1, m2, m3, m4 of the regular tetrahedron embedded in the table tennis ball, and the monochromatic color spots correspond to the colors c1, c2, c3, c4, for example, four colors such as red, blue, green, black, and the like. In the identification process, the monochromatic color spot images S1, S2, S3 and S4 marked on the table tennis image S are respectively identified on the table tennis surface, the colors corresponding to the monochromatic color spots S1, S2, S3 and S4 are obtained, and by taking the round monochromatic color spots as an example, the round monochromatic area is identified and the monochromatic color is combined, so that the monochromatic color spot image can be rapidly identified.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating an exemplary distribution position of monochromatic spots for identification, which uses the central pixel positions o1, o2, o3, o4 of the monochromatic spots as reference points to determine the distribution position of the central pixel positions of the monochromatic spots relative to the table tennis image S, and determine the position parameters of the central pixel positions o1, o2, o3, o4 relative to the central point of the table tennis image S; as shown in fig. 4, if the monochromatic color spots s1, s2, s3 are identified and the central pixel positions o1, o2, o3 of the three monochromatic color spot images on the ping-pong ball image are obtained, the center o of the ping-pong ball image is used’And establishing a table tennis section coordinate system for the origin point, thereby determining two-dimensional coordinate values on the table tennis section coordinate system of the central pixel positions o1, o2 and o3 of the monochromatic color spot image.
In the technical scheme of the embodiment, firstly, the single-color spot images and the corresponding colors on the table tennis image are quickly identified; then calculating the distribution position of the monochromatic color spot image relative to the ping-pong ball image; therefore, the two-dimensional coordinates of the central pixel position relative to the table tennis image tangent plane coordinate system can be converted into the table tennis three-dimensional coordinate system in the subsequent process.
S30, calculating a first three-dimensional coordinate value of the monochromatic color spot on a ping-pong three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color, and associating the corresponding color and the first three-dimensional coordinate value thereof on the frame of ping-pong table image; the table tennis three-dimensional coordinate system is a three-dimensional coordinate system with a table tennis center as an origin.
In an embodiment, step S30 may specifically include the following:
s301, constructing a three-dimensional coordinate system of the table tennis with the center of the table tennis as an origin; the xy-axis plane of the three-dimensional coordinate system of the table tennis is parallel to the table-tennis table-board plane, and the z-axis is vertical to the table-tennis center.
S302, determining a shooting included angle between a high-speed camera and a core of the table tennis ball according to the distribution position of the table tennis ball image in the table tennis ball surface image and the set height.
S303, calculating a first three-dimensional coordinate value of the monochromatic color spot on the table tennis three-dimensional coordinate system according to the camera angle and the two-dimensional coordinate value.
As an embodiment, the high-speed camera may be disposed at a set height position right above the center of the net in the table tennis table; accordingly, the step of calculating the image capturing angle in step S302 may include the following steps:
(1) And acquiring the center position of the table tennis image and the midpoint position of the middle net of the table tennis table top image.
(2) And determining a first distance between the center of the table tennis ball and the midpoint of the middle net of the table tennis table top according to the center position of the table tennis image and the midpoint of the middle net of the table tennis table top image.
(3) And calculating a camera angle between the high-speed camera and the center of the table tennis ball according to the first distance and the set height H.
S304, recording the identified color and the first three-dimensional coordinate value of the monochromatic color spot on the ping-pong table image in a related manner.
Referring to fig. 5, fig. 5 is a schematic diagram of an exemplary table tennis three-dimensional coordinate system; the figure is a schematic diagram in a side direction, a three-dimensional coordinate system of a ping-pong ball is 0-xyz, referring to fig. 6, fig. 6 is a schematic diagram of a distribution position of an exemplary ping-pong ball image in a ping-pong table top image, a high-speed camera is arranged right above the center of a net in the ping-pong table, a picture frame as shown in fig. 6 is obtained after a shot ping-pong table top image is differentiated from the ping-pong table top reference image, wherein the distribution position of the ping-pong ball image in the ping-pong table top image can obtain a shooting included angle β according to a connection line; referring to fig. 7, fig. 7 is a schematic diagram of an exemplary projection of a ping-pong ball image onto a ping-pong table image, wherein a solid line ping-pong ball S is a real ping-pong ball position and a dashed line ping-pong ball S is a broken line ping-pong ball position’Is the real table tennis position identified on the image, the dotted table tennis S’The first distance d1 from the center position of the table tennis table to the middle point of the middle net of the table tennis table top, and the camera angle beta value can be calculated by combining the height H. As can be seen from fig. 5, an included angle β exists between the table tennis image tangent plane coordinate system and the 0-xyz table tennis three-dimensional coordinate system, and then the two-dimensional coordinate value of the table tennis image tangent plane coordinate system can be converted into the first three-dimensional coordinate value of the table tennis three-dimensional coordinate system according to the included angle β.
According to the technical scheme of the embodiment, the three-dimensional coordinate of the surface of the table tennis ball can be positioned through the monochromatic color spot image by converting the two-dimensional coordinate of the table tennis image tangent plane coordinate system into the three-dimensional coordinate system of the table tennis ball; therefore, the spatial position of the ping-pong ball moved to the surface at the current moment can be accurately recorded.
S40, a plurality of frames of adjacent table tennis table surface images are obtained, and the rotating direction and the rotating angular speed of the table tennis are calculated according to the associated color and the first three-dimensional coordinate value of each frame of table tennis table surface image.
Specifically, after the implementation space position of the monochromatic color spots on the surface of the table tennis is determined through the steps, continuous multiple frames of table tennis table top images can be selected to analyze and calculate the rotation direction and the rotation angular velocity of the table tennis, and because the monochromatic color spots are arranged on the surface of the table tennis at the vertex position of the built-in regular tetrahedron of the table tennis, at least one monochromatic color spot can be shot by a high-speed camera regardless of the rotation of the table tennis, namely, each frame of table tennis table top image can be recorded with the rotation of the table tennis, even if part of the monochromatic color spots are in the shadow area of the high-speed camera, the rotation direction and the rotation angular velocity of the table tennis around the origin can be calculated by utilizing the monochromatic color spots detected on each frame of table tennis images and combining the frame rate of the table top images.
In an embodiment, step S40 may specifically include the following:
s401, selecting a plurality of continuous frames of table tennis table top images as image frames to be analyzed; wherein, the image frame to be analyzed at least comprises a plurality of image frames with the same color appearing repeatedly;
s402, identifying image frames contained in various colors from the image frames to be analyzed respectively, and forming image frame groups to be analyzed with the colors as types;
s403, aiming at different color types, calculating the rotation direction of the ping-pong ball around the origin and the rotation angular velocity thereof by using the first three-dimensional coordinate value associated with the ping-pong ball desktop image in the image frame group to be analyzed and combining the frame rate of the ping-pong ball desktop image; specifically, according to the rotation principle of the sphere surface, the three-dimensional coordinate value change between two points and the movement time (frame interval) thereof can be calculated.
S404, averaging is carried out according to the rotating angular velocities calculated by the image frame groups to be analyzed, and the real-time rotating angular velocity of the table tennis is obtained.
According to the scheme of the embodiment, the image frames to be analyzed are grouped according to colors, then the grouped data of each color type can be used for calculating a rotating direction and a rotating angular velocity thereof, and averaging is carried out on the rotating angular velocity, so that the rotating angular velocity detection accuracy can be further improved.
According to the technical scheme of the embodiment of the application, monochromatic color spots are beneficial to image identification processing, so that the data volume of image processing can be reduced, the monochromatic color spots are arranged at the vertex positions of the built-in regular tetrahedrons of the table tennis, the three-dimensional coordinate positions of other monochromatic color spots can be determined through at least one monochromatic color spot, accurate detection is realized through a single high-speed camera, and the using number of the high-speed cameras is reduced; meanwhile, the calculation is carried out through the average data of a plurality of color types, the one-dimensional marking information identification process is decomposed into the multi-dimensional marking information identification process, the identification can be carried out without a shot image with a high frame rate, the identification process in a short time is converted into a long-time identification process, the frame rate requirement on a high-speed camera is greatly reduced, and the detection efficiency is improved; taking the rotating speed of the rotating ball as an example, 50 revolutions per second, the frame rate of the high-speed camera is 200fps, and accurate detection can be realized.
In order to make the technical solution of the present application clearer, more embodiments are set forth below.
In one embodiment, the table tennis ball movement parameter detection method of the present application may further include S50, a step of generating a table tennis ball movement trajectory; the step may specifically include the following:
s501, constructing a desktop three-dimensional coordinate system by taking the middle point position of the middle net as an origin; the XY axis plane of the three-dimensional coordinate system of the table top is parallel to the table tennis table top, and the Z axis is vertical to the table tennis table top plane;
s502, acquiring a first included angle between a connecting line of a ping-pong ball center of the ping-pong ball image and a midpoint position of a middle net and the ping-pong ball desktop middle net according to the ping-pong ball desktop image;
s503, acquiring the area of a pixel area of the ping-pong image in the ping-pong table image;
s504, calculating a second distance between the center of the table tennis ball and the high-speed camera according to a functional relation between the area of a pixel region of the table tennis image and the shooting distance;
s505, calculating a first height value of the table tennis center relative to a table tennis table top and a projection distance relative to a middle point position of a middle net according to the second distance, the camera angle and a set height;
s506, calculating a second three-dimensional coordinate value of the center of the table tennis ball on the table top three-dimensional coordinate system according to the projection distance and the first included angle;
and S507, fitting according to second three-dimensional coordinate values obtained by each frame of table tennis table top image to obtain the motion trail of the table tennis.
According to the technical scheme of the embodiment, a desktop three-dimensional coordinate system is constructed by taking the middle net midpoint position as an origin to detect, an XY axis plane of the desktop three-dimensional coordinate system is parallel to a table tennis desktop, a Z axis is perpendicular to the table tennis desktop plane, a first included angle alpha between a connecting line of a table tennis center of a table tennis image and the middle net midpoint position and a table tennis desktop middle net is calculated, a functional relation between a pixel area and a shooting distance is utilized, an actual second distance d2 between the table tennis center and a high-speed camera can be calculated through the pixel area of the table tennis image, and a first height value of the table tennis center relative to the table tennis desktop and a projection distance relative to the middle net midpoint position are calculated by utilizing the second distance d2, the shooting included angle beta and the set height H; calculating a second three-dimensional coordinate value of the center of the table tennis on the three-dimensional coordinate system of the table tennis table according to the projection distance and the first included angle alpha; therefore, the motion trail of the table tennis is detected, and the motion trail of the table tennis can be obtained by fitting the three-dimensional coordinate values obtained by the images of the frames.
By integrating the technical scheme of the embodiment, the rotation direction and the rotation angular velocity of the table tennis ball can be detected based on the single high-speed camera, the motion track of the table tennis ball can be further detected, the amount of image data to be processed is small in the detection process, the rotation direction and the rotation angular velocity of the table tennis ball can be accurately detected by the high-speed camera under the condition of a low frame rate, the detection cost is reduced, and the detection efficiency is improved.
The following describes an embodiment of the table tennis ball movement parameter detection device.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a table tennis motion parameter detecting device according to an embodiment, including:
the image acquisition module 10 is used for shooting a table tennis table top image of a table tennis in the motion process through a high-speed camera arranged at a set height above the table tennis table, and analyzing each image frame of the table tennis table top image to identify the table tennis image;
the position determining module 20 is used for identifying a monochromatic color spot image arranged on the surface of the table tennis from the table tennis image and determining the color of the monochromatic color spot and the distribution position of the monochromatic color spot relative to the table tennis image; the table tennis bat comprises a table tennis ball body, a table tennis ball cover, a color spot and a color filter, wherein the monochromatic color spot is arranged on the surface of the table tennis ball and is positioned at the vertex position of a built-in regular tetrahedron of the table tennis ball;
the coordinate association module 30 is configured to calculate a first three-dimensional coordinate value of the monochromatic color spot on the ping-pong three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color, and associate a corresponding color and the first three-dimensional coordinate value thereof on the frame of ping-pong table image; the table tennis three-dimensional coordinate system is a three-dimensional coordinate system taking a table tennis center as an origin;
and the parameter calculation module 40 is configured to obtain a plurality of adjacent frames of ping-pong table images, and calculate a rotation direction and a rotation angular velocity of the ping-pong according to the color associated with each frame of ping-pong table image and the first three-dimensional coordinate value thereof.
The table tennis motion parameter detection device of this embodiment may execute the table tennis motion parameter detection method provided in the embodiments of the present disclosure, and the implementation principles thereof are similar, the actions performed by the modules in the table tennis motion parameter detection device in each embodiment of the present disclosure correspond to the steps in the table tennis motion parameter detection method in each embodiment of the present disclosure, and for the detailed functional description of each module of the table tennis motion parameter detection device, reference may be specifically made to the description in the corresponding table tennis motion parameter detection method shown in the foregoing, and details are not repeated here.
An embodiment of a table tennis training aid system is set forth below.
Referring to fig. 9, fig. 9 is a schematic structural diagram of a table tennis training assisting system according to an embodiment, including: the high-speed cameras, the posture cameras, the sensing devices and the background server are distributed above the table tennis table tops, and the sensing devices are arranged in the table tennis bats.
The high-speed camera, the sensing device, the attitude camera and the contact sensing panel are connected to the background server through wireless network equipment (such as WIFI). The sensing device includes: the table tennis bat comprises an acceleration sensor, a touch sensing layer adhered to a rubber of the table tennis bat, an MCU and a wireless communication module; the acceleration sensor is connected to the MCU, and the MCU is connected to the background server through the wireless communication module. The gesture camera is used for shooting real-time images of the sportsman and acquiring motion gesture data of the sportsman according to the real-time images and sending the motion gesture data to the background server.
In addition, the background server can be accessed through wireless network equipment, such as a computer end Web, or through an App mode of a smart phone.
The background server is configured to execute the steps of the table tennis motion parameter detection method of any one of the above embodiments, and execute the following steps: receiving acceleration data of the table tennis bat detected by the acceleration sensor, receiving firing position data of a table tennis ball contacting the bat surface detected by the touch sensing layer, and receiving movement posture data of players; and performing data analysis according to the rotation direction and the rotation angular velocity of the table tennis, the acceleration data of the table tennis bat, the firing position data and the motion posture data of the player, and generating auxiliary training reference information according to the analysis result.
According to the technical scheme of the embodiment, the rotation direction and the rotation angular velocity of the table tennis are detected based on the single high-speed camera, the motion track of the table tennis can be further detected, meanwhile, data analysis is carried out by utilizing acceleration data, firing position data, motion posture data and the like, and auxiliary training reference information is generated according to the analysis result, so that a player can train according to the guidance of the auxiliary training reference information during training, and relevant data are visually displayed during training.
In one embodiment, the table tennis training assistance system of the present application, the background server is further configured to perform the following steps: and carrying out statistical analysis on the rotation direction and rotation angular velocity of the table tennis, the motion track of the table tennis, the acceleration data of the table tennis bat swung by the player, the triggering position data of the table tennis bat face and the motion posture data of the player, which are acquired in the auxiliary training of any player, outputting the evaluation index score of the player, and outputting correction auxiliary information according to the evaluation score.
According to the technical scheme of the embodiment, the table tennis training auxiliary system can continuously perform statistical analysis on the relevant detection data of any player, can score the data by utilizing a predetermined model, outputs the evaluation index score of the player, can output correction auxiliary information according to the evaluation score, and can correct own percussion action and various posture actions according to the correction auxiliary information.
In one embodiment, the table tennis training assistance system of the present application, the background server is further configured to perform the following steps: performing model training according to the rotating direction and the rotating angular velocity of the table tennis ball, the motion trail of the table tennis ball, the acceleration data of the table tennis bat swung by the player, the firing position data of the table tennis bat surface and the motion posture data of the player, which are acquired in the auxiliary training of each player, and generating an confrontation training model of the player; and carrying out simulated confrontation according to the confrontation training models of different players, and outputting auxiliary training reference information according to the simulated confrontation.
The technical scheme of above-mentioned embodiment, table tennis training auxiliary system can utilize sportsman's relevant detected data to train sportsman's antagonism training model, then utilize different sportsman's antagonism training models to simulate and resist, can analyze out the interact relation between sportsman's percussion action and the gesture action through simulating and resist, can be according to the supplementary training reference information of simulation percussion output to supplementary sportsman constantly improves percussion action and gesture action.
In one embodiment, the table tennis training assistance system of the present application, the background server is further configured to perform the following steps: based on the utilization of a 3D virtual animation technology, virtual batting animation of a player is generated according to the motion attitude data, and virtual flying animation of the table tennis is generated according to the motion track; and generating live animation videos with a plurality of view angles by using the virtual ball hitting animation and the virtual flying animation, and performing virtual live broadcast by using the live animation videos.
The technical scheme of above-mentioned embodiment utilizes the virtual animation technique of 3D, combines the relevant data generation virtual animation of the sportsman who detects to can carry out convenient virtual live, on the one hand, can reduce the data bulk of live video in real time through virtual animation, the picture content's of can being convenient for simultaneously save, other sportsman of being convenient for watch in playback, reduced live equipment cost and live broadcast content's storage cost.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (9)
1. A table tennis motion parameter detection method is characterized by comprising the following steps:
shooting a table tennis table top image of a table tennis in the motion process by a high-speed camera arranged at a set height above the table tennis table, and analyzing each image frame of the table tennis table top image to identify the table tennis image;
identifying a monochromatic color spot image arranged on the surface of a table tennis from the table tennis image, and determining the color of the monochromatic color spot and the distribution position of the monochromatic color spot relative to the table tennis image; the table tennis bat comprises a table tennis ball body, a table tennis ball cover, a color spot and a color filter, wherein the monochromatic color spot is arranged on the surface of the table tennis ball and is positioned at the vertex position of a built-in regular tetrahedron of the table tennis ball;
respectively calculating a first three-dimensional coordinate value of the monochromatic color spot on a ping-pong three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color, and associating the corresponding color and the first three-dimensional coordinate value thereof on the frame of ping-pong table image; the table tennis three-dimensional coordinate system is a three-dimensional coordinate system taking a table tennis center as an origin;
the method comprises the following steps of acquiring a plurality of frames of adjacent table tennis table surface images, and calculating the rotating direction and the rotating angular velocity of the table tennis according to the associated color and the first three-dimensional coordinate value of each frame of table tennis table surface image, wherein the method comprises the following steps: selecting a plurality of continuous frames of the table tennis table top images as image frames to be analyzed; wherein, the image frame to be analyzed at least comprises a plurality of image frames with the same color appearing repeatedly; respectively identifying image frames contained in various colors from the image frames to be analyzed to form image frame groups to be analyzed with the colors as types; aiming at different color types, calculating the rotation direction of the ping-pong ball around the origin and the rotation angular velocity thereof by utilizing the first three-dimensional coordinate value associated with the ping-pong table image in the image frame group to be analyzed and combining the frame rate of the ping-pong table image; and averaging according to the rotation angular velocities calculated by the image frame groups to be analyzed to obtain the real-time rotation angular velocity of the table tennis.
2. The method for detecting table tennis parameters according to claim 1, wherein the step of identifying monochromatic color spots on the surface of the table tennis from the table tennis image and determining the color of the monochromatic color spots and the distribution position of the monochromatic color spots relative to the table tennis image comprises:
judging the pixel color values in the table tennis image range according to preset color range thresholds of various colors, and determining various single-color stain images on the table tennis image and the corresponding colors of the single-color stain images;
acquiring pixel areas where monochromatic color spot images of all colors are located, and determining the central positions of the pixel areas as the central positions of the monochromatic color spots;
calculating relative position parameters of the center position and the center of the table tennis image; the relative position parameter is a two-dimensional coordinate value of the center position on a table tennis section coordinate system with the table tennis image center as an origin;
and obtaining the distribution position of the monochromatic color spot image relative to the table tennis image according to the relative position parameters.
3. The method for detecting parameters of table tennis according to claim 2, wherein the step of calculating the first three-dimensional coordinate value of the monochromatic color spot on the table tennis three-dimensional coordinate system according to the distribution position of the monochromatic color spot image of each color, and associating the corresponding color and the first three-dimensional coordinate value thereof on the frame of table tennis table image comprises:
constructing a three-dimensional coordinate system of the table tennis with the center of the table tennis as an origin; the xy-axis plane of the three-dimensional table tennis coordinate system is parallel to the table tennis table surface plane, and the z-axis is vertical to the table tennis center;
determining a shooting included angle between a high-speed camera and the center of the table tennis ball according to the distribution position of the table tennis ball image in the table tennis ball surface image and the set height;
calculating a first three-dimensional coordinate value of the monochromatic color spot on the three-dimensional coordinate system of the table tennis according to the camera angle and the two-dimensional coordinate value;
and recording the identified color and the first three-dimensional coordinate value of the monochromatic color spot on the ping-pong table image in a related manner.
4. The method for detecting parameters of table tennis according to claim 3, wherein the high-speed camera is located at a predetermined height position directly above the center of the net in the table tennis table;
the step of determining the camera angle between the high-speed camera and the core of the table tennis ball according to the distribution position of the table tennis ball image in the table tennis ball image and the set height comprises the following steps:
acquiring the center position of a table tennis image and the middle net midpoint position of the table tennis table top image;
determining a first distance between the center of the table tennis ball and the midpoint of the middle net of the table tennis table top according to the center position of the table tennis image and the midpoint of the middle net of the table tennis table top image;
and calculating a camera angle between the high-speed camera and the center of the table tennis ball according to the first distance and the set height.
5. The method of detecting table tennis parameters of claim 4, further comprising:
constructing a desktop three-dimensional coordinate system by taking the midpoint position of the middle net as an origin; the XY axis plane of the three-dimensional table top coordinate system is parallel to the table tennis table top, and the Z axis is perpendicular to the table tennis table top plane;
acquiring a first included angle between a connecting line of a ping-pong ball center of the ping-pong ball image and a midpoint position of a middle net and the middle net of the ping-pong ball table top according to the ping-pong ball table top image;
acquiring the area of a pixel area of the ping-pong image in the ping-pong table image;
calculating a second distance between the center of the table tennis ball and the high-speed camera according to a functional relation between the area of the pixel region of the table tennis ball image and the shooting distance;
calculating a first height value of the table tennis core relative to a table tennis table top and a projection distance relative to a middle point position of the middle net according to the second distance, the camera angle and a set height;
calculating a second three-dimensional coordinate value of the table tennis ball center on the tabletop three-dimensional coordinate system according to the projection distance and the first included angle;
and fitting according to a second three-dimensional coordinate value obtained by each frame of the table tennis table top image to obtain the motion trail of the table tennis.
6. A table tennis training assistance system, comprising: the high-speed cameras, the posture cameras, the sensing devices and the background server are distributed above the table tennis table tops, and the sensing devices are arranged in the table tennis bats;
the high-speed camera, the sensing device, the attitude camera and the contact sensing panel are connected to the background server through wireless network equipment;
the sensing device includes: the table tennis bat comprises an acceleration sensor, a touch induction layer stuck on a rubber of the table tennis bat, an MCU and a wireless communication module; the acceleration sensor is connected to the MCU, and the MCU is connected to the background server through the wireless communication module;
the posture camera is used for shooting real-time images of players, acquiring motion posture data of the players according to the real-time images and sending the motion posture data to the background server;
the background server is configured to perform the steps of the table tennis motion parameter detection method of any one of claims 1-5, and to perform the steps of: receiving acceleration data of the table tennis bat detected by the acceleration sensor, receiving firing position data of a table tennis ball contacting the bat surface detected by the touch sensing layer, and receiving movement posture data of players; and performing data analysis according to the rotation direction and the rotation angular velocity of the table tennis, the acceleration data of the table tennis bat, the firing position data and the motion posture data of the player, and generating auxiliary training reference information according to the analysis result.
7. The table tennis training assistance system of claim 6, wherein the back-office server is further configured to perform the steps of: and carrying out statistical analysis on the rotation direction and rotation angular velocity of the table tennis, the motion track of the table tennis, the acceleration data of the table tennis bat swung by the player, the triggering position data of the table tennis bat surface and the motion posture data of the player, which are acquired in the auxiliary training of any player, outputting the evaluation index score of the player, and outputting correction auxiliary information according to the evaluation index score.
8. The table tennis training assistance system of claim 6, wherein the back-office server is further configured to perform the steps of: performing model training according to the rotating direction and the rotating angular velocity of the table tennis ball, the motion trail of the table tennis ball, the acceleration data of the table tennis bat swung by the player, the firing position data of the table tennis bat surface and the motion posture data of the player, which are acquired in the auxiliary training of each player, and generating an confrontation training model of the player; and carrying out simulated confrontation according to the confrontation training models of different players, and outputting auxiliary training reference information according to the simulated confrontation.
9. The table tennis training assistance system of claim 8, wherein the back-office server is further configured to perform the steps of: based on the utilization of a 3D virtual animation technology, virtual batting animation of a player is generated according to the motion attitude data, and virtual flying animation of the table tennis is generated according to the motion track; and generating live animation videos with a plurality of view angles by using the virtual ball hitting animation and the virtual flying animation, and performing virtual live broadcast by using the live animation videos.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210498105.9A CN114612522B (en) | 2022-05-09 | 2022-05-09 | Table tennis sport parameter detection method and device and table tennis training auxiliary system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210498105.9A CN114612522B (en) | 2022-05-09 | 2022-05-09 | Table tennis sport parameter detection method and device and table tennis training auxiliary system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114612522A CN114612522A (en) | 2022-06-10 |
| CN114612522B true CN114612522B (en) | 2023-01-17 |
Family
ID=81868517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210498105.9A Active CN114612522B (en) | 2022-05-09 | 2022-05-09 | Table tennis sport parameter detection method and device and table tennis training auxiliary system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114612522B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103019024A (en) * | 2012-11-29 | 2013-04-03 | 浙江大学 | System for realtime and accurate observation and analysis of table tennis rotating and system operating method |
| CN104486591A (en) * | 2014-12-26 | 2015-04-01 | 安徽寰智信息科技股份有限公司 | Video acquisition and processing method for table tennis teaching and training |
| CN107481270A (en) * | 2017-08-10 | 2017-12-15 | 上海体育学院 | Table tennis target following and trajectory predictions method, apparatus, storage medium and computer equipment |
| WO2020096120A1 (en) * | 2018-11-09 | 2020-05-14 | 김상경 | Method for calculating number of revolutions of table tennis ball |
| CN112245893A (en) * | 2020-11-05 | 2021-01-22 | 上海理工大学 | Method and device for measuring rotation speed of table tennis |
| CN112702481A (en) * | 2020-11-30 | 2021-04-23 | 杭州电子科技大学 | Table tennis track tracking device and method based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6412998B1 (en) * | 2017-09-29 | 2018-10-24 | 株式会社Ｑｏｎｃｅｐｔ | Moving object tracking device, moving object tracking method, moving object tracking program |
-
2022
- 2022-05-09 CN CN202210498105.9A patent/CN114612522B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103019024A (en) * | 2012-11-29 | 2013-04-03 | 浙江大学 | System for realtime and accurate observation and analysis of table tennis rotating and system operating method |
| CN104486591A (en) * | 2014-12-26 | 2015-04-01 | 安徽寰智信息科技股份有限公司 | Video acquisition and processing method for table tennis teaching and training |
| CN107481270A (en) * | 2017-08-10 | 2017-12-15 | 上海体育学院 | Table tennis target following and trajectory predictions method, apparatus, storage medium and computer equipment |
| WO2020096120A1 (en) * | 2018-11-09 | 2020-05-14 | 김상경 | Method for calculating number of revolutions of table tennis ball |
| CN112245893A (en) * | 2020-11-05 | 2021-01-22 | 上海理工大学 | Method and device for measuring rotation speed of table tennis |
| CN112702481A (en) * | 2020-11-30 | 2021-04-23 | 杭州电子科技大学 | Table tennis track tracking device and method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114612522A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11951373B2 (en) | Automated or assisted umpiring of baseball game using computer vision | |
| US11064107B2 (en) | Objects trail-based analysis and control of video | |
| CN107871120B (en) | Sports event understanding system and method based on machine learning | |
| US9036864B2 (en) | Ball trajectory and bounce position detection | |
| US20220233939A1 (en) | Device for calculating flight information of ball, method of calculating flight information of ball, and computing-device-readable recording medium having the method recorded therein | |
| CN109289187B (en) | Table tennis training and level examination system | |
| CN105288982A (en) | Motion state testing device for golf | |
| CN109001484A (en) | The detection method and device of rotation speed | |
| US20230289982A1 (en) | Methods and systems to track a moving objects trajectory using a single camera | |
| CN110458100A (en) | Based on target detection and the identification of the table tennis drop point of tracking and methods of marking and system | |
| CN110298864B (en) | Visual sensing method and device for golf push rod equipment | |
| CN114612522B (en) | Table tennis sport parameter detection method and device and table tennis training auxiliary system | |
| WO2018097612A1 (en) | Sensing device for calculating information on user's golf shot and sensing method using same | |
| CN111738093B (en) | Automatic speed measuring method for curling balls based on gradient characteristics | |
| CN107754286A (en) | A kind of table tennis system based on inertial navigation and sense of touch correction positioning | |
| CN207545784U (en) | A kind of smart motion trap setting and system | |
| US20230070986A1 (en) | Deep learning method of determining golf club parameters from both radar signal and image data | |
| US20230364468A1 (en) | Deep learning method of determining golf swing and golf ball parameters from radar signal and image data | |
| CN114005072A (en) | Intelligent auxiliary judgment method and system for badminton | |
| TWI799184B (en) | Device and method for calculating spin of golf ball moved by hitting | |
| JP7083333B2 (en) | Image processing equipment, image processing methods, and programs | |
| JP7083334B2 (en) | Image processing equipment, image processing methods, and programs | |
| Wang | Method for Capturing Tennis Training Actions under Machine Vision Images | |
| CN115171219A (en) | Basketball auxiliary shooting hit rate statistical method | |
| CN115457083A (en) | Table tennis motion parameter detection method, system and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221229 Address after: 510000 Shahe longan cave, Tianhe District, Guangzhou City, Guangdong Province Applicant after: Guangdong University of Finance Address before: 510000 a508, building 1, No. 1, Nanxiang Branch Road, Guangzhou Economic and Technological Development Zone, Guangdong Province Applicant before: Guangzhou Jingtian Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |