CN116486297A - Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation - Google Patents

Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation Download PDF

Info

Publication number
CN116486297A
CN116486297A CN202310299090.8A CN202310299090A CN116486297A CN 116486297 A CN116486297 A CN 116486297A CN 202310299090 A CN202310299090 A CN 202310299090A CN 116486297 A CN116486297 A CN 116486297A
Authority
CN
China
Prior art keywords
shooting
hit rate
pitching
ball
pose
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.)
Pending
Application number
CN202310299090.8A
Other languages
Chinese (zh)
Inventor
王海滨
纪文峰
乔守良
程伟鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Genjian Intelligent Technology Co ltd
Original Assignee
Qingdao Genjian Intelligent Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao Genjian Intelligent Technology Co ltd filed Critical Qingdao Genjian Intelligent Technology Co ltd
Priority to CN202310299090.8A priority Critical patent/CN116486297A/en
Publication of CN116486297A publication Critical patent/CN116486297A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/32—Normalisation of the pattern dimensions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G06V20/47—Detecting features for summarising video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/23—Recognition of whole body movements, e.g. for sport training
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a shooting hit rate prediction method and a shooting hit rate prediction system combining pose discrimination and strength estimation, which relate to the technical field of computer vision and are used for processing panoramic images of a court and continuous video data of a pitcher from shooting preparation to shooting to obtain a group of continuous images of a ball; acquiring coordinates of a wrist, an elbow and a shoulder on the ball holding side of a pitcher, and determining the ball throwing direction of the pitcher; estimating the pitching force by utilizing video target tracking; determining a basketball displacement curve based on the shooting direction and the shooting force, and finally judging whether the shooting hits; according to the invention, only video information of a player from preparation to shooting is required to be obtained, the pose of the shooting player at the shooting moment is analyzed, whether the shooting angle is consistent with the basket azimuth is judged, then the force estimation is carried out through the basketball movement process, the relation between the shooting direction and the basket coordinates is calculated by combining the two information, and whether the player finally shoots the ball is judged, so that the shooting hit rate prediction efficiency and accuracy are improved, and the training of the player is better assisted.

Description

Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation
Technical Field
The invention belongs to the technical field of computer vision, and particularly relates to a shooting hit rate prediction method and system combining pose discrimination and dynamics estimation.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Basketball is a very common competitive sport, the game aims at shooting score, the scoring person wins, in recent years, chinese basketball is greatly advanced, the scale ratio of various basketball events is increased, the scoring ability of basketball players is more important, and the scoring ability of basketball players is more represented on shooting hit rate, so that the problem of the players in shooting is found in the game or during ordinary training, and the shooting hit rate is increased.
The shooting video images of the basketball players are analyzed to predict the shooting hit rate, training of the player can be assisted, problems occurring during shooting are found, but shooting hit rate prediction is a challenging complex computer vision task, a large amount of complex data needs to be collected in the existing shooting hit rate prediction method, chinese patent No. 113617004A-a training method (publication days: 2021-11-09) for improving the shooting hit rate of the basketball players, upper limb hand data of the players during shooting actions are collected through HIPLAY (high performance liquid chromatography) bracelets, myoelectricity collection equipment, neuron inertial data collection gloves and other wearable equipment, constraint is necessarily generated on the player by the wearable equipment, the action extensibility is influenced, the collected data is not consistent with actual data, and accordingly the prediction accuracy is influenced.
The search for a simple, efficient and accurate shot hit rate prediction scheme is a problem to be solved.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the shooting hit rate prediction method and the shooting hit rate prediction system by combining pose discrimination and strength estimation, which only need to acquire video information of a player from preparation to shooting, analyze the pose of the shooting player at the shooting moment, judge whether the shooting angle is consistent with the basket azimuth, perform strength estimation through the basketball movement process, calculate the relation between the emission direction and the basket coordinates by combining the two information, and pre-judge whether to get a ball finally, thereby improving the efficiency and the accuracy of shooting hit rate prediction and assisting the training of the player better.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
the first aspect of the invention provides a shooting hit rate prediction method combining pose discrimination and dynamics estimation;
the shooting hit rate prediction method combining pose discrimination and dynamics estimation comprises the following steps:
processing the obtained panoramic image of the court and continuous video data of a pitcher from the preparation of shooting to the delivery of the hand to obtain a group of continuous pitching images under the same three-dimensional rectangular coordinate system;
based on the pitching pose of the pitcher in the image, coordinates of the wrist, elbow and shoulder of the ball holding side of the pitcher are obtained, and the pitching direction of the pitcher is determined;
according to the continuous pitching images, tracking by utilizing a video target, and estimating pitching force;
based on the shooting direction and the shooting force, a basketball displacement curve is determined, and whether the shooting hits or not is finally determined.
Furthermore, a three-dimensional rectangular coordinate system is established by taking the center of the court as a zero point, and image denoising and image enhancement are carried out on the panoramic image of the court.
Further, the continuous video data is split into a plurality of images according to the number of frames, and each image is normalized to a uniform size.
Further, the specific method for determining the pitching direction of the pitching machine comprises the following steps:
acquiring feature coordinates of a ball throwing pose, wherein the features comprise: wrist, elbow, ball-holding side shoulder;
establishing a ball throwing pose plane in a three-dimensional rectangular coordinate system by using a planar three-point equation;
and determining the ball throwing direction of the ball thrower based on the ball throwing pose plane.
Further, the shooting pose plane established by the wrist, elbow and the shoulder of the side holding part of the shooting pose of the shooter is used for preliminarily judging the shooting hit condition, judging whether the shooting direction of the shooter is consistent with the basketball frame direction or not, and if not, the shooting probability is 0.
Further, the specific method for estimating the pitching force comprises the following steps:
acquiring a bowling parameter value, including: pixel distance, time interval, pixel speed;
and estimating acceleration and pitching force.
Further, the determining the basketball displacement distance includes:
based on the horizontal pixel distance and the vertical pixel distance of the basketball, respectively calculating the acceleration and the speed of the horizontal movement and the vertical movement;
calculating the vertical movement distance when the horizontal displacement of the ball reaches the basket;
and judging whether the pitching ball hits or not through the comparison of the vertical movement distance and the vertical pixel distance.
The second aspect of the present invention provides a shooting hit rate prediction system combining pose discrimination and dynamics estimation.
The shooting hit rate prediction system combines pose discrimination and strength estimation, and comprises a data processing module, a direction determining module, a strength estimating module and a hit judging module:
a data processing module configured to: processing the obtained panoramic image of the court and continuous video data of a pitcher from the preparation of shooting to the delivery of the hand to obtain a group of continuous pitching images under the same three-dimensional rectangular coordinate system;
a direction determination module configured to: based on the pitching pose of the pitcher in the image, coordinates of the wrist, elbow and shoulder of the ball holding side of the pitcher are obtained, and the pitching direction of the pitcher is determined;
a dynamics estimation module configured to: according to the continuous pitching images, tracking by utilizing a video target, and estimating pitching force;
a hit determination module configured to: based on the shooting direction and the shooting force, a basketball displacement curve is determined, and whether the shooting hits or not is finally determined.
A third aspect of the present invention provides a computer readable storage medium having stored thereon a program which when executed by a processor performs the steps in a shooting hit rate prediction method combining pose discrimination and dynamics estimation according to the first aspect of the present invention.
A fourth aspect of the present invention provides an electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps in the shooting hit rate prediction method combining pose discrimination and dynamics estimation according to the first aspect of the present invention when the program is executed.
The one or more of the above technical solutions have the following beneficial effects:
the invention provides a shooting hit rate prediction method and a shooting hit rate prediction system combining pose discrimination and strength estimation, which only need to acquire video information of a player from preparation to shooting, analyze the pose of the shooting player at the shooting moment, judge whether the shooting angle is consistent with the basket azimuth, perform strength estimation through a basketball motion process, calculate the relation between the emission direction and basket coordinates by combining the two information, and predict whether to finally goal, thereby improving the shooting hit rate prediction efficiency and accuracy and better assisting the training of the player.
The invention provides a new technology for confirming the ball throwing direction, wherein the coordinates of the wrist, the elbow and the shoulder on the ball holding side of a ball throwing person are confirmed through the ball throwing pose of a team member, a plane is further established by using a plane three-point equation, and the extending direction of the plane is considered as the ball throwing direction, so that the ball throwing direction is judged and confirmed as a ball frame.
The invention provides a novel method for estimating shooting force through video target tracking, which comprises the steps of calculating basketball displacement, comparing with a coordinate point of a ball frame after obtaining a basketball displacement curve, confirming whether a moving path of a ball passes through the ball frame, and finally judging whether shooting hits.
According to the invention, only the video information of a player from preparation to hand-out is required to be obtained, the shooting hit rate can be predicted by analyzing the hand-out force and the hand-out angle, a large amount of data acquired by wearable equipment is not required, and the method is easy to implement and has the feasibility of wide popularization; by combining the method, the problem of the player when shooting can be found in the competition or during ordinary training, and the training of the player is assisted.
Additional aspects of the invention 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 invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flow chart of a method of a first embodiment.
Fig. 2 is a system configuration diagram of a second embodiment.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention; unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention; as used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
The embodiment discloses a shooting hit rate prediction method combining pose discrimination and strength estimation;
as shown in fig. 1, the shooting hit rate prediction method combining pose discrimination and strength estimation includes:
step S1: processing the obtained panoramic image of the court and continuous video data of a pitcher from the preparation of shooting to the delivery of the hand to obtain a group of continuous pitching images under the same three-dimensional rectangular coordinate system;
a panoramic image of the course is acquired, including the pitcher and the rim, and continuous video data of the pitcher from the preparation of the shot to the play is acquired.
And (3) establishing a three-dimensional rectangular coordinate system for the panoramic image of the court by taking the center of the court as a zero point, denoising the image and enhancing the image, so that the body structure of the athlete and the basketball sport situation in the image are easier to identify, and finally, the image is presented in a three-dimensional rectangular coordinate form.
The continuous video data is split into N images by frame number (N is the total frame number of the video) and each image is normalized to a uniform size (e.g., h×w pixels).
Step S2: based on the pitching pose of the pitcher in the image, coordinates of the wrist, the elbow and the lateral shoulder of the pitcher are obtained, and the pitching direction of the pitcher is determined, specifically:
step S201: acquiring feature coordinates of a ball throwing pose, wherein the features comprise: wrist, elbow, ball-holding side shoulder;
selecting a frame image of a bowler when the bowler is out of hands by utilizing a three-dimensional rectangular coordinate system in the panoramic image of the court, and respectively recording coordinates of the wrist, the elbow, the side shoulder and the basketball basket of the bowler, wherein the coordinates are respectively recorded as follows: t (T) 1 (x 1 ,y 1 ,z 1 )、T 2 (x 2 ,y 2 ,z 2 )、T 3 (x 3 ,y 3 ,z 3 )、P 1 (x p ,y p ,z p )。
Step S202: establishing a ball throwing pose plane in a three-dimensional rectangular coordinate system by using a planar three-point equation;
acquired bowler wrist coordinate T 1 Elbow coordinates T 2 Ball-holding side shoulder coordinate T 3 And (3) carrying out equation ax+by+Cz+D=0 By a undetermined coefficient method, solving equation coefficient A, B, C, D to obtain a plane equation established By the coordinates of the wrist, the elbow and the shoulder of the ball-holding and measuring device when the ball-throwing person throws the ball, and determining whether the ball-throwing direction of the ball-throwing person is a ball frame or not By the plane equation.
Step S203: and determining the ball throwing direction of the ball thrower based on the ball throwing pose plane.
Coordinate P of basketball rim 1 The established plane equation of the shooting pose is brought in, if the equation is satisfied, the shooting direction of the shooter is shown as a basketball frame, the basic requirement of shooting is met, and the probability of shooting is improved; if the equation is not satisfied, it is indicated that the direction of the bowler is different from the direction of the basketball rim, and the probability of goal is 0, that is, the bowling hit condition is primarily determined by determining whether the direction of the bowler is consistent with the direction of the basketball rim.
Step S3: according to the continuous pitching image, the pitching force is estimated by utilizing video target tracking, specifically:
step S301: acquiring a bowling parameter value, including: pixel distance, time interval, pixel speed;
calculating the time from the preparation of the shot to the departure of the player, the total time (N.times.40) ms being recorded as time t, since each frame in the video is 40ms 1 Then, the comparison between the 1 st frame image and the N th frame image can be obtained at t 1 In the time, the distance of basketball moving on the x axis is S 1 The distance of movement in the y-axis is S 2 After the playing is obtained by combining the panoramic image of the court and the Nth frame image, the horizontal pixel distance between the basketball and the basketball frame is recorded as S 3 The vertical pixel distance is denoted as S 4 。
Step S302: and estimating acceleration and pitching force.
Assuming that the pitching person applies a force obliquely upwards to basketball, performing pitching force estimation calculation by using the acquired pitching parameter value, and using an acceleration distance formulaAccording to t 1 Distance S of basketball moving in x-axis in time 1 Initial speedDegree v 0 =0, calculate acceleration a of basketball 1 Then calculating the pitching force F through the relation formula F=ma of acceleration and force 1 M is the weight of basketball.
Step S4: based on the shooting direction and the shooting force, determining a basketball displacement curve, and finally judging whether shooting hits or not, wherein the method specifically comprises the following steps:
step S401: based on the horizontal pixel distance and the vertical pixel distance of the basketball, respectively calculating the acceleration and the speed of the horizontal movement and the vertical movement;
using time t spent by basketball moving from position 1 to position N 1 Obtaining horizontal movement distance S 1 By the formulaAnd v=v 0 +at to calculate the horizontal movement acceleration a x And horizontal movement velocity v after hand-out x The method comprises the steps of carrying out a first treatment on the surface of the Similarly, the vertical movement distance S of basketball from the 1 st frame position to the N frame position is utilized 2 Calculate the vertical acceleration a y And vertical velocity v after hand-out y 。
Step S402: calculating the vertical movement distance when the horizontal displacement of the ball reaches the basket;
through the formula tan theta 1 ＝S 2 /S 1 Solving the initial included angle theta of the ball throwing 1 Through the formula tan theta 2 ＝
S 4 /S 3 Calculate the included angle theta of basketball 2 Comparing initial included angle theta of ball throwing 1 Included angle theta with basketball 2 If the initial angle theta of the ball is larger than the initial angle theta 1 Is smaller than the included angle theta of the basketball 2 No precession is possible, otherwise the following calculation is continued.
According to the force F of throwing the ball 1 And an included angle theta 2 Judging whether the vertical force is greater than a preset force threshold F 0 If F 1 sinθ<F 0 No precession is possible, otherwise the following calculation is continued.
After the basketball is taken out, the basketball is transported at a constant speed in the horizontal directionMoving (neglecting factors such as air resistance) and uniformly decelerating and then uniformly accelerating (acceleration is gravity acceleration g) in the vertical direction; horizontal pixel distance S between basketball and basketball rim after basketball is handed out 3 And horizontal movement velocity v after hand-out x The time t from the horizontal displacement of the ball to the moment of reaching the rim is calculated by taking the velocity distance formula s=vt 2 Using the acceleration distance formulaLet t 2 And vertical velocity v after hand-out y Bringing into a formula to calculate at t 2 Distance S of basketball vertical movement in time y 。
Step S403: by comparing the vertical movement distance with the vertical pixel distance, whether the shot hits or not is judged, namely, the vertical pixel distance S between the basketball and the basketball frame after the basketball is taken out 4 And the vertical movement distance S of basketball y. And if the two are equal, determining that the shot hits, otherwise, determining that the shot misses.
Example two
The embodiment discloses a shooting hit rate prediction system combining pose discrimination and dynamics estimation;
as shown in fig. 2, the shooting hit rate prediction system combining pose discrimination and strength estimation includes a data processing module, a direction determining module, a strength estimating module and a hit determining module:
a data processing module configured to: processing the obtained panoramic image of the court and continuous video data of a pitcher from the preparation of shooting to the delivery of the hand to obtain a group of continuous pitching images under the same three-dimensional rectangular coordinate system;
a direction determination module configured to: based on the pitching pose of the pitcher in the image, coordinates of the wrist, elbow and shoulder of the ball holding side of the pitcher are obtained, and the pitching direction of the pitcher is determined;
a dynamics estimation module configured to: according to the continuous pitching images, tracking by utilizing a video target, and estimating pitching force;
a hit determination module configured to: based on the shooting direction and the shooting force, a basketball displacement curve is determined, and whether the shooting hits or not is finally determined.
Example III
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps in a shooting hit rate prediction method combining pose discrimination and strength estimation as described in embodiment 1 of the present disclosure.
Example IV
An object of the present embodiment is to provide an electronic apparatus.
An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the steps in the shooting hit rate prediction method combining pose discrimination and dynamics estimation as described in embodiment 1 of the present disclosure.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. The shooting hit rate prediction method combining pose discrimination and dynamics estimation is characterized by comprising the following steps:
processing the obtained panoramic image of the court and continuous video data of a pitcher from the preparation of shooting to the delivery of the hand to obtain a group of continuous pitching images under the same three-dimensional rectangular coordinate system;
based on the pitching pose of the pitcher in the image, coordinates of the wrist, elbow and shoulder of the ball holding side of the pitcher are obtained, and the pitching direction of the pitcher is determined;
according to the continuous pitching images, tracking by utilizing a video target, and estimating pitching force;
based on the shooting direction and the shooting force, a basketball displacement curve is determined, and whether the shooting hits or not is finally determined.
2. The shooting hit rate prediction method combining pose discrimination and dynamics estimation according to claim 1, wherein a three-dimensional rectangular coordinate system is established by taking the center of a court as a zero point, and image denoising and image enhancement are performed on the panoramic image of the court.
3. The shooting hit rate prediction method combining pose discrimination and dynamics estimation according to claim 1, wherein continuous video data is split into a plurality of images according to the number of frames, and each image is normalized to a uniform size.
4. The shooting hit rate prediction method combining pose discrimination and dynamics estimation according to claim 1, wherein the specific method for determining the shooting direction of a shooter is as follows:
acquiring feature coordinates of a ball throwing pose, wherein the features comprise: wrist, elbow, ball-holding side shoulder;
establishing a ball throwing pose plane in a three-dimensional rectangular coordinate system by using a planar three-point equation;
and determining the ball throwing direction of the ball thrower based on the ball throwing pose plane.
5. The shooting hit rate prediction method combining pose discrimination and dynamics estimation according to claim 1, wherein the shooting hit condition is preliminarily determined by a shooting pose plane established by three points of a wrist, an elbow and a holding side shoulder of a shooting pose of a shooter, and whether the shooting direction of the shooter is consistent with the basketball rim direction is judged, and if the shooting direction is inconsistent with the basketball rim direction, the probability of goal is 0.
6. The shooting hit rate prediction method combining pose discrimination and strength estimation according to claim 1, wherein the specific method for estimating the shooting strength is as follows:
acquiring a bowling parameter value, including: pixel distance, time interval, pixel speed;
and estimating acceleration and pitching force.
7. The method for predicting a shooting hit rate by combining pose discrimination and dynamics estimation according to claim 1, wherein said determining a basketball displacement distance comprises:
based on the horizontal pixel distance and the vertical pixel distance of the basketball, respectively calculating the acceleration and the speed of the horizontal movement and the vertical movement;
calculating the vertical movement distance when the horizontal displacement of the ball reaches the basket;
and judging whether the pitching ball hits or not through the comparison of the vertical movement distance and the vertical pixel distance.
8. The shooting hit rate prediction system combining pose discrimination and strength estimation is characterized by comprising a data processing module, a direction determining module, a strength estimation module and a hit judging module:
a data processing module configured to: processing the obtained panoramic image of the court and continuous video data of a pitcher from the preparation of shooting to the delivery of the hand to obtain a group of continuous pitching images under the same three-dimensional rectangular coordinate system;
a direction determination module configured to: based on the pitching pose of the pitcher in the image, coordinates of the wrist, elbow and shoulder of the ball holding side of the pitcher are obtained, and the pitching direction of the pitcher is determined;
a dynamics estimation module configured to: according to the continuous pitching images, tracking by utilizing a video target, and estimating pitching force;
a hit determination module configured to: based on the shooting direction and the shooting force, a basketball displacement curve is determined, and whether the shooting hits or not is finally determined.
9. A computer-readable storage medium having a program stored thereon, wherein the program when executed by a processor implements the steps of the shooting hit rate prediction method combining pose discrimination and strength estimation according to any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor, when executing the program, performs the steps in the shot hit rate prediction method combining pose discrimination and dynamics estimation as claimed in any one of claims 1 to 7.
CN202310299090.8A 2023-03-24 2023-03-24 Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation Pending CN116486297A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310299090.8A CN116486297A (en) 2023-03-24 2023-03-24 Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310299090.8A CN116486297A (en) 2023-03-24 2023-03-24 Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation

Publications (1)

Publication Number Publication Date
CN116486297A true CN116486297A (en) 2023-07-25

Family

ID=87225933

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310299090.8A Pending CN116486297A (en) 2023-03-24 2023-03-24 Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation

Country Status (1)

Country Link
CN (1) CN116486297A (en)

Similar Documents

Publication Publication Date Title
KR102205639B1 (en) Golf ball tracking system
CN112154482B (en) Ball game image analysis device and ball game image analysis method
US20140301600A1 (en) True space tracking of axisymmetric object flight using diameter measurement
JP6484858B2 (en) Image processing apparatus and image processing method
JP6596804B1 (en) Position tracking system and position tracking method
CN111369629B (en) Ball return track prediction method based on binocular vision perception of swing and batting actions
US11850498B2 (en) Kinematic analysis of user form
JPWO2018122956A1 (en) Sports motion analysis support system, method and program
JP2012090709A (en) Mobile terminal, program and method for counting golf stroke
CN116486297A (en) Shooting hit rate prediction method and system combining pose discrimination and dynamics estimation
CN112121392B (en) Ping-pong skill and tactics analysis method and analysis device
US10258851B2 (en) System and method for calculating projected impact generated by sports implements and gaming equipment
Kuruppu et al. Comparison of different template matching algorithms in high speed sports motion tracking
EP4325448A1 (en) Data processing apparatus and method
EP4325443A1 (en) Data processing apparatus and method
Tamaki et al. Spin measurement system for table tennis balls based on asynchronous non-high-speed cameras
Yoshikawa et al. Prediction of shot type and hit location based on pose information using badminton match videos
WO2023100235A1 (en) Evaluation device, evaluation method, and program
US20220343649A1 (en) Machine learning for basketball rule violations and other actions
CN110711368B (en) Ball hitting method and device of table tennis robot
Marwat ANALYSIS OF UPPER BODY THREE-D MOTION OF BATTERS FOR EXECUTION OF PULL SHOT IN CRICKET
WO2022056315A1 (en) System and method for capture and analysis of sporting performance data and broadcast of the same
Song et al. Research and analysis of table tennis movement trajectory prediction model based on deep learning
CN114565641A (en) Image recognition method, device, equipment, system and storage medium
CN111782643A (en) Juvenile sport special skill group training and evaluating system and method based on Internet of things and machine learning

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