CN113011310B - Method and device for collecting shooting exercise amount, computer equipment and storage medium - Google Patents

Method and device for collecting shooting exercise amount, computer equipment and storage medium Download PDF

Info

Publication number
CN113011310B
CN113011310B CN202110277974.4A CN202110277974A CN113011310B CN 113011310 B CN113011310 B CN 113011310B CN 202110277974 A CN202110277974 A CN 202110277974A CN 113011310 B CN113011310 B CN 113011310B
Authority
CN
China
Prior art keywords
basketball
image
video frame
human body
space coordinate
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
Application number
CN202110277974.4A
Other languages
Chinese (zh)
Other versions
CN113011310A (en
Inventor
罗新建
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.)
China University of Geosciences
Original Assignee
China University of Geosciences
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 China University of Geosciences filed Critical China University of Geosciences
Priority to CN202110277974.4A priority Critical patent/CN113011310B/en
Publication of CN113011310A publication Critical patent/CN113011310A/en
Application granted granted Critical
Publication of CN113011310B publication Critical patent/CN113011310B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
    • G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
    • G06F16/786—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content using motion, e.g. object motion or camera motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • 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
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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
    • G06T2207/30196—Human being; Person
    • 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
    • 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
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention relates to the technical field of sports equipment, and discloses a method and a device for collecting the amount of shooting exercise based on image recognition and induction of a backboard, computer equipment and a storage medium. The invention provides a brand-new method for acquiring the amount of shooting motion based on image recognition and induction of a backboard, namely when the method is applied to a shooting training place provided with a binocular camera and the induction backboard, basketball/human body image recognition and space positioning are carried out on shooting monitoring videos to determine the movement track of the basketball in a single shooting process, then the mechanical energy of the basketball is further calculated according to the movement track of the basketball, finally the heat consumed by the shooting of the athlete can be determined according to the law of energy conservation and the mechanical energy, namely the amount of shooting motion of the athlete is acquired, and the problem that the current shooting training place cannot acquire the amount of shooting motion of the athlete is solved.

Description

Method and device for collecting shooting exercise amount, computer equipment and storage medium
Technical Field
The invention belongs to the technical field of sports equipment, and particularly relates to a method and a device for collecting the amount of shooting exercise based on image recognition and induction of a backboard, computer equipment and a storage medium.
Background
The Amount of exercise (Amount of exercise), also called "exercise load", refers to the Amount of physical and psychological load and the Amount of heat consumed by the human body during the physical activity, and is determined by the intensity and duration of exercise, the accuracy of the exercise and the characteristics of the exercise. In the process of physical exercise, it is necessary to timely grasp the amount of exercise (i.e., the amount of heat consumed) generated by the athlete during the exercise, so as to prevent the exercise from being lost due to insufficient amount of exercise, and to avoid the injury to the body of the athlete due to excessive exercise. However, the current shooting training places (such as basketball courts or places where basketball shooting machines are arranged) cannot collect the shooting amount of the player.
Disclosure of Invention
In order to solve the problem that the shooting exercise amount of a player cannot be acquired in the existing shooting training place, the invention aims to provide a method, a device, computer equipment and a storage medium for acquiring the shooting exercise amount of the player based on image recognition and induction of a backboard, which can be applied to the shooting training place provided with a binocular camera and the induction of the backboard, determine the basketball movement track in a single shooting process by carrying out basketball/human body image recognition and space positioning on a shooting monitoring video, further calculate the mechanical energy of a basketball according to the basketball movement track, and finally determine the heat consumed by the player for shooting according to the law of energy conservation and the mechanical energy, namely acquire the shooting exercise amount of the player.
In a first aspect, the present invention provides a method for capturing the amount of basketball shooting motion based on image recognition and sensing, comprising:
acquiring a shooting monitoring video collected by a binocular camera;
identifying whether a target image is contained or not aiming at each video frame image in the shooting monitoring video, and determining the space coordinate of a target object when the target image is identified to be contained, wherein the target image comprises a basketball image and a human body image, and the target object is a basketball or a human body corresponding to the target image;
extracting a continuous video frame image set which meets the following conditions (A) to (D) and corresponds to the basketball induction signals one by one from the shooting monitoring video according to the identification result of the target image, the positioning result of the target object and the basketball induction signals from the induction backboard:
(A) the continuous video frame image set comprises N video frame images, and each video frame image in the N video frame images comprises a single basketball image respectively, wherein N is a natural number not less than 2;
(B) the first video frame image in the continuous video frame image set further comprises at least one human body image, and for at least one human body image and a single basketball image in the first video frame image, the distance from the human body space coordinate corresponding to the at least one human body image to the basketball space coordinate corresponding to the single basketball image is not greater than a preset distance threshold;
(C) the non-first video frame image in the continuous video frame image set does not contain a human body image, or when at least one human body image is contained, aiming at any one human body image and a single basketball image in the non-first video frame images, the distance from the human body space coordinate corresponding to the any one human body image to the basketball space coordinate corresponding to the single basketball image is larger than the preset distance threshold;
(D) the acquisition time stamp of the Nth video frame image in the continuous video frame image set is not later than the trigger time stamp of the basketball induction signal;
for each group of two adjacent video frame images in the continuous video frame image set, calculating the corresponding basketball mechanical energy E according to the following formula:
Figure BDA0002977393820000021
in the formula, m represents the weight of a basketball, d represents the distance from a previous basketball space coordinate to a later basketball space coordinate, the previous basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a previous video frame image, the later basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a later video frame image, the previous video frame image and the later video frame image are two video frame images which are sequenced in sequence according to a collecting timestamp in the two adjacent video frame images, and h represents the distance from the previous basketball space coordinate to the later basketball space coordinateBRepresenting the elevation, h, of the space coordinate of the basketball at the backAElevation, h, representing the spatial coordinates of the previous basketball1The elevation of a first basketball space coordinate is represented, wherein the first basketball space coordinate is a basketball space coordinate, t, corresponding to a single basketball image in the first video frame imageBRepresenting the acquisition time stamp, t, of said subsequent video frame imageARepresenting a capture timestamp of the previous video frame image, g representing a gravitational acceleration;
and determining the shooting motion amount of the athlete according to the earliest value, the maximum value, the average value or the middle value of the N-1 calculated basketball mechanical energy, wherein the earliest value is the value calculated according to the basketball mechanical energy corresponding to the first group of adjacent two video frame images in the sequence before and after the acquisition time.
Based on the content of the invention, a brand new method for acquiring the amount of shooting motion based on image recognition and induction of a backboard can be provided, namely when the method is applied to a shooting training place provided with a binocular camera and the induction backboard, basketball/human body image recognition and space positioning can be carried out on shooting monitoring videos, the motion track of the basketball in the single shooting process is determined, then the mechanical energy of the basketball is further calculated according to the motion track of the basketball, finally the heat consumed by the player due to shooting can be determined according to the law of energy conservation and the mechanical energy, namely the amount of shooting motion of the player is acquired, and the problem that the amount of shooting motion of the player cannot be acquired in the current shooting training place is solved.
In one possible design, identifying whether a target image is included in each video frame image in the shooting monitoring video includes:
importing a video frame image into a first detection model which is pre-trained, and then judging whether the video frame image contains a basketball image according to a detection result of the first detection model, wherein the first detection model adopts a fast R-CNN detection model, an SSD detection model or a YOLO detection model;
and importing a video frame image containing a basketball image into a second detection model which is pre-trained, and then judging whether the video frame image contains a human body image according to a detection result of the second detection model, wherein the second detection model adopts a Faster R-CNN detection model, an SSD detection model or a YOLO detection model.
In one possible design, determining the spatial coordinates of the target object upon identifying that the target image is included includes:
determining the distance from the target object to the origin of a camera coordinate system according to the binocular distance measuring principle of the binocular camera;
acquiring the coordinate position of the target object in a camera coordinate system according to the distance from the target object to the origin of the camera coordinate system and the plane coordinate of the target image in the video frame image;
and converting the coordinate position of the target object in a camera coordinate system into the space coordinate of the target object according to the installation position and the installation posture of the binocular camera.
In one possible design, the determining the amount of the basketball's shot movement based on the calculated earliest, largest, average or median of the N-1 basketball's mechanical energies comprises:
identifying at least one field person corresponding to at least one human body image one by one according to at least one human body image in the first video frame image;
taking a live person of the at least one live person and closest to the first basketball spatial coordinate as a basketball player;
and determining the shooting motion quantity of the shooting player according to the earliest value, the maximum value, the average value or the middle value of the calculated N-1 basketball mechanical energy.
Through the possible design, when a plurality of field personnel appear in the first video frame image, the basketball shooting player can be accurately locked based on the distance relation between the personnel and the basketball, the goal of automatically binding, recording or displaying the amount of shooting exercise and the basketball shooting player is achieved, the method is particularly suitable for basketball game scenes in which a plurality of people participate, and the application range is further expanded.
In one possible design, identifying at least one athlete corresponding to at least one human body image in a one-to-one correspondence with the at least one human body image according to the at least one human body image in the first video frame image includes:
intercepting a corresponding face image from the human body image;
and importing the face image into an identification model which finishes deep learning training, and then determining the identity of the person corresponding to the human body image according to the identification result of the identification model.
In one possible design, identifying at least one athlete corresponding to at least one human body image in a one-to-one correspondence with the at least one human body image according to the at least one human body image in the first video frame image includes:
and determining the identity of the person corresponding to the human body image according to the person tracking result based on the shooting monitoring video.
In one possible design, the induction backboard is a backboard with a plurality of basketball induction sensors arranged, wherein the basketball induction sensors comprise a proximity sensor arranged on the backboard and used for sensing whether a basketball is close to the proximity sensor, a pressure/vibration sensor used for sensing whether the backboard and the basketball collide with each other or not and/or a sensor used for sensing whether a basketball is shot or not.
The invention provides a device for collecting shooting motion quantity based on image recognition and induction backboard, comprising a video acquisition unit, a recognition positioning unit, a video frame extraction unit, a mechanical energy calculation unit and a motion quantity determination unit which are sequentially connected in communication;
the video acquisition unit is used for acquiring shooting monitoring videos collected by the binocular camera;
the identification and positioning unit is used for identifying whether a target image is included or not aiming at each video frame image in the shooting monitoring video, and determining the space coordinate of a target object when the target image is identified to be included, wherein the target image includes a basketball image and a human body image, and the target object is a basketball or a human body corresponding to the target image;
the video frame extraction unit is used for extracting a continuous video frame image set which meets the following conditions (A) to (D) and corresponds to the basketball induction signals one by one from the shooting monitoring video according to the identification result of the target image, the positioning result of the target object and the basketball induction signals from the induction backboard:
(A) the continuous video frame image set comprises N video frame images, and each video frame image in the N video frame images comprises a single basketball image respectively, wherein N is a natural number not less than 2;
(B) the first video frame image in the continuous video frame image set further comprises at least one human body image, and for at least one human body image and a single basketball image in the first video frame image, the distance from the human body space coordinate corresponding to the at least one human body image to the basketball space coordinate corresponding to the single basketball image is not greater than a preset distance threshold;
(C) the non-first video frame image in the continuous video frame image set does not contain a human body image, or when at least one human body image is contained, aiming at any one human body image and a single basketball image in the non-first video frame images, the distance from the human body space coordinate corresponding to the any one human body image to the basketball space coordinate corresponding to the single basketball image is larger than the preset distance threshold;
(D) the acquisition time stamp of the Nth video frame image in the continuous video frame image set is not later than the trigger time stamp of the basketball induction signal;
the mechanical energy calculating unit is configured to calculate, for each group of two adjacent video frame images in the continuous video frame image set, a corresponding basketball mechanical energy E according to the following formula:
Figure BDA0002977393820000041
in the formula, m represents the weight of a basketball, d represents the distance from a previous basketball space coordinate to a later basketball space coordinate, the previous basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a previous video frame image, the later basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a later video frame image, the previous video frame image and the later video frame image are two video frame images which are sequenced in sequence according to a collecting timestamp in the two adjacent video frame images, and h represents the distance from the previous basketball space coordinate to the later basketball space coordinateBIndicating the rear basketElevation of the spherical space coordinate, hAElevation, h, representing the spatial coordinates of the previous basketball1The elevation of a first basketball space coordinate is represented, wherein the first basketball space coordinate is a basketball space coordinate, t, corresponding to a single basketball image in the first video frame imageBRepresenting the acquisition time stamp, t, of said subsequent video frame imageARepresenting a capture timestamp of the previous video frame image, g representing a gravitational acceleration;
and the motion amount determining unit is used for determining the shooting motion amount of the athlete according to the earliest value, the maximum value, the average value or the middle value of the N-1 calculated basketball mechanical energy, wherein the earliest value is the value calculated according to the basketball mechanical energy corresponding to the first group of adjacent two video frame images in the sequence of the acquisition time.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver, which are communicatively connected in sequence, wherein the memory is used for storing a computer program, the transceiver is used for transmitting and receiving signals, and the processor is used for reading the computer program and executing the method according to the first aspect or any one of the possible designs of the first aspect.
In a fourth aspect, the present invention provides a storage medium having stored thereon instructions for performing the method of the first aspect or any one of the possible designs of the first aspect, when the instructions are run on a computer.
In a fifth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method as described above in the first aspect or any one of the possible designs of the first aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a system for acquiring the amount of shooting motion arranged in a shooting training place according to the present invention.
FIG. 2 is a flowchart illustrating a method for capturing an amount of basketball shooting movement based on image recognition and sensing provided by the present invention.
FIG. 3 is a schematic structural diagram of an apparatus for capturing the amount of basketball shooting motion based on image recognition and sensing provided by the present invention.
Fig. 4 is a schematic structural diagram of a computer device provided by the present invention.
In the above drawings: 1-binocular camera; 2-induction backboard; 3-a computer device; 401 — first field person; 402-a second field person; 403-third field personnel; 5-basketball.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. Specific structural and functional details disclosed herein are merely representative of exemplary embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of exemplary embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
It will be understood that when an element is referred to herein as being "connected," "connected," or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Conversely, if a unit is referred to herein as being "directly connected" or "directly coupled" to another unit, it is intended that no intervening units are present. In addition, other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between … …" versus "directly between … …", "adjacent" versus "directly adjacent", etc.).
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. As used herein, the singular forms "a", "an" 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," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative designs, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
It should be understood that specific details are provided in the following description to facilitate a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques may be shown without unnecessary detail in order to avoid obscuring example embodiments.
As shown in fig. 1 to 2, the method for acquiring the amount of shooting exercise based on image recognition and sensing of a backboard provided in the first aspect of this embodiment may be applied, but not limited to, in a shooting training place where a shooting exercise acquisition system (including a binocular camera 1, a sensing backboard 2, a computer device 3, and the like, as shown in fig. 1) is arranged, and is executed by the computer device 3 in the shooting exercise acquisition system, so as to acquire the amount of heat consumed by a player in shooting (i.e., the shooting exercise). The method for acquiring the shooting motion amount based on image recognition and sensing of the backboard can be, but is not limited to, comprising the following steps S101-S105.
S101, shooting monitoring videos collected by the binocular camera are obtained.
In the step S101, the shooting monitoring video refers to a monitoring video for recording the whole shooting process of the player, and may be, but is not limited to, acquired by the binocular camera 1 shown in fig. 1, where the binocular camera 1 is an existing camera device with two lenses symmetrically arranged left and right/up and down, and the arrangement position of the binocular camera is required to ensure that the imaging field of view covers the whole shooting training site, so as to image people and basketballs appearing in the shooting training site without obstruction, and obtain multiple frames of continuously acquired shooting monitoring video, for example, arranged at a high position as shown in fig. 1. In addition, the shooting monitoring video can be a real-time video from the binocular camera or a historical video stored in a video library.
S102, identifying whether a target image is contained or not aiming at each video frame image in the shooting monitoring video, and determining the space coordinate of a target object when the target image is identified to be contained, wherein the target image comprises a basketball image and a human body image, and the target object is a basketball or a human body corresponding to the target image.
In step S102, the specific identification method may be implemented by using an existing image identification technology. In the optimization, the basketball movement track needs to be determined in consideration of the following requirements, so that the basketball image needs to be identified firstly, and the first video frame in the video recording the single shooting process needs to be determined, so that the human body image needs to be identified secondly, therefore, in order to reduce the calculation amount required by image identification, whether the target image is included in each video frame image in the shooting monitoring video is identified, including but not limited to the following steps S1021 to S1022.
And S1021, importing a video frame image into a first detection model which is pre-trained, and then judging whether the video frame image contains a basketball image according to a detection result of the first detection model, wherein the first detection model can be but is not limited to a Faster R-CNN detection model, an SSD detection model or a YOLO detection model.
In the step S1021, the Faster R-CNN detection model, the SSD detection model, and the YOLO detection model are respectively conventional image target detection models, so that the first detection model that has been pre-trained can be obtained based on a conventional training mode, and the first detection model has an ability to accurately identify a basketball image, and can further identify whether the basketball image is included in the video frame image.
S1022, importing a video frame image containing a basketball image into a second detection model which is pre-trained, and then judging whether the video frame image contains a human body image according to a detection result of the second detection model, wherein the second detection model can be but is not limited to a Faster R-CNN detection model, an SSD detection model or a YOLO detection model.
In the step S1022, the pre-trained second detection model may also be obtained based on the existing conventional training mode, so that the second detection model has the capability of accurately identifying the human body image, and further, whether the video frame image further includes the human body image may be identified.
In the step S102, the optimization, when the target image is identified, determines the spatial coordinates of the target object, including but not limited to the following steps S1023 to S1025.
And S1023, determining the distance from the target object to the origin of a camera coordinate system according to a binocular distance measuring principle of the binocular camera.
In the step S1023, the binocular range finding principle means that a difference directly existing in horizontal/vertical coordinates imaged by a target point on two views of left and right/up and down (which are respectively acquired by two lenses symmetrically arranged left and right/up and down one by one) has an inverse proportion relation with a distance from the target point to an imaging plane, so that a distance from the target object to an origin of a camera coordinate system, that is, a Z-axis coordinate of the target object in the camera coordinate system can be calculated based on the existing binocular range finding technology.
And S1024, acquiring the coordinate position of the target object in the camera coordinate system according to the distance from the target object to the origin of the camera coordinate system and the plane coordinates of the target image in the video frame image.
In step S1024, since the video frame image is perpendicular to the optical axis of the binocular camera 1 (i.e., the Z axis in the camera coordinate system), the X axis coordinate and the Y axis coordinate of the target object in the camera coordinate system can be directly obtained based on the coordinate position of the target image in the video frame image, and then the coordinate position of the target object in the camera coordinate system can be obtained.
And S1025, converting the coordinate position of the target object in a camera coordinate system into the space coordinate of the target object according to the installation position and the installation posture of the binocular camera.
In step S1025, the installation position is the spatial coordinate of the binocular camera, the installation posture may include, but is not limited to, an azimuth angle, a pitch angle, a roll angle, and the like of the binocular camera, and further, the coordinate position of the target object in the camera coordinate system may be converted into the spatial coordinate of the target object through conventional geometric analysis and coordinate transformation.
S103, according to the identification result of the target image, the positioning result of the target object and the basketball induction signal from the induction backboard, extracting a continuous video frame image set which meets the following conditions (A) to (D) and corresponds to the basketball induction signal one by one from the shooting monitoring video:
(A) the continuous video frame image set comprises N video frame images, and each video frame image in the N video frame images comprises a single basketball image respectively, wherein N is a natural number not less than 2;
(B) the first video frame image in the continuous video frame image set further comprises at least one human body image, and for at least one human body image and a single basketball image in the first video frame image, the distance from the human body space coordinate corresponding to the at least one human body image to the basketball space coordinate corresponding to the single basketball image is not greater than a preset distance threshold;
(C) the non-first video frame image in the continuous video frame image set does not contain a human body image, or when at least one human body image is contained, aiming at any one human body image and a single basketball image in the non-first video frame images, the distance from the human body space coordinate corresponding to the any one human body image to the basketball space coordinate corresponding to the single basketball image is larger than the preset distance threshold;
(D) and the acquisition time stamp of the Nth video frame image in the continuous video frame image set is not later than the trigger time stamp of the basketball induction signal.
In step S103, the sensing backboard 2 is used for sensing whether the thrown basketball is approached or touched, so as to determine the time end of the single shooting process by triggering the generated basketball sensing signal. Preferably, the sensing backboard 2 is a backboard with a plurality of basketball sensing sensors, wherein the basketball sensing sensors include, but are not limited to, a proximity sensor arranged on the backboard for sensing whether a basketball is approaching, a pressure/vibration sensor for sensing whether the backboard and the basketball collide, and/or a sensor for sensing whether a basketball is shot or not, etc. The sensors such as the proximity sensor, the pressure sensor and the vibration sensor can be realized by adopting the related existing sensors.
In step S103, the condition (a) is used to ensure that each video frame image in the video recording a single shooting process (i.e., the set of consecutive video frame images) contains a single basketball image, so as to lock the thrown basketball. The conditions (B) and (C) are used to jointly determine the starting point of the single shooting process, that is, to determine which frame is the first video frame in the video recording the single shooting process according to the distance change relationship between the basketball and the human body in the shooting process (that is, the basketball is gradually far away from the human body in the single shooting process, as shown in fig. 1), wherein the preset distance threshold may be specifically set according to the physical condition of the player, and may generally default to 1 meter (that is, the length of the arm of an adult is not greater than the length, if the distance between the basketball and the human body is not greater than the length, the capturing moment of the first video frame may be regarded as the basketball is at the moment of shooting, and if the distance between the basketball and the human body is greater than the length, the capturing moment of the non-first video frame may be regarded as the moment after the basketball is shot). The condition (D) is used to determine the time end of a single shooting process, that is, it is determined which frame is the last video frame in the video recording the single shooting process according to the trigger timestamp of the basketball induction signal, and after the basketball induction signal is generated by triggering, the basketball contacts with objects such as a backboard or a net bag to change mechanical energy, so that a corresponding video frame image needs to be rejected.
S104, aiming at each group of adjacent two video frame images in the continuous video frame image set, calculating the corresponding basketball mechanical energy E according to the following formula:
Figure BDA0002977393820000091
where m represents the weight of the basketball and d represents the distance from the previous basketball spatial coordinate, which is the basket corresponding to a single basketball image in the previous video frame image, to the next basketball spatial coordinateThe subsequent basketball space coordinate refers to a basketball space coordinate corresponding to a single basketball image in the subsequent video frame image, the previous video frame image and the subsequent video frame image are two video frame images which are sequenced in sequence according to the acquisition time stamps in the two adjacent video frame images, and h is the time stamp of the acquisition of the two video frame imagesBRepresenting the elevation, h, of the space coordinate of the basketball at the backAElevation, h, representing the spatial coordinates of the previous basketball1The elevation of a first basketball space coordinate is represented, wherein the first basketball space coordinate is a basketball space coordinate, t, corresponding to a single basketball image in the first video frame imageBRepresenting the acquisition time stamp, t, of said subsequent video frame imageARepresenting the capture timestamp of the previous video frame image, g representing the acceleration of gravity.
In the step S104, as shown in fig. 1, five video frame images respectively including a single basketball image are obtained according to the parabolic motion trajectory after the basketball is thrown, so as to form four groups of two adjacent video frame images. In the calculation formula of the basketball mechanical energy E,
Figure BDA0002977393820000092
reflects the average kinetic energy of the basketball between the acquisition time stamps of the two adjacent video frame images (because of the
Figure BDA0002977393820000093
Reflecting the average speed of this period),
Figure BDA0002977393820000094
the gravitational potential energy of the basketball changing from the first basketball space coordinate O to the middle point M between the previous basketball space coordinate A and the next basketball space coordinate B is reflected, so that the average kinetic energy is regarded as the transient kinetic energy of the basketball at the middle point M, and the transient kinetic energy and the variation of the gravitational potential energy are summed and calculated, and the accurate mechanical energy of the basketball can be obtained.
And S105, determining the shooting motion amount of the player according to the earliest value, the maximum value, the average value or the middle value of the N-1 calculated basketball mechanical energy, wherein the earliest value is the value calculated according to the basketball mechanical energy corresponding to the first group of adjacent two video frame images in the sequence before and after the acquisition time.
In step S105, considering that at the moment when the basketball is thrown, the player does work on the basketball to make the mechanical energy of the basketball (in this embodiment, the mechanical energy of the basketball is zero before the basketball is thrown), and according to the law of conservation of energy, the mechanical energy of the basketball is inevitably smaller than the amount of heat consumed by the player when the player shoots the basketball, and the mechanical energy of the basketball and the amount of heat consumed have positive correlation (i.e., the amount of heat consumed is larger when the mechanical energy of the basketball is larger), the amount of shooting motion of the player can be calculated according to the earliest value, the maximum value, the average value or the intermediate value, and a proportional coefficient of the mechanical energy of the basketball and the amount of shooting motion obtained in advance by a conventional data fitting technique (i.e., curve fitting is performed on historically collected mechanical energy data of the basketball and data of the amount of shooting motion). Further, considering that the basketball may experience a reduction in mechanical energy due to air resistance during the throwing process, it may be preferable to determine the amount of basketball shot by the player based on the earliest value.
Therefore, through the exercise amount acquisition scheme described in detail in the steps S101 to S105, a brand new method for acquiring the shooting exercise amount based on image recognition and induction of the backboard can be provided, namely when the method is applied to a shooting training place provided with a binocular camera and the induction backboard, basketball/human body image recognition and space positioning can be carried out on shooting monitoring videos, the basketball motion track in the single shooting process is determined, then the mechanical energy of the basketball is further calculated according to the basketball motion track, finally the heat consumed by the shooting of the player can be determined according to the law of energy conservation and the mechanical energy, namely the shooting exercise amount of the player is acquired, and the problem that the shooting exercise amount of the player cannot be acquired in the current shooting training place is solved.
Based on the technical solution of the first aspect, the present embodiment further specifically proposes a second possible design for automatically identifying a basketball shooting player, that is, determining the amount of the basketball shooting motion of the player according to the calculated earliest value, the maximum value, the average value or the middle value of the N-1 basketball mechanical energies, including but not limited to the following steps S201 to S203.
S201, identifying at least one field person corresponding to at least one human body image one by one according to at least one human body image in the first video frame image.
In step S201, two cases of the human body image including a face image and not including a face image are considered, so that the former case can be identified as follows: intercepting a corresponding face image from the human body image; and importing the face image into an identification model which finishes deep learning training, and then determining the identity of the person corresponding to the human body image according to the identification result of the identification model. The recognition model can adopt a conventional convolutional neural network model and is obtained based on a conventional training mode, so that the recognition model has the capability of accurately recognizing the identity of a person, and the identity of the person corresponding to the human body image can be recognized.
In step S201, the person may be identified as follows: and determining the identity of the person corresponding to the human body image according to the person tracking result based on the shooting monitoring video. The aforementioned person tracking technology is a conventional technology, so that the person identity corresponding to the human body image can be identified, and the method is particularly suitable for the case that the human body image does not include a human face image.
S202, the live person, which is the nearest to the first basketball space coordinate, of the at least one live person is used as a shooting player.
In step S202, as shown in fig. 1, three live persons may exist in the captured first video frame image as follows: the first field person 401, the second field person 402 and the third field person 403 can determine that the first field person 401 is the basketball player because the first field person 401 is closest to the first basketball space coordinate, so that the amount of the shooting motion can be automatically bound and recorded or displayed with the shooting player in the following process.
S203, determining the shooting motion amount of the basketball shooting player according to the earliest value, the maximum value, the average value or the middle value of the N-1 mechanical energy of the basketball obtained through calculation.
Therefore, through the possible design one described in the above steps S201 to S203, when a plurality of field persons appear in the first video frame image, the basketball shooting player can be accurately locked based on the distance relationship between the persons and the basketball, the purpose of automatically binding, recording or displaying the amount of shooting motion and the basketball shooting player is achieved, and the method is particularly suitable for basketball game scenes in which a plurality of persons participate, and further expands the application range.
As shown in fig. 3, a second aspect of the present embodiment provides a virtual device for implementing the method according to any one of the first aspect or the possible designs of the first aspect, including a video acquisition unit, an identification and positioning unit, a video frame extraction unit, a mechanical energy calculation unit, and a motion amount determination unit, which are sequentially connected in a communication manner;
the video acquisition unit is used for acquiring shooting monitoring videos collected by the binocular camera;
the identification and positioning unit is used for identifying whether a target image is included or not aiming at each video frame image in the shooting monitoring video, and determining the space coordinate of a target object when the target image is identified to be included, wherein the target image includes a basketball image and a human body image, and the target object is a basketball or a human body corresponding to the target image;
the video frame extraction unit is used for extracting a continuous video frame image set which meets the following conditions (A) to (D) and corresponds to the basketball induction signals one by one from the shooting monitoring video according to the identification result of the target image, the positioning result of the target object and the basketball induction signals from the induction backboard:
(A) the continuous video frame image set comprises N video frame images, and each video frame image in the N video frame images comprises a single basketball image respectively, wherein N is a natural number not less than 2;
(B) the first video frame image in the continuous video frame image set further comprises at least one human body image, and for at least one human body image and a single basketball image in the first video frame image, the distance from the human body space coordinate corresponding to the at least one human body image to the basketball space coordinate corresponding to the single basketball image is not greater than a preset distance threshold;
(C) the non-first video frame image in the continuous video frame image set does not contain a human body image, or when at least one human body image is contained, aiming at any one human body image and a single basketball image in the non-first video frame images, the distance from the human body space coordinate corresponding to the any one human body image to the basketball space coordinate corresponding to the single basketball image is larger than the preset distance threshold;
(D) the acquisition time stamp of the Nth video frame image in the continuous video frame image set is not later than the trigger time stamp of the basketball induction signal;
the mechanical energy calculating unit is configured to calculate, for each group of two adjacent video frame images in the continuous video frame image set, a corresponding basketball mechanical energy E according to the following formula:
Figure BDA0002977393820000111
in the formula, m represents the weight of a basketball, d represents the distance from a previous basketball space coordinate to a later basketball space coordinate, the previous basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a previous video frame image, the later basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a later video frame image, the previous video frame image and the later video frame image are two video frame images which are sequenced in sequence according to a collecting timestamp in the two adjacent video frame images, and h represents the distance from the previous basketball space coordinate to the later basketball space coordinateBRepresenting the elevation, h, of the space coordinate of the basketball at the backAElevation, h, representing the spatial coordinates of the previous basketball1The elevation of the first basketball spatial coordinate is shown,the first basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in the first video frame image, tBRepresenting the acquisition time stamp, t, of said subsequent video frame imageARepresenting a capture timestamp of the previous video frame image, g representing a gravitational acceleration;
and the motion amount determining unit is used for determining the shooting motion amount of the athlete according to the earliest value, the maximum value, the average value or the middle value of the N-1 calculated basketball mechanical energy, wherein the earliest value is the value calculated according to the basketball mechanical energy corresponding to the first group of adjacent two video frame images in the sequence of the acquisition time.
For the working process, working details and technical effects of the foregoing apparatus provided in the second aspect of this embodiment, reference may be made to the method described in the first aspect or any one of the possible designs of the first aspect, which is not described herein again.
As shown in fig. 4, a third aspect of the present embodiment provides a computer device for executing the method according to any one of the first aspect or any one of the possible designs of the first aspect, and includes a memory, a processor and a transceiver, which are communicatively connected in sequence, where the memory is used for storing a computer program, the transceiver is used for transceiving a signal, and the processor is used for reading the computer program to execute the method according to any one of the possible designs of the first aspect or the first aspect. For example, the Memory may include, but is not limited to, a Random-Access Memory (RAM), a Read-Only Memory (ROM), a Flash Memory (Flash Memory), a First-in First-out (FIFO), and/or a First-in Last-out (FILO), and the like; the processor may not be limited to the microprocessor of the model number employing the STM32F105 family. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, working details, and technical effects of the foregoing computer device provided in the third aspect of this embodiment, reference may be made to the method in the first aspect or any one of the possible designs in the first aspect, which is not described herein again.
A fourth aspect of the present embodiment provides a storage medium storing instructions of the method according to any one of the possible designs of the first aspect or the first aspect, that is, the storage medium has instructions stored thereon, which when executed on a computer, perform the method according to any one of the possible designs of the first aspect or the first aspect. The storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, a flash disk and/or a Memory Stick (Memory Stick), etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, the working details, and the technical effects of the foregoing storage medium provided in the fourth aspect of this embodiment, reference may be made to the method in the first aspect or any one of the possible designs in the first aspect, which is not described herein again.
A fifth aspect of the present embodiments provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method as set forth in the first aspect or any one of the possible designs of the first aspect. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices.
The embodiments described above are merely illustrative, and may or may not be physically separate, if referring to units illustrated as separate components; if reference is made to a component displayed as a unit, it may or may not be a physical unit, and may be located in one place or distributed over a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: modifications may be made to the embodiments described above, or equivalents may be substituted for some of the features described. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Finally, it should be noted that the present invention is not limited to the above alternative embodiments, and that various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.

Claims (10)

1. A method for collecting shooting exercise quantity based on image recognition and induction of a backboard is characterized by comprising the following steps:
acquiring a shooting monitoring video collected by a binocular camera;
identifying whether a target image is contained or not aiming at each video frame image in the shooting monitoring video, and determining the space coordinate of a target object when the target image is identified to be contained, wherein the target image comprises a basketball image and a human body image, and the target object is a basketball or a human body corresponding to the target image;
extracting a continuous video frame image set which meets the following conditions (A) to (D) and corresponds to the basketball induction signals one by one from the shooting monitoring video according to the identification result of the target image, the positioning result of the target object and the basketball induction signals from the induction backboard:
(A) the continuous video frame image set comprises N video frame images, and each video frame image in the N video frame images comprises a single basketball image respectively, wherein N is a natural number not less than 2;
(B) the first video frame image in the continuous video frame image set further comprises at least one human body image, and for at least one human body image and a single basketball image in the first video frame image, the distance from the human body space coordinate corresponding to the at least one human body image to the basketball space coordinate corresponding to the single basketball image is not greater than a preset distance threshold;
(C) the non-first video frame image in the continuous video frame image set does not contain a human body image, or when at least one human body image is contained, aiming at any one human body image and a single basketball image in the non-first video frame images, the distance from the human body space coordinate corresponding to the any one human body image to the basketball space coordinate corresponding to the single basketball image is larger than the preset distance threshold;
(D) the acquisition time stamp of the Nth video frame image in the continuous video frame image set is not later than the trigger time stamp of the basketball induction signal;
for each group of two adjacent video frame images in the continuous video frame image set, calculating the corresponding basketball mechanical energy E according to the following formula:
Figure FDA0002977393810000011
in the formula, m represents the weight of a basketball, d represents the distance from a previous basketball space coordinate to a later basketball space coordinate, the previous basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a previous video frame image, the later basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a later video frame image, the previous video frame image and the later video frame image are two video frame images which are sequenced in sequence according to a collecting timestamp in the two adjacent video frame images, and h represents the distance from the previous basketball space coordinate to the later basketball space coordinateBRepresenting the elevation, h, of the space coordinate of the basketball at the backAHeight, h, representing the spatial coordinates of the previous basketball1The elevation of a first basketball space coordinate is represented, wherein the first basketball space coordinate is a basketball space coordinate, t, corresponding to a single basketball image in the first video frame imageBRepresenting the acquisition time stamp, t, of said subsequent video frame imageARepresenting a capture timestamp of the previous video frame image, g representing a gravitational acceleration;
and determining the shooting motion amount of the athlete according to the earliest value, the maximum value, the average value or the middle value of the N-1 calculated basketball mechanical energy, wherein the earliest value is the value calculated according to the basketball mechanical energy corresponding to the first group of adjacent two video frame images in the sequence before and after the acquisition time.
2. The method of claim 1, wherein identifying whether a target image is included for each video frame image in the shot monitoring video comprises:
importing a video frame image into a first detection model which is pre-trained, and then judging whether the video frame image contains a basketball image according to a detection result of the first detection model, wherein the first detection model adopts a fast R-CNN detection model, an SSD detection model or a YOLO detection model;
and importing a video frame image containing a basketball image into a second detection model which is pre-trained, and then judging whether the video frame image contains a human body image according to a detection result of the second detection model, wherein the second detection model adopts a Faster R-CNN detection model, an SSD detection model or a YOLO detection model.
3. The method of claim 1, wherein determining spatial coordinates of the target object upon identifying the target image as containing the target image comprises:
determining the distance from the target object to the origin of a camera coordinate system according to the binocular distance measuring principle of the binocular camera;
acquiring the coordinate position of the target object in a camera coordinate system according to the distance from the target object to the origin of the camera coordinate system and the plane coordinate of the target image in the video frame image;
and converting the coordinate position of the target object in a camera coordinate system into the space coordinate of the target object according to the installation position and the installation posture of the binocular camera.
4. The method of claim 1, wherein determining the amount of the player's shot movement based on the calculated earliest, largest, average, or median of the N-1 basketball's mechanical energy comprises:
identifying at least one field person corresponding to at least one human body image one by one according to at least one human body image in the first video frame image;
taking a live person of the at least one live person and closest to the first basketball spatial coordinate as a basketball player;
and determining the shooting motion quantity of the shooting player according to the earliest value, the maximum value, the average value or the middle value of the calculated N-1 basketball mechanical energy.
5. The method of claim 4, wherein identifying at least one athlete in one-to-one correspondence with at least one human body image from the at least one human body image in the first video frame image comprises:
intercepting a corresponding face image from the human body image;
and importing the face image into an identification model which finishes deep learning training, and then determining the identity of the person corresponding to the human body image according to the identification result of the identification model.
6. The method of claim 4, wherein identifying at least one athlete in one-to-one correspondence with at least one human body image from the at least one human body image in the first video frame image comprises:
and determining the identity of the person corresponding to the human body image according to the person tracking result based on the shooting monitoring video.
7. The method of claim 1, wherein the sensing backboard is a backboard with a plurality of basketball sensing sensors disposed thereon, wherein the basketball sensing sensors comprise a proximity sensor disposed on the backboard for sensing whether a basketball is approaching, a pressure/vibration sensor for sensing whether the backboard and the basketball collide, and/or a sensor for sensing whether a basketball is shot.
8. A device for collecting shooting motion quantity based on image recognition and induction backboard is characterized by comprising a video acquisition unit, a recognition positioning unit, a video frame extraction unit, a mechanical energy calculation unit and a motion quantity determination unit which are sequentially connected in communication;
the video acquisition unit is used for acquiring shooting monitoring videos collected by the binocular camera;
the identification and positioning unit is used for identifying whether a target image is included or not aiming at each video frame image in the shooting monitoring video, and determining the space coordinate of a target object when the target image is identified to be included, wherein the target image includes a basketball image and a human body image, and the target object is a basketball or a human body corresponding to the target image;
the video frame extraction unit is used for extracting a continuous video frame image set which meets the following conditions (A) to (D) and corresponds to the basketball induction signals one by one from the shooting monitoring video according to the identification result of the target image, the positioning result of the target object and the basketball induction signals from the induction backboard:
(A) the continuous video frame image set comprises N video frame images, and each video frame image in the N video frame images comprises a single basketball image respectively, wherein N is a natural number not less than 2;
(B) the first video frame image in the continuous video frame image set further comprises at least one human body image, and for at least one human body image and a single basketball image in the first video frame image, the distance from the human body space coordinate corresponding to the at least one human body image to the basketball space coordinate corresponding to the single basketball image is not greater than a preset distance threshold;
(C) the non-first video frame image in the continuous video frame image set does not contain a human body image, or when at least one human body image is contained, aiming at any one human body image and a single basketball image in the non-first video frame images, the distance from the human body space coordinate corresponding to the any one human body image to the basketball space coordinate corresponding to the single basketball image is larger than the preset distance threshold;
(D) the acquisition time stamp of the Nth video frame image in the continuous video frame image set is not later than the trigger time stamp of the basketball induction signal;
the mechanical energy calculating unit is configured to calculate, for each group of two adjacent video frame images in the continuous video frame image set, a corresponding basketball mechanical energy E according to the following formula:
Figure FDA0002977393810000031
in the formula, m represents the weight of a basketball, d represents the distance from a previous basketball space coordinate to a later basketball space coordinate, the previous basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a previous video frame image, the later basketball space coordinate is a basketball space coordinate corresponding to a single basketball image in a later video frame image, the previous video frame image and the later video frame image are two video frame images which are sequenced in sequence according to a collecting timestamp in the two adjacent video frame images, and h represents the distance from the previous basketball space coordinate to the later basketball space coordinateBRepresenting the elevation, h, of the space coordinate of the basketball at the backAHeight, h, representing the spatial coordinates of the previous basketball1The elevation of a first basketball space coordinate is represented, wherein the first basketball space coordinate is a basketball space coordinate, t, corresponding to a single basketball image in the first video frame imageBRepresenting the acquisition time stamp, t, of said subsequent video frame imageARepresenting a capture timestamp of the previous video frame image, g representing a gravitational acceleration;
and the motion amount determining unit is used for determining the shooting motion amount of the athlete according to the earliest value, the maximum value, the average value or the middle value of the N-1 calculated basketball mechanical energy, wherein the earliest value is the value calculated according to the basketball mechanical energy corresponding to the first group of adjacent two video frame images in the sequence of the acquisition time.
9. A computer device comprising a memory, a processor and a transceiver communicatively connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive signals, and the processor is configured to read the computer program and perform the method according to any one of claims 1 to 7.
10. A storage medium having stored thereon instructions for performing a method according to any one of claims 1-7 when the instructions are run on a computer.
CN202110277974.4A 2021-03-15 2021-03-15 Method and device for collecting shooting exercise amount, computer equipment and storage medium Active CN113011310B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110277974.4A CN113011310B (en) 2021-03-15 2021-03-15 Method and device for collecting shooting exercise amount, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110277974.4A CN113011310B (en) 2021-03-15 2021-03-15 Method and device for collecting shooting exercise amount, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113011310A CN113011310A (en) 2021-06-22
CN113011310B true CN113011310B (en) 2022-03-11

Family

ID=76407538

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110277974.4A Active CN113011310B (en) 2021-03-15 2021-03-15 Method and device for collecting shooting exercise amount, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113011310B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420715B (en) * 2021-07-15 2023-03-24 临沂大学 Basketball player motion capture analysis device based on industrial camera
CN114949795A (en) * 2022-05-09 2022-08-30 乐跑体育互联网（武汉）有限公司 Kinect skeleton data-based exercise amount monitoring method, device and system
CN114998425B (en) * 2022-08-04 2022-10-25 吉奥时空信息技术股份有限公司 Target object geographic coordinate positioning method and device based on artificial intelligence

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017022286A1 (en) * 2015-08-03 2017-02-09 ソニー株式会社 Information processing system, information processing method, and recording medium
CN109862949A (en) * 2016-08-23 2019-06-07 沛勒尔维珍公司 System and method for tracking rebounder's performance
CN111539294A (en) * 2020-04-17 2020-08-14 广东世宇科技股份有限公司 Shooting detection method and device, electronic equipment and computer readable storage medium
CN111724414A (en) * 2020-06-23 2020-09-29 宁夏大学 Basketball movement analysis method based on 3D attitude estimation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017022286A1 (en) * 2015-08-03 2017-02-09 ソニー株式会社 Information processing system, information processing method, and recording medium
CN109862949A (en) * 2016-08-23 2019-06-07 沛勒尔维珍公司 System and method for tracking rebounder's performance
CN111539294A (en) * 2020-04-17 2020-08-14 广东世宇科技股份有限公司 Shooting detection method and device, electronic equipment and computer readable storage medium
CN111724414A (en) * 2020-06-23 2020-09-29 宁夏大学 Basketball movement analysis method based on 3D attitude estimation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
智能运动监测系统的设计;王力，周妮娜;《自动化技术与应用》;20151231;第34卷(第11期);全文 *

Also Published As

Publication number Publication date
CN113011310A (en) 2021-06-22

Similar Documents

Publication Publication Date Title
CN113011310B (en) Method and device for collecting shooting exercise amount, computer equipment and storage medium
US10607349B2 (en) Multi-sensor event system
US11348255B2 (en) Techniques for object tracking
CN108229294B (en) Motion data acquisition method and device, electronic equipment and storage medium
AU2016293616B2 (en) Integrated sensor and video motion analysis method
CN103106411A (en) Tennis motion capturing and analyzing method
CN108090421B (en) Athlete athletic ability analysis method
CN110418114B (en) Object tracking method and device, electronic equipment and storage medium
US20160042227A1 (en) System and method for determining view invariant spatial-temporal descriptors for motion detection and analysis
US11624825B2 (en) Object tracking
US20160370239A1 (en) Body Motion Assessment Using Image Analysis
US20230419731A1 (en) Detection of kinetic events and mechanical variables from uncalibrated video
CN112465855B (en) Passenger flow statistical method, device, storage medium and equipment
CN101826155B (en) Method for identifying act of shooting based on Haar characteristic and dynamic time sequence matching
CN104941168A (en) Football match replay system and replay method based on wearable equipment
CN112907618B (en) Multi-target sphere motion trail tracking method and system based on rigid body collision characteristics
CN110059653A (en) A kind of method of data capture and device, electronic equipment, storage medium
Nelikanti et al. An optimization based deep lstm predictive analysis for decision making in cricket
Lin et al. Design and implement a mobile badminton stroke classification system
CN110235191B (en) Detection system and method
CN114882408A (en) Monocular vision-based automatic drop point reporting method and system
CN107866058A (en) A kind of table tennis system based on multi-level mapping parsing positioning
CN113082680A (en) Automatic judgment system for ball out of bound of ball game based on machine vision
KR20210010408A (en) Apparatus and Method for Vision-Sensor Data Based Golf Swing Trace Tracking and Analysis
CN115273243B (en) Fall detection method, device, electronic equipment and computer readable storage medium

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
GR01 Patent grant
GR01 Patent grant