CN114742974A

CN114742974A - Player determination method and device, electronic equipment and storage medium

Info

Publication number: CN114742974A
Application number: CN202210449343.0A
Authority: CN
Inventors: 金代圣; 赵海宇
Original assignee: Beijing Sensetime Technology Development Co Ltd
Current assignee: Beijing Sensetime Technology Development Co Ltd
Priority date: 2022-04-26
Filing date: 2022-04-26
Publication date: 2022-07-12

Abstract

The present disclosure relates to a player determination method and apparatus, an electronic device, and a storage medium by determining a three-dimensional information sequence of a target course, wherein each three-dimensional information includes an object point cloud of a target object in a three-dimensional course coordinate system, and a player point cloud of at least one player in the three-dimensional course coordinate system. And determining the motion state of the target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each three-dimensional information. And under the condition that the three-dimensional information corresponds to the movement state shooting failure state of the target object, determining the three-dimensional information corresponding to the shooting failure state as target three-dimensional information, and determining a target player changing the movement state of the target object next time according to the positions of the object point cloud and at least one player point cloud in the three-dimensional information after the target three-dimensional information. The basketball game is monitored through the computer vision technology, and the efficiency and the accuracy of the process of determining the basketball players robbing the backboard in the game are improved.

Description

Player determination method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a golfer, an electronic device, and a storage medium.

Background

At present, computer vision technology is widely applied to various fields, such as human face unlocking, pedestrian re-recognition, intelligent home, intelligent medical treatment and other application scenes, and can be used for counting and processing data for human beings by using a computer, so that the working efficiency and the living efficiency under various application scenes are improved. However, in the ball game of multi-player sports such as basketball, soccer and hockey, since a plurality of players exist in the field, it is often difficult to recognize the action of each player and the contact with the ball by a computer in a dense crowd. Therefore, it is currently difficult to apply computer vision to ball games.

Disclosure of Invention

The disclosure provides a player determination method and device, electronic equipment and a storage medium, and aims to identify a basketball grabbing player in a basketball game through a computer vision technology.

According to a first aspect of the present disclosure, there is provided a player determination method, including:

determining a three-dimensional information sequence of a target court, wherein the three-dimensional information sequence comprises at least two pieces of three-dimensional information which are arranged according to a time sequence, and the three-dimensional information comprises an object point cloud of a target object in a three-dimensional court coordinate system and a player point cloud of at least one player in the three-dimensional court coordinate system;

determining the motion state of a target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each three-dimensional information;

responding to the fact that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state, and determining that the three-dimensional information corresponding to the shooting failure state is target three-dimensional information;

and determining a target player according to the positions of the object point cloud and the at least one player point cloud in the three-dimensional information with the time sequence position behind the target three-dimensional information, wherein the target player is the player changing the motion state of the target object next time.

In one possible implementation manner, the determining the three-dimensional information sequence of the target course includes:

acquiring the three-dimensional information of the target court in real time;

and arranging the acquired three-dimensional information according to a time sequence to obtain a three-dimensional information sequence of the target court.

In a possible implementation manner, the acquiring, in real time, the three-dimensional information of the target course includes:

the method comprises the steps of acquiring at least two-dimensional image sequences corresponding to different acquisition visual angles of a target court in real time, wherein the at least two-dimensional image sequences are obtained by simultaneously acquiring images of the target court through at least two image acquisition devices, and the target court comprises a target object and at least one player;

and determining corresponding three-dimensional information according to the at least two-dimensional images.

In one possible implementation manner, the determining, according to the at least two-dimensional images, corresponding three-dimensional information includes:

determining a first feature point of the target object in each two-dimensional image and a second feature point of each player;

determining an object point cloud of the target object in the three-dimensional court coordinate system according to the first characteristic point, and determining a player point cloud of each player in the three-dimensional court coordinate system according to the second characteristic point of each player;

and determining corresponding three-dimensional information according to the object point cloud of the target object in the three-dimensional court coordinate system and the player point cloud of each player in the three-dimensional court coordinate system.

In one possible implementation, the determining the object point cloud of the target object in the three-dimensional course coordinate system according to the first feature point and the determining the player point cloud of the player in the three-dimensional course coordinate system according to the second feature point of each player includes:

determining the attitude parameters of the image acquisition devices for acquiring each two-dimensional image sequence in the three-dimensional court coordinate system;

determining a first three-dimensional feature point of a target object in the three-dimensional court coordinate system according to a first feature point of the target object in the at least two-dimensional images based on a posture parameter and an attribute parameter corresponding to an image acquisition device for acquiring each two-dimensional image, and determining a second three-dimensional feature point of each target object in the three-dimensional court coordinate system according to a second feature point of each player in the at least two-dimensional images;

and determining the object point cloud according to the first three-dimensional characteristic point of the target object, and determining the player point cloud of each player according to the second three-dimensional characteristic point of each player.

In a possible implementation manner, the determining, according to the position of the object point cloud in the three-dimensional course coordinate system in each piece of three-dimensional information, a motion state of a target object corresponding to each piece of three-dimensional information includes:

determining the object state of a target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each three-dimensional information;

and determining that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state in response to that the object state of the target object corresponding to the three-dimensional information is a shooting non-scoring state.

In a possible implementation manner, the determining, according to the position of the object point cloud in the three-dimensional course coordinate system in each piece of three-dimensional information, an object state of a target object corresponding to each piece of three-dimensional information includes:

determining a ball frame plane representing a ball frame in the target court in the three-dimensional court coordinate system and a state judgment plane parallel to the ball frame plane, wherein the state judgment plane is positioned below the ball frame plane and has a size larger than the ball frame plane;

determining a target three-dimensional characteristic point corresponding to the object point cloud in each three-dimensional information;

under the condition that a connecting line of two target three-dimensional feature points adjacent in time sequence passes through the state judgment plane, sequentially determining the target three-dimensional feature points of the object point cloud in each three-dimensional information backwards in the three-dimensional information sequence from the corresponding time of the target three-dimensional feature points at the later time;

and under the condition that the height of the previous target three-dimensional feature point in two adjacent target three-dimensional feature points in time sequence is higher than the ball frame plane, the height of the next target three-dimensional feature point is lower than the ball frame plane, and the connecting line of the two target three-dimensional feature points is not intersected with the ball frame plane, determining the object state of the target object corresponding to the target three-dimensional feature point at the later time sequence position as a shooting unbearable state.

In one possible implementation, the determining a target player according to the positions of the object point cloud and the at least one player point cloud in the three-dimensional information whose time sequence position follows the target three-dimensional information includes:

determining whether each piece of three-dimensional information in the three-dimensional information sequence has a player point cloud meeting a preset distance condition or not according to the position of the object point cloud from the moment corresponding to the target three-dimensional information;

determining the player point clouds meeting the preset distance condition as candidate point clouds;

and in response to the fact that candidate point clouds exist in the three-dimensional information of the continuous preset number and correspond to the same player, determining the player corresponding to the candidate point clouds as the target player.

In a possible implementation manner, the determining, from a time corresponding to the target three-dimensional information, whether there is a player point cloud satisfying a preset distance condition in each of the three-dimensional information in the three-dimensional information sequence according to the position of the object point cloud includes:

starting from the moment corresponding to the target three-dimensional information, acquiring the position of an object point cloud of the three-dimensional information in the three-dimensional information sequence and the position of the at least one player point cloud;

and determining that the player point cloud meets a preset distance condition in response to that the shortest distance between the object point cloud in the three-dimensional information and a characteristic region in the player point cloud is smaller than a distance threshold, wherein the characteristic region represents the hand of the player point cloud corresponding to the body of the player.

In one possible implementation manner, before determining a player corresponding to a candidate point cloud as a target player in response to that the candidate point cloud exists in a continuous preset number of three-dimensional information and corresponds to the same player, determining the target player according to the positions of the object point cloud and the at least one player point cloud in three-dimensional information of which the time sequence position is behind the target three-dimensional information, further comprising:

determining the position of a target three-dimensional feature point corresponding to an object point cloud in the three-dimensional information sequence from the moment corresponding to the target three-dimensional information;

and determining that the target player does not exist in response to the position of the target three-dimensional feature point meeting the out-of-bounds condition. According to a second aspect of the present disclosure, there is provided a player determination device including:

the sequence determination module is used for determining a three-dimensional information sequence of a target court, wherein the three-dimensional information sequence comprises at least two pieces of three-dimensional information which are arranged according to a time sequence, and the three-dimensional information comprises an object point cloud of a target object in a three-dimensional court coordinate system and a player point cloud of at least one player in the three-dimensional court coordinate system;

the state determining module is used for determining the motion state of a target object corresponding to each piece of three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each piece of three-dimensional information;

the information determining module is used for responding to the situation that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state, and determining the three-dimensional information corresponding to the shooting failure state as target three-dimensional information;

and the player determining module is used for determining a target player according to the positions of the object point cloud and the at least one player point cloud in the three-dimensional information of which the time sequence position is behind the target three-dimensional information, wherein the target player is the player changing the motion state of the target object next time.

In one possible implementation, the sequence determining module includes:

the information acquisition submodule is used for acquiring the three-dimensional information of the target court in real time;

and the sequence determining sub-module is used for arranging the acquired three-dimensional information according to a time sequence to obtain a three-dimensional information sequence of the target court.

In one possible implementation manner, the information obtaining sub-module includes:

the system comprises an image acquisition unit, a storage unit and a display unit, wherein the image acquisition unit is used for acquiring at least two-dimensional image sequences corresponding to different acquisition visual angles of a target court in real time, the at least two-dimensional image sequences are obtained by simultaneously acquiring images of the target court through at least two image acquisition devices, and the target court comprises a target object and at least one player;

and the information determining unit is used for determining corresponding three-dimensional information according to the at least two-dimensional images.

In one possible implementation manner, the information determining unit includes:

a feature point determination subunit, configured to determine a first feature point of the target object in each of the two-dimensional images, and a second feature point of each of the players;

a point cloud determining subunit, configured to determine an object point cloud of the target object in the three-dimensional court coordinate system according to the first feature point, and determine a player point cloud of each player in the three-dimensional court coordinate system according to the second feature point of the player;

and the information determining subunit is used for determining corresponding three-dimensional information according to the object point cloud of the target object in the three-dimensional court coordinate system and the player point cloud of each player in the three-dimensional court coordinate system.

In one possible implementation, the point cloud determining subunit includes:

the parameter determining subunit is used for determining the attitude parameters of the image acquisition devices for acquiring each two-dimensional image sequence in the three-dimensional court coordinate system;

the characteristic point matching subunit is used for determining a first three-dimensional characteristic point of a target object in the three-dimensional court coordinate system according to a first characteristic point of the target object in the at least two-dimensional images on the basis of a posture parameter and an attribute parameter corresponding to an image acquisition device for acquiring each two-dimensional image, and determining a second three-dimensional characteristic point of each target object in the three-dimensional court coordinate system according to a second characteristic point of each player in the at least two-dimensional images;

and the point cloud matching subunit is used for determining the object point cloud according to the first three-dimensional characteristic point of the target object and determining the player point cloud of each player according to the second three-dimensional characteristic point of each player.

In one possible implementation, the state determination module includes:

the first state determining submodule is used for determining the object state of a target object corresponding to each piece of three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each piece of three-dimensional information;

and the second state determining submodule is used for determining that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state in response to the object state of the target object corresponding to the three-dimensional information being a shooting non-scoring state.

In one possible implementation manner, the first state determining sub-module includes:

a plane determining unit, configured to determine a ball frame plane representing a ball frame in the target ball field in the three-dimensional ball field coordinate system, and a state determining plane parallel to the ball frame plane, where the state determining plane is located below the ball frame plane and has a size larger than the ball frame plane;

the first characteristic point determining unit is used for determining a target three-dimensional characteristic point corresponding to the object point cloud in each three-dimensional information;

a second feature point determining unit, configured to determine, sequentially and backwards in the three-dimensional information sequence, a target three-dimensional feature point of the object point cloud in each piece of three-dimensional information, starting from a time corresponding to a later target three-dimensional feature point when a connection line between two target three-dimensional feature points adjacent in time series passes through the state determination plane;

and the state determining unit is used for determining that the object state of the target object corresponding to the target three-dimensional feature point at the later time sequence position is the shooting non-scoring state under the condition that the height of the former target three-dimensional feature point in two adjacent target three-dimensional feature points in time sequence is higher than the ball frame plane, the height of the latter target three-dimensional feature point is lower than the ball frame plane, and the connecting line of the two target three-dimensional feature points is not intersected with the ball frame plane.

In one possible implementation, the player determination module includes:

the point cloud screening sub-module is used for determining whether each piece of three-dimensional information in the three-dimensional information sequence has a player point cloud meeting a preset distance condition from the moment corresponding to the target three-dimensional information according to the position of the object point cloud;

a candidate point cloud determining submodule, configured to determine a player point cloud satisfying the preset distance condition as a candidate point cloud;

and the target point cloud determining sub-module is used for responding to the situation that candidate point clouds exist in the three-dimensional information with the continuous preset number and correspond to the same player, and determining the player corresponding to the candidate point clouds as a target player.

In one possible implementation, the point cloud filtering sub-module includes:

the position judging unit is used for acquiring the position of the object point cloud of the three-dimensional information and the position of the point cloud of the at least one player in the three-dimensional information sequence from the moment corresponding to the target three-dimensional information;

and the point cloud screening unit is used for responding that the shortest distance between the object point cloud in the three-dimensional information and the characteristic area in the player point cloud is smaller than a distance threshold value, determining that the player point cloud meets a preset distance condition, and representing the characteristic area on the hand part of the player point cloud corresponding to the body of the player.

In one possible implementation manner, before determining a player corresponding to a candidate point cloud as a target player in response to that the candidate point cloud exists in a continuous preset number of three-dimensional information and corresponds to the same player, the player determination module further includes:

the position determining submodule is used for determining the position of a target three-dimensional characteristic point corresponding to an object point cloud in the three-dimensional information sequence from the moment corresponding to the target three-dimensional information;

and the out-of-range judgment submodule is used for responding to the situation that the position of the target three-dimensional feature point meets the out-of-range condition and determining that the target player does not exist.

According to a third aspect of the present disclosure, there is provided an electronic device comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

According to a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

In the embodiment of the disclosure, the basketball game is monitored through a computer vision technology, so that the efficiency and the accuracy of the process of determining the basketball backboard grabbing player in the ball game are improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

FIG. 1 illustrates a flow chart of a player determination method according to an embodiment of the present disclosure;

FIG. 2 illustrates a schematic diagram for determining a state of an object in accordance with an embodiment of the disclosure;

FIG. 3 shows a schematic diagram of a player determination device according to an embodiment of the present disclosure;

FIG. 4 shows a schematic diagram of an electronic device in accordance with an embodiment of the disclosure;

fig. 5 shows a schematic diagram of another electronic device according to an embodiment of the present disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

In one possible implementation manner, the player determination method of the embodiment of the present disclosure may be executed by an electronic device such as a terminal device or a server. The terminal device may be a fixed or mobile terminal such as a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, and a wearable device. The server may be a single server or a server cluster of multiple servers. The player determination method of the embodiments of the present disclosure may be implemented by a processor in the electronic device invoking computer readable instructions stored in a memory.

The basketball game application method and device can be applied to any application scene for judging the basketball of the basketball game, for example, the application scene of a basketball player who robs the basketball is identified, or the application scene of the goal types of different players in the game process is counted.

Fig. 1 shows a flowchart of a player determination method according to an embodiment of the present disclosure, and as shown in fig. 1, the player determination method of an embodiment of the present disclosure may include the following steps S10-S40.

And step S10, determining the three-dimensional information sequence of the target court.

In one possible implementation, the three-dimensional information sequence used to record the real-time dynamics in the target course is determined by the electronic device. The target court comprises a target object and at least one player, the target object is used for representing balls in the target court, and the target object is different under different application scenes. For example, in the case where the target court is a basketball court, the target object is a basketball. In the case where the target course is a soccer field, the target object is a soccer ball. In the case where the target course is a hockey course, the target object is a hockey puck. Alternatively, the three-dimensional information sequence may be a dynamically updated sequence including at least two pieces of three-dimensional information arranged in time series, that is, the electronic device may determine the three-dimensional information in real time during execution of the player determination method and update the determined three-dimensional information into the three-dimensional information sequence according to the time series.

Optionally, each three-dimensional information in the three-dimensional information sequence has a corresponding time for characterizing the position of the target object and the at least one player in the target course at the corresponding time. Wherein each three-dimensional information may represent the position of the target court by a three-dimensional court coordinate system, and may include an object point cloud of the target object in the three-dimensional court coordinate system, and a player point cloud of the at least one player in the three-dimensional court coordinate system. The three-dimensional court coordinate system is used for representing the space where the target court is located and can be a world coordinate system. Or, the electronic device may further determine the three-dimensional court coordinate system according to the plane where the target court is located, for example, taking one corner of the target court as the origin of the three-dimensional coordinate system, taking the straight lines where the length and the width of the target court are located as the x axis and the y axis, respectively, and taking the straight line perpendicular to the plane where the target court is located as the z axis to determine the three-dimensional court coordinate system of the target court.

In a possible implementation manner, the electronic device may obtain the three-dimensional information sequence of the target court by obtaining the three-dimensional information of the target court in real time and then sorting the obtained three-dimensional information according to a time sequence. Optionally, each piece of three-dimensional information may be determined by at least two-dimensional images obtained by acquiring the target course through image acquisition devices at different viewing angles, that is, the three-dimensional information corresponding to the moment is determined by acquiring two-dimensional images of the target course at different angles at the same moment. Optionally, in the process of determining the three-dimensional information in real time, the electronic device may acquire at least two-dimensional images of the target course in real time, which correspond to different collection viewing angles. The two-dimensional images are acquired by simultaneously acquiring images of a target court through at least two image acquisition devices, and the target court comprises a target object and at least one player. And determining corresponding three-dimensional information according to the at least two-dimensional images.

Optionally, the at least two-dimensional images may be acquired by image acquisition devices disposed at different positions of the target court, and each image acquisition device may perform image acquisition at the same time according to the same acquisition rule or acquisition signal. For example, at least two image capturing devices on the target court can perform image capturing on the target court according to the same image capturing frequency to obtain a plurality of groups of two-dimensional images with a time sequence, wherein each group of two-dimensional images comprises at least two-dimensional images.

Further, for at least two-dimensional images at the same moment, the target object characteristic points and the characteristic points of at least one player included in the two-dimensional images can be extracted, and the position of the target object and each player in the target court at the current moment, namely the object point cloud of the target object and the player point cloud of each player, can be obtained by carrying out triangulation based on the characteristic points. That is, after acquiring at least two-dimensional images at the same time, the electronic device may determine a first feature point of the target object and a second feature point of each player in each two-dimensional image. And further determining object point clouds of the target objects in a three-dimensional court coordinate system according to the first characteristic points of at least two-dimensional images corresponding to the same time in at least two groups of two-dimensional image sequences, determining player point clouds of players in the three-dimensional court coordinate system according to the second characteristic points of the players, and determining corresponding three-dimensional information according to the object point clouds of the target objects in the three-dimensional court coordinate system and the player point clouds of the players in the three-dimensional court coordinate system at each time.

Optionally, the plurality of first feature points of the target object in each two-dimensional image may be obtained by performing object identification on the two-dimensional image to obtain an area where the target object is located, and then performing feature point identification on the area to obtain the plurality of first feature points of the target object. Meanwhile, object recognition is carried out on each player to obtain an area where the player is located, and then feature point recognition is carried out on the area to obtain a plurality of second feature points of each player. Wherein, can also discern at least one in every sportsman's face and the ball clothing respectively, obtain including sportsman identity and sportsman's at least one in the battle. Alternatively, the same player in different two-dimensional images in the sequence of two-dimensional images may be determined by re-recognition techniques.

In one possible implementation manner, the electronic device may match the three-dimensional feature points according to two-dimensional feature points in different two-dimensional images at the same time, so as to obtain an object point cloud and a player point cloud of the target object and the players in the three-dimensional court coordinate system according to the three-dimensional feature points. Alternatively, the electronic device may first determine the pose parameters of the image capture device capturing each two-dimensional image in the three-dimensional court coordinate system. Based on the posture parameters and the attribute parameters corresponding to the image acquisition equipment for acquiring each two-dimensional image, determining first three-dimensional feature points of the target object in the three-dimensional court coordinate system according to a plurality of first feature points of the target object in at least two-dimensional images, and determining second three-dimensional feature points of each player in the three-dimensional court coordinate system according to second feature points of each player in at least two-dimensional images. And determining object point clouds according to the first three-dimensional characteristic points of the target object, and determining player point clouds of players according to the second three-dimensional characteristic points of each player.

The attitude parameters of the image acquisition equipment for acquiring each two-dimensional image in the three-dimensional court coordinate system are camera external parameters, and can include translation offset and rotation offset of the image acquisition equipment in the three-dimensional court coordinate system. The attribute parameters of the image acquisition equipment are camera internal parameters and can comprise a focal length, an imaging origin and distortion parameters. The electronic device can determine the corresponding ray of each first characteristic point and each second characteristic point in the three-dimensional court coordinate system according to the attitude parameter and the attribute parameter of the corresponding image acquisition device, and then determine the first three-dimensional characteristic point or the second three-dimensional characteristic point according to the intersection point of the rays of the first characteristic point or the second characteristic point which have the matching relationship in different two-dimensional images acquired at the same moment.

Alternatively, the matching relationship may be determined by calculating the similarity of the feature points in different two-dimensional images acquired at the same time. For example, the electronic device may acquire descriptors corresponding to the first feature point and the second feature point in different two-dimensional images acquired at the same time, calculate the similarity of the first feature point in the different two-dimensional images based on the corresponding descriptors, and obtain the first feature point and the second feature point having a matching relationship in the different two-dimensional images based on the similarity of the second feature point in the different two-dimensional images. The descriptor is a feature vector for recording features of corresponding feature points, and the vector distance can be directly calculated and determined based on the similarity calculation mode of the descriptor.

In a possible implementation manner, the electronic device may also obtain the three-dimensional information sequence of the target court in other manners, for example, directly obtain the three-dimensional information generated by other electronic devices in real time to obtain the three-dimensional information sequence. Or the electronic device can also directly acquire the three-dimensional images in the target court through the three-dimensional camera to obtain the corresponding three-dimensional information, and determine the three-dimensional information sequence according to the acquisition time of the three-dimensional images.

Step S20, determining the motion state of the target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each three-dimensional information.

In a possible implementation manner, after determining the three-dimensional information sequence, the electronic device may determine, according to the position of the object point cloud in each three-dimensional information in the three-dimensional court coordinate system, a motion state of the target object corresponding to each three-dimensional information in the three-dimensional information sequence, that is, a motion state of the target object at the time corresponding to each three-dimensional information. Alternatively, the motion state may represent the state of the target object in the target course, varying according to the player's actions. For example, in different application scenarios, the motion state may include a pass state, a ball-in state, a shot score state, a shot not score state, and the like.

Alternatively, the motion state of the target object may be determined in any manner by the embodiments of the present disclosure. For example, a candidate three-dimensional information and a preset number of adjacent three-dimensional information may be directly input into the trained state judgment model, and a motion state corresponding to the candidate three-dimensional information may be output. Or, the electronic device may further determine whether the object state of the target object is the shooting state, and determine the scoring state corresponding to the shooting state according to the three-dimensional information after the three-dimensional information corresponding to the shooting state when the object state of the target object is the shooting state. For example, the electronic device may determine the object state of the target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional court coordinate system in each three-dimensional information. And determining that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state in response to the object state of the target object corresponding to the three-dimensional information being a shooting non-scoring state. The non-scoring state of the shooting can be determined in a segmented manner, namely the determining process can comprise the step of determining the scoring state corresponding to the shooting state according to the three-dimensional information of the corresponding moment after the corresponding moment of the shooting state. Further, in response to the score state being the no-score state, the motion state of the target object corresponding to the three-dimensional information corresponding to the no-score state is determined to be a shooting failure state.

Further, the electronic device may determine the object state of each three-dimensional information corresponding to the target object in any manner. For example, the object state may be determined directly according to the position of the object point cloud in each three-dimensional information, or according to the position change of the three-dimensional point cloud in each three-dimensional information and the three-dimensional point cloud in the temporally adjacent three-dimensional information.

For example, the electronic device may determine a position change of the target object in the target course according to the three-dimensional point cloud position in the current three-dimensional information and the three-dimensional point cloud position in the previous three-dimensional information in time sequence, so as to determine an object state corresponding to the target object in the current three-dimensional information according to the position change. For example, the electronic device may determine a frame plane representing a ball in the target course in the three-dimensional course coordinate system, and a state determination plane parallel to the frame plane, the state determination plane being located below the frame plane and having a size larger than the frame plane. And determining target three-dimensional characteristic points corresponding to the object point clouds in each three-dimensional information. And sequentially determining the target three-dimensional feature points of the object point cloud in each three-dimensional information backwards in the three-dimensional information sequence from the corresponding time of the target three-dimensional feature points at the later time under the condition that the connecting line of two adjacent target three-dimensional feature points in the time sequence passes through the state judgment plane. And under the condition that the height of the previous target three-dimensional feature point in two adjacent target three-dimensional feature points in the time sequence is higher than the plane of the ball frame, the height of the next target three-dimensional feature point is lower than the plane of the ball frame, and the connecting line of the two target three-dimensional feature points is not intersected with the plane of the ball frame, determining the object state of the target object corresponding to the target three-dimensional feature point at the later time sequence position as the goal-shooting non-scoring state. The process of the electronic device determining the state judgment plane may be to determine the position of at least one ball frame in the target court in the three-dimensional court coordinate system. And determining a preset distance below each ball frame in a three-dimensional court coordinate system, taking a preset size plane area parallel to the plane where the ball frame is located as a state judgment plane, and projecting the orthographic projection of the ball frame in the state judgment plane.

For example, when the disclosed embodiment is applied to detecting the shooting state of a basketball in a basketball game, it is also possible to previously cut the plane of the rim in the target course and set a state judgment plane having a size larger than the plane of the rim below the plane of the rim in the three-dimensional course coordinate system for judging the object state of the target object by position. Optionally, the state determination plane is a plane area that is located below the basketball rim in the three-dimensional court coordinate system by a preset distance and is parallel to the plane where the basketball rim is located. The size and the shape of the state judgment plane can be preset and are positioned right below the basketball rim, so that the orthographic projection of the basketball rim along the z-axis can fall in the state judgment plane. The electronic equipment judges that the basketball moves from the lower basket to the shooting state according to the movement condition of the basketball under the condition that the connecting line of the two adjacent target three-dimensional feature points passes through the state judgment plane, and further judges whether the connecting line of the two target three-dimensional feature points passes through the ball frame plane or not under the condition that one of the two adjacent target three-dimensional feature points is higher than the ball frame plane and the other one is lower than the ball frame plane after the corresponding moment of the shooting state in time sequence. The object state is determined to be a shooting non-scoring state when the ball frame plane is not passed through, and the object state is determined to be a shooting scoring state when the ball frame plane is passed through. The target three-dimensional feature point corresponding to the object point cloud may be any point capable of representing the position feature of the object point cloud, for example, the coordinate mean value of a plurality of three-dimensional points in the object point cloud in each piece of three-dimensional information may be calculated by an electronic device to obtain the target three-dimensional feature point.

That is, in the case where the target three-dimensional feature point is above the rim in the previous three-dimensional information and the target three-dimensional feature point is below the rim in the next three-dimensional information, and the connecting line does not pass through the rim, the electronic device determines that the shooting action of the basketball is completed, but the basketball does not pass through the rim, and therefore the basketball does not score.

FIG. 2 illustrates a schematic diagram of determining a state of an object according to an embodiment of the disclosure. As shown in fig. 2, the electronic device determines the position of the target three-dimensional feature point of the object point cloud in each three-dimensional information, and determines whether the connection line of two adjacent target three-dimensional feature points passes through a preset state judgment plane 20. When the connecting line of the adjacent target three-dimensional feature point 21 and the target three-dimensional feature point 22 passes through the state judgment plane 20, the object state of the target three-dimensional feature point 22 which is later in time sequence is determined to be the shooting state. Further, starting from the time corresponding to the target three-dimensional feature point 22 positioned later in time sequence, the target three-dimensional feature point position of the object point cloud in each piece of three-dimensional information is continuously determined backwards until the height of the previous target three-dimensional feature point 24 in the two adjacent target three-dimensional feature points is higher than the spherical frame plane 23, the height of the next target three-dimensional feature point 25 is lower than the spherical frame plane 23, and under the condition that the connecting line of the two target three-dimensional feature points does not intersect with the spherical frame plane 23, the goal of shooting is determined to be not scored, that is, the goal of shooting is determined to be not scored. Optionally, the state determination plane 20 is located below the ball frame plane 23 and is parallel to the ball frame plane 23. Further, since the basketball usually passes through the state determination plane twice in the processes of upward throwing and downward falling in the process of shooting, in order to avoid that one shooting action is recognized twice, the electronic device may further set a time threshold, and merge two shooting states into one when the duration between the times corresponding to the three-dimensional information of which the two object states are shooting states is less than the time threshold. Optionally, the electronic device may further determine that a state corresponding to the three-dimensional information at the previous time is a shooting state, and a state corresponding to the three-dimensional information at the later time is a non-shooting state, so as to further reduce the calculation amount in the subsequent process of determining the position of the key point.

For example, the electronic device may also directly determine the object state corresponding to the three-dimensional information according to the position of the object point cloud itself in each piece of three-dimensional information. Optionally, the location of at least one frame in the target course in the three-dimensional course coordinate system is determined. And determining the shortest distance between the point cloud position of the object and the position of the ball frame in each piece of three-dimensional information. And determining that the target object in the three-dimensional information is in a shooting state in response to that the shortest distance between the point cloud position of the object and the position of the ball frame is smaller than a distance threshold, and judging the object state of the target object according to the relative position of the target object and the plane of the ball frame in the three-dimensional information which follows in time sequence. The shortest distance between the object point cloud position and the ball frame position can be obtained by calculating the distance between a target three-dimensional feature point in the object point cloud and a ball frame feature point, the target three-dimensional feature point can be obtained by calculating the coordinate mean value of a plurality of three-dimensional points in the object point cloud in each piece of three-dimensional information through electronic equipment, and the ball frame feature point can be obtained by calculating the coordinate mean value of each three-dimensional feature point of the ball frame in a three-dimensional court coordinate system.

In a possible implementation manner, the embodiment of the present disclosure may also determine the object state of the target object in each three-dimensional information in other manners. For example, each piece of three-dimensional information and a preset number of pieces of three-dimensional information adjacent in time sequence are input into a trained state judgment model, and the state judgment model judges the object state of the current three-dimensional information according to the change condition of the object point cloud in the three-dimensional information and outputs the object state.

Further, the electronic device may simultaneously perform the determination of the state of the target object in a plurality of ways. In order to avoid repeated identification, the electronic equipment can also combine more than two times of shooting non-scoring states into one time when the time length time threshold value between the three-dimensional information of which the object state is the shooting non-scoring state is detected and obtained in different detection modes.

And step S30, in response to the fact that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state, determining that the three-dimensional information corresponding to the shooting failure state is target three-dimensional information.

In a possible implementation manner, the electronic device determines that the three-dimensional information after the time sequence is the three-dimensional information corresponding to the shooting failure state when judging that the motion state of the target object is the shooting failure state according to the positions of the target three-dimensional feature points corresponding to the two consecutive three-dimensional information. That is to say, in the case that the height of the previous target three-dimensional feature point in the two adjacent target three-dimensional feature points is higher than the ball frame plane, the height of the next target three-dimensional feature point is lower than the ball frame plane, and the connecting line of the two target three-dimensional feature points is not intersected with the ball frame plane, the electronic device determines that the motion state of the three-dimensional information corresponding to the next target three-dimensional feature point is the shooting failure state. Further, after the electronic equipment determines that the motion state of the corresponding target object is the three-dimensional information of the shooting failure state, the three-dimensional information is determined as the target three-dimensional information, and the target player is further determined according to the three-dimensional information of the time sequence position behind the target three-dimensional information.

Since the embodiment of the disclosure is used for judging the player who changes the motion state of the target object next time, for example, the player who robs the cricket in the basketball game, the crime action occurs in the case of shooting failure. Therefore, target player detection for grabbing the backboard based on three-dimensional information after the target three-dimensional information is needed, and the method for determining the target three-dimensional information can reduce redundant calculation and improve calculation efficiency.

And step S40, determining the target player according to the position of the object point cloud and the position of the at least one player point cloud in the three-dimensional information with the time sequence position behind the target three-dimensional information.

In a possible implementation manner, after the electronic equipment determines that the three-dimensional information with the motion state being the shooting failure state is the target three-dimensional information, the electronic equipment determines a target player according to the positions of the object point cloud and the at least one player point cloud in the three-dimensional information behind the target three-dimensional information of the time sequence position. The target player is a player which renames the motion state of the target object next time, for example, a player who robs a basketball board after one shooting failure in a basketball game can be determined by the relative position of each player and the basketball after the moment corresponding to the target three-dimensional information, namely the relative position of the object point cloud and other player point clouds in each three-dimensional information after the target three-dimensional information is determined.

Alternatively, the electronic device may determine that the player first in contact with the basketball for a certain amount of time after the basketball is in a failed shot state is a backboard grabbing player, i.e., a target player. That is to say, the electronic device may determine whether each piece of three-dimensional information in the three-dimensional information sequence has a player point cloud satisfying a preset distance condition according to the amount position of the object point cloud from the time corresponding to the target three-dimensional information. And determining the player point cloud meeting the preset distance condition as a candidate point cloud. And responding to the situation that candidate point clouds exist in the three-dimensional information with the continuous preset number and correspond to the same player, and determining the player corresponding to the candidate point clouds as a target player. That is, some physical contact and impact between players during the game, as well as the competition of different players for the same basketball, can occur. Therefore, after the basketball shooting fails, a plurality of candidate point clouds in contact with the object point clouds may exist in each three-dimensional information. However, the time for a player who fails to catch the basketball backboard to contact the basketball is usually short, so that candidate point clouds in which a continuous preset number of three-dimensional information are contacted with the object point clouds can be determined as the target point clouds corresponding to the target player.

Further, the electronic device may determine a player point cloud with which the feature region is in contact with the object point cloud by a distance between the point clouds. That is, the process of sequentially determining the position relationship between the object point cloud and the at least one player point cloud in the three-dimensional information may include: and starting from the moment corresponding to the target three-dimensional information, acquiring the position of the object point cloud of the three-dimensional information behind the target three-dimensional information in the time sequence in the three-dimensional information sequence and the position of at least one player point cloud. And determining that the player point cloud meets a preset distance condition in response to that the shortest distance between the object point cloud in the three-dimensional information and the characteristic region in the player point cloud is smaller than a distance threshold. Wherein, the characteristic region represents the hand of sportsman's health is answered to sportsman's point cloud. The shortest distance between the object point cloud and the feature area in one player point cloud can be calculated in any mode, for example, the shortest distance can be obtained by calculating the minimum value in the distance between the target three-dimensional feature point corresponding to the object point cloud and each three-dimensional feature point in the feature area in the player point cloud.

In one possible implementation, the backboard may fail due to the basketball going out of bounds before or during the backboard grabbing process. Therefore, the electronic equipment can detect whether the target three-dimensional feature point of the object point cloud in each three-dimensional information is out of bounds or not while detecting the candidate point cloud in each three-dimensional information after detecting the target three-dimensional information, and judges that the backboard grabbing fails under the condition of out of bounds, namely that the target player does not exist. That is to say, before determining that the player corresponding to the player point cloud which is taken as the candidate point cloud in the continuous number of three-dimensional information is the target player, determining the target player according to the positions of the object point cloud and at least one player point cloud in the three-dimensional information after the target three-dimensional information at the time sequence position, and determining the position of the target three-dimensional feature point corresponding to the object point cloud in the three-dimensional information sequence from the time corresponding to the target three-dimensional information. The electronic device may determine that the target player is absent in response to the position of the target three-dimensional feature point satisfying an out-of-bounds condition. Optionally, the out-of-range condition of the electronic device may be that an offset of the target three-dimensional feature point in the x axis or the y axis is greater than a preset offset, and an offset of the z axis is less than the preset offset.

Further, in some application scenarios where the number of the cricket in each square in the competition process needs to be counted, or the cricket type is judged to be attack cricket or defense cricket, the cricket type of the cricket needs to be judged. Alternatively, the electronic device may be determined based on the half-fielder relationship that occurs between the target player and the shot failure status. That is, the electronic device may determine the identity information of the target player, and the location information corresponding to the failed shot state. And judging the backboard type of the target player according to the identity information and the position information. Wherein, the identity information represents the team of the corresponding player, and the position information represents the half field of the shooting failure state. And when the team of the target player is not matched with the half court, determining that the backboard type is attack backboard ball, and when the team of the target player is matched with the half court, determining that the backboard type is defense backboard ball.

Based on the technical characteristics, the basketball game is monitored through the computer vision technology, and the efficiency and the accuracy of the process of determining the basketball players robbing the backboard in the game are improved. Meanwhile, whether the basketball is out of bounds or not can be monitored in real time in the process of judging whether the basketball is robbed for the basketball backboard player, detection of the backboard player is stopped under the condition that the basketball is out of bounds, and redundant calculation is reduced.

It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.

In addition, the disclosure also provides a player determination device, an electronic device, a computer-readable storage medium and a program, which can be used for realizing any player determination method provided by the disclosure, and the corresponding technical scheme and description and the corresponding record in the reference method section are not repeated.

Fig. 3 shows a schematic diagram of a player determination device according to an embodiment of the present disclosure, and as shown in fig. 3, the player determination device of an embodiment of the present disclosure may include:

the sequence determination module 30 is configured to determine a three-dimensional information sequence of a target court, where the three-dimensional information sequence includes at least two pieces of three-dimensional information arranged in time sequence, and the three-dimensional information includes an object point cloud of a target object in a three-dimensional court coordinate system and a player point cloud of at least one player in the three-dimensional court coordinate system;

the state determining module 31 is configured to determine, according to a position of the object point cloud in the three-dimensional court coordinate system in each piece of three-dimensional information, a motion state of a target object corresponding to each piece of three-dimensional information;

the information determining module 32 is configured to determine, in response to that the motion state of the target object corresponding to the three-dimensional information is a shooting failure state, that the three-dimensional information corresponding to the shooting failure state is target three-dimensional information;

and the player determining module 33 is used for determining a target player according to the positions of the object point cloud and the at least one player point cloud in the three-dimensional information of which the time sequence position is behind the target three-dimensional information, wherein the target player is the player changing the motion state of the target object next time.

In one possible implementation, the sequence determining module 30 includes:

and the sequence determining submodule is used for arranging the acquired three-dimensional information according to a time sequence to obtain a three-dimensional information sequence of the target court.

the point cloud determining subunit is used for determining an object point cloud of the target object in the three-dimensional court coordinate system according to the first characteristic point and determining a player point cloud of each player in the three-dimensional court coordinate system according to the second characteristic point of each player;

In one possible implementation, the point cloud determining subunit includes:

In one possible implementation, the state determining module 31 includes:

In one possible implementation, the player determination module 33 includes:

In one possible implementation, the point cloud filtering sub-module includes:

the position judging unit is used for acquiring the position of an object point cloud of the three-dimensional information and the position of the point cloud of the at least one player in the three-dimensional information sequence from the moment corresponding to the target three-dimensional information;

In one possible implementation manner, before determining a player corresponding to a candidate point cloud as a target player in response to that the candidate point cloud exists in a continuous preset number of three-dimensional information and corresponds to the same player, the player determination module 33 further includes:

and the out-of-range judgment submodule is used for responding to the situation that the position of the target three-dimensional feature point meets the out-of-range condition and determining that the target player does not exist. The method has specific technical relevance with the internal structure of the computer system, and can solve the technical problem of how to improve the hardware operation efficiency or the execution effect (including reducing data storage capacity, reducing data transmission capacity, improving hardware processing speed and the like), thereby obtaining the technical effect of improving the internal performance of the computer system according with the natural law.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a volatile or non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

The disclosed embodiments also provide a computer program product comprising computer readable code or a non-transitory computer readable storage medium carrying computer readable code, which when run in a processor of an electronic device, the processor in the electronic device performs the above method.

The electronic device may be provided as a terminal, server, or other form of device.

Fig. 4 shows a schematic diagram of an electronic device 800 according to an embodiment of the disclosure. For example, the electronic device 800 may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or other terminal device.

Referring to fig. 4, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communications component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 814 may also include a light sensor, such as a Complementary Metal Oxide Semiconductor (CMOS) or Charge Coupled Device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as a wireless network (Wi-Fi), a second generation mobile communication technology (2G), a third generation mobile communication technology (3G), a fourth generation mobile communication technology (4G), a long term evolution of universal mobile communication technology (LTE), a fifth generation mobile communication technology (5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.

The disclosure relates to the field of augmented reality, and aims to detect or identify relevant features, states and attributes of a target object by means of various visual correlation algorithms by acquiring image information of the target object in a real environment, so as to obtain an AR effect combining virtual and reality matched with specific applications. For example, the target object may relate to a face, a limb, a gesture, an action, etc. associated with a human body, or a marker, a marker associated with an object, or a sand table, a display area, a display item, etc. associated with a venue or a place. The vision-related algorithms may involve visual localization, SLAM, three-dimensional reconstruction, image registration, background segmentation, key point extraction and tracking of objects, pose or depth detection of objects, and the like. The specific application can relate to interactive scenes such as navigation, explanation, reconstruction, virtual effect superposition display and the like related to a real scene or an article, and can also relate to special effect treatment related to people such as interactive scenes such as makeup beautification, limb beautification, special effect display, virtual model display and the like. The detection or identification processing of the relevant characteristics, states and attributes of the target object can be realized through the convolutional neural network. The convolutional neural network is a network model obtained by performing model training based on a deep learning framework.

Fig. 5 shows a schematic diagram of another electronic device 1900 according to an embodiment of the disclosure. For example, electronic device 1900 may be provided as a server or terminal device. Referring to fig. 5, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as the Microsoft Server operating system (Windows Server), stored in the memory 1932^TM) Apple Inc. of the present application based on the graphic user interface operating System (Mac OS X)^TM) Multi-user, multi-process computer operating system (Unix)^TM) Free and open native code Unix-like operating System (Linux)^TM)，Unix-like operating system with open native code (FreeBSD)^TM) Or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK) or the like.

The foregoing description of the various embodiments is intended to highlight various differences between the embodiments, and the same or similar parts may be referred to each other, and for brevity, will not be described again herein.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

If the technical scheme of the application relates to personal information, a product applying the technical scheme of the application clearly informs personal information processing rules before processing the personal information, and obtains personal independent consent. If the technical scheme of the application relates to sensitive personal information, a product applying the technical scheme of the application obtains individual consent before processing the sensitive personal information, and simultaneously meets the requirement of 'express consent'. For example, at a personal information collection device such as a camera, a clear and significant identifier is set to inform that the personal information collection range is entered, the personal information is collected, and if the person voluntarily enters the collection range, the person is regarded as agreeing to collect the personal information; or on the device for processing the personal information, under the condition of informing the personal information processing rule by using obvious identification/information, obtaining personal authorization by modes of popping window information or asking a person to upload personal information of the person by himself, and the like; the personal information processing rule may include information such as a personal information processor, a personal information processing purpose, a processing method, and a type of personal information to be processed.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A player determination method, the method comprising:

2. The method according to claim 1, wherein the determining the three-dimensional information sequence of the target course comprises:

acquiring the three-dimensional information of the target court in real time;

3. The method according to claim 2, wherein the obtaining the three-dimensional information of the target court in real time comprises:

4. The method of claim 3, wherein determining corresponding three-dimensional information from the at least two-dimensional images comprises:

5. The method of claim 4, wherein determining the object point cloud of the target object in the three-dimensional course coordinate system from the first feature point and determining the player point cloud of the player in the three-dimensional course coordinate system from the second feature point of each of the players comprises:

6. The method according to any one of claims 1-5, wherein the determining the motion state of the target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional course coordinate system in each three-dimensional information comprises:

7. The method as claimed in claim 6, wherein the determining the object state of the target object corresponding to each three-dimensional information according to the position of the object point cloud in the three-dimensional course coordinate system in each three-dimensional information comprises:

under the condition that the height of the former target three-dimensional feature point in two adjacent target three-dimensional feature points in time sequence is higher than the ball frame plane, the height of the latter target three-dimensional feature point is lower than the ball frame plane, and the connecting line of the two target three-dimensional feature points is not intersected with the ball frame plane, the object state of the target object corresponding to the target three-dimensional feature point at the later time sequence position is determined to be a shooting non-scoring state.

8. The method according to any one of claims 1-7, wherein the determining a target player from the positions of the object point cloud and the at least one player point cloud in three-dimensional information subsequent to the target three-dimensional information according to time series position comprises:

9. The method according to claim 8, wherein the determining whether each three-dimensional information in the three-dimensional information sequence has a player point cloud satisfying a preset distance condition according to the position of the object point cloud from the time corresponding to the target three-dimensional information comprises:

10. The method of claim 8 or 9, wherein before determining a player corresponding to a candidate point cloud as a target player in response to the candidate point cloud being present in a predetermined number of consecutive three-dimensional information and the candidate point cloud corresponding to the same player, determining the target player according to the positions of the object point cloud and the at least one player point cloud in three-dimensional information chronologically after the target three-dimensional information, further comprises:

and determining that the target player does not exist in response to the position of the target three-dimensional feature point meeting the out-of-bounds condition.

11. The method according to any one of claims 1-10, further comprising:

determining identity information of the target player and position information corresponding to the shooting failure state;

and judging the backboard type of the target player according to the identity information and the position information.

12. A player determination apparatus, the apparatus comprising:

and the player determining module is used for determining a target player according to the positions of the object point cloud and the at least one player point cloud in the three-dimensional information of which the time sequence position is behind the target three-dimensional information, wherein the target player is a player changing the motion state of the target object next time.

13. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 11.

14. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any one of claims 1 to 11.