Badminton serving control method and system based on artificial intelligence

Abstract

The invention relates to the technical field of computer vision data processing, and particularly discloses a badminton serving control method and system based on artificial intelligence. According to the method and the system, batting analysis of athletes in a standard badminton battle video is realized, and a standard serving strategy set and a standard catching feature set are formed; the automatic pitching machine realizes pitching operation by using the standard pitching strategy set, and collects real-time ball receiving videos of the trainees at the same time to obtain a real-time ball receiving feature set of the trainees and an overall ball receiving feature set of the trainees; determining a serving strategy of a next ball by using the real-time ball receiving feature set of the trainee and executing the serving strategy; and determining and executing a ball serving strategy of the next stage by utilizing the standard ball receiving feature set and the training personnel overall ball receiving feature set. The ball serving strategy of a real athlete can be simulated, the next ball and the ball serving strategy of the next stage are adjusted according to the ball receiving reaction of trainees, and the individual requirements of different trainees are met.

Description

Technical Field

[0001] This invention belongs to the field of computer vision data processing technology, specifically relating to a badminton serve control method and system based on artificial intelligence. Background Art

[0002] Badminton is a common ball sport. Traditionally, badminton training relies heavily on human coaches. However, with technological advancements, automatic serve machines have emerged for training. An automatic serve machine is a complex device comprising mechanical and electronic units. The electronic unit processes sensor signals, calculates various parameters at the time of the serve, and converts these parameters into control signals that are output to the mechanical unit to automate the serve. However, traditional automatic serve machines typically serve according to pre-set mechanical parameters, resulting in a fixed and monotonous serve pattern, which is not conducive to personalized training for athletes.

[0003] With the continuous development of artificial intelligence and big data technologies, data processing technology based on computer vision is also constantly improving, leading to higher demands for the intelligence of automatic badminton serving machines. How to improve the electronic unit of the automatic badminton serving machine to simulate the serving style of real athletes and adjust the serving strategy according to the current state and needs of the trainee, thus making the automatic badminton serving machine more intelligent, is the technical problem this invention aims to solve. Therefore, this invention aims to provide a badminton serving control method and system based on artificial intelligence. Summary of the Invention

[0004] The purpose of this invention is to overcome the aforementioned problems in the prior art and provide a badminton serve control method and system based on artificial intelligence. This method and system analyzes the players' shots in standard badminton match videos to form a standard serve strategy set and a standard receive feature set. An automatic serve machine uses the standard serve strategy set to perform the serve operation. Simultaneously, it collects real-time receive videos of the trainee, obtaining a real-time receive feature set and an overall receive feature set for the trainee. The real-time receive feature set is used to determine and execute the serve strategy for the next shot. The standard receive feature set and the overall receive feature set are used to determine and execute the serve strategy for the next stage. This invention can simulate the serve strategies of real athletes and adjust the serve strategy for the next shot and the next stage based on the trainee's receive response, meeting the personalized needs of different trainees.

[0005] To achieve the above-mentioned objectives, the present invention provides the following technical solution: An artificial intelligence-based badminton serve control method includes the following steps: A standard badminton match video set is collected, comprising n videos of different difficulty levels, wherein the i-th video segment includes m players from both sides. i A series of flawless rallies, where i ranges from 1 to n; the movement postures, body movements, and racket movements of both players in the standard badminton match video are analyzed to form n sets of standard serving strategies and standard receiving features of different difficulty levels; the standard serving strategy set includes m serves. i The system includes the following parameters: serving interval, serving position, serving height, serving angle, and serving power. The standard receiving feature set includes posture and movement category feature vectors, key point movement speed feature vectors, and racket movement feature vectors. When a training task begins, the automatic ball-serving machine controls the serving according to a standard serving strategy set at a certain difficulty level, and the trainee, as the receiver, trains to receive the ball. Real-time receiving videos of the trainee are collected and analyzed to obtain the trainee's real-time receiving feature set and overall receiving feature set. The trainee's real-time receiving feature set corresponds to the trainee's real-time receiving reaction in each serving strategy; the trainee's overall receiving feature set corresponds to the trainee's overall receiving reaction in this round of serving strategies. The trainee's real-time receiving feature set is used to determine and execute the serving strategy for the next ball; the standard receiving feature set and the trainee's overall receiving feature set are used to determine and execute the serving strategy for the next stage.

[0006] Furthermore, a set of n standard serving strategies with different difficulty levels is formed, specifically including: Label the two players in the i-th segment of the standard badminton match video as Player A and Player B, respectively; identify and track Player A in the standard badminton match video, locating m... i In each round, athlete A corresponds to m i Second shot image frames IA1~IA mi Each shot image frame IA mi Centered on this, extract IA from the battle videos. mi The after k i Zhang image frame, compared with the current hit image frame IA mi Together they form a total quantity of k i +1 is the set of keyframe images IA_i for athlete A's i-th shot; Calculate m i Second shot image frames IA1~IA mi The timestamp difference between consecutive frames in the data is used to obtain m. i -1 timestamp difference, used as the service interval time in the standard service strategy set; Construct a spatial data model corresponding to a badminton court and establish a coordinate mapping model between the pixel coordinate system and the court plane coordinate system; For m respectively i Second shot image frames IA1~IA mi Each image in the process is used to identify and segment the half-court area, resulting in an image of the half-court area including athlete A's shoes and shuttlecock. Contour detection is performed on athlete A's shoes and shuttlecock in the half-court area image to obtain shoe area and shuttlecock area, respectively. The two smallest bounding rectangles corresponding to the shoe area and shuttlecock area are calculated to obtain the centroid pixel coordinates of the shoe and shuttlecock. The relative position between the centroid pixel coordinates of the shoe and shuttlecock is used to obtain the height pixel coordinates of the shuttlecock. The coordinate mapping model is used to obtain the ground coordinates of the shoe and the height coordinates of the shuttlecock. The ground coordinates of the shoe and the height coordinates of the shuttlecock are used as the serving position and serving height in the standard serving strategy set, respectively. Each image in the keyframe image set IA_i is subjected to badminton shuttlecock recognition and tracking to obtain the trajectory sequence of key points of badminton shuttlecock movement ((x1,y1,t1),(x2,y2,t2),(x3,y3,t3),...,(x j ,y j ,t j ), where (x j ,y j ,t j Let ) represent the x-coordinate, y-coordinate, and timestamp corresponding to the j-th key point; calculate the flight angle and initial velocity of the badminton using the trajectory sequence of the key points of the badminton movement, and use the flight angle as the serving angle in the standard serving strategy set; use the flight angle and initial velocity to obtain the hitting force of the badminton, and use the hitting force as the serving force in the standard serving strategy set; The above method is used to process the n standard badminton match videos of different difficulty levels to obtain n sets of standard serving strategies of different difficulty levels.

[0007] Furthermore, n standard ball-receiving feature sets with different difficulty levels are formed, specifically including: Label the two players in the i-th segment of the standard badminton match video as Player A and Player B, respectively; identify and track Player B in the standard badminton match video, locating m... i In each round, athlete B corresponds to m i Second shot image frames IB1~IB1 mi IB, respectively, for each shot image frame mi Centered on this, extract IB from the battle videos. mi k before and after iZhang image frame, compared with the current hit image frame IB mi Together they form a total of 2k i +1 is the set of keyframe images of athlete B's i-th shot; Each image in the keyframe image set IB_i is identified and segmented to obtain the human body region image of athlete B. Key point detection is performed on the human body region image to obtain a set of key point spatial coordinates corresponding to a total of 14 key points, including the nose, neck, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees and left and right ankles. The joint angle feature set and joint distance feature set are obtained using the set of key point spatial coordinates. The joint angle feature set and joint distance feature set are concatenated to obtain a posture and action feature vector. The posture and action feature vector is input into a pre-trained posture and action recognition model for recognition to obtain the corresponding posture and action category. The posture and action category includes jumping, turning sideways, and raising arms. The posture and action category corresponding to each image in the keyframe image set IB_i is combined according to the timestamp order to obtain the posture and action category feature vector in the standard ball-catching feature set. Using the set of keypoint spatial coordinates of each adjacent image in the keyframe image set IB_i, the movement velocity sequence of each keypoint in the x and y directions is obtained, which serves as the keypoint movement velocity feature vector in the standard ball-catching feature set. Each image in the keyframe image set IB_i is identified and segmented to obtain a racket region image. The racket region image is then processed to calculate the area value of the minimum bounding rectangle and the centroid coordinate value of the minimum bounding rectangle corresponding to the racket region. For m respectively i Second shot image frames IB1~IB1 mi For each image in the data, racket and shuttlecock are identified, and the coordinates of the centroid of the minimum bounding rectangle of the racket area and the coordinates of the shuttlecock impact point are calculated to obtain the relative coordinates of the impact point. The area value, centroid coordinate value, and relative coordinate value of the ball impact point corresponding to each image in the keyframe image set IB_i are combined in the order of timestamps to obtain the racket motion feature vector in the standard ball receiving feature set; The above method is used to process the n standard badminton match videos of different difficulty levels to obtain n standard receiving feature sets of different difficulty levels.

[0008] Furthermore, the real-time ball-receiving feature set of the trainees and the overall ball-receiving feature set of the trainees specifically include: The real-time ball-catching feature set of the trainees includes the ball-catching result of the trainees and the feature vector of the trainees' posture and movement categories corresponding to each ball. The feature vector of the trainees' posture and movement categories is obtained by processing and analyzing the real-time ball-catching video of the trainees, and the specific calculation method is the same as that of the athlete posture and movement category feature vector in the standard ball-catching feature set. The overall ball-catching feature set of the trainees is obtained by processing and analyzing the real-time ball-catching video of the trainees, and the specific calculation method is the same as that of the standard ball-catching feature set.

[0009] Furthermore, the serving strategy for the next ball is determined and executed using the real-time ball-receiving feature set of the trainees. Specifically, this includes: if the ball-receiving result in the real-time ball-receiving feature set is a failure, and the similarity between the trainee's posture and movement category feature vector and the athlete's posture and movement category feature vector for the corresponding ball in the standard ball-receiving feature set is less than a preset threshold T. p If the current serving strategy is repeated, the next serving strategy will be used; otherwise, the next serving strategy will be used according to the predetermined standard serving strategy. The step of determining and executing the next stage serving strategy using the standard receiving feature set and the overall receiving feature set of the trainees specifically includes: if the similarity between the overall receiving feature set of the trainees and the standard receiving feature set is less than a preset threshold T... w Furthermore, the overall receiving error rate is greater than the preset threshold T. n If the serve is successful, the next stage's serve strategy will repeat the current stage's serve strategy; otherwise, the receiving training corresponding to the current stage's serve strategy is considered satisfactory, and more difficult training can proceed to the next stage.

[0010] The present invention also provides the following technical solutions: An artificial intelligence-based badminton serve control system includes the following functional modules: Standard badminton match video processing and analysis module: Collects a set of standard badminton match videos, which includes n segments of standard badminton match videos at different difficulty levels, wherein the i-th segment of the standard badminton match video includes m segments of both players. i A series of flawless rallies, where i ranges from 1 to n; the movement postures, body movements, and racket movements of both players in the standard badminton match video are analyzed to form n sets of standard serving strategies and standard receiving features of different difficulty levels; the standard serving strategy set includes m serves. i The standard receiving feature set includes the following parameters: serving interval, serving position, serving height, serving angle, and serving power; the standard receiving feature set includes posture and movement category feature vectors, key point movement speed feature vectors, and racket motion feature vectors. Serving Control Analysis Module: When a training task begins, the automatic serving machine controls the serving according to a standard serving strategy set at a certain difficulty level, and the trainee, as the receiver, trains to receive the ball. The module collects and analyzes real-time receiving videos of the trainee to obtain a real-time receiving feature set and an overall receiving feature set. The real-time receiving feature set corresponds to the trainee's real-time receiving reaction in each serving strategy; the overall receiving feature set corresponds to the trainee's overall receiving reaction in this round of serving strategies. Serving strategy adjustment module: Determines and executes the serving strategy for the next ball using the real-time receiving feature set of the trainees; determines and executes the serving strategy for the next stage using the standard receiving feature set and the overall receiving feature set of the trainees.

[0011] Furthermore, the standard battle video processing and analysis module specifically includes: Standard serve strategy set calculation unit: Label the two players in the i-th segment of the standard badminton match video as player A and player B respectively; identify and track player A in the standard badminton match video, locating m... i In each round, athlete A corresponds to m i Second shot image frames IA1~IA mi Each shot image frame IA mi Centered on this, extract IA from the battle videos. mi The after k i Zhang image frame, compared with the current hit image frame IA mi Together they form a total quantity of k i +1 is the set of keyframe images IA_i for athlete A's i-th shot; Calculate m i Second shot image frames IA1~IA mi The timestamp difference between consecutive frames in the data is used to obtain m. i -1 timestamp difference, used as the service interval time in the standard service strategy set; Construct a spatial data model corresponding to a badminton court and establish a coordinate mapping model between the pixel coordinate system and the court plane coordinate system; For m respectively i Second shot image frames IA1~IA miEach image in the process is used to identify and segment the half-court area, resulting in an image of the half-court area including athlete A's shoes and shuttlecock. Contour detection is performed on athlete A's shoes and shuttlecock in the half-court area image to obtain shoe area and shuttlecock area, respectively. The two smallest bounding rectangles corresponding to the shoe area and shuttlecock area are calculated to obtain the centroid pixel coordinates of the shoe and shuttlecock. The relative position between the centroid pixel coordinates of the shoe and shuttlecock is used to obtain the height pixel coordinates of the shuttlecock. The coordinate mapping model is used to obtain the ground coordinates of the shoe and the height coordinates of the shuttlecock. The ground coordinates of the shoe and the height coordinates of the shuttlecock are used as the serving position and serving height in the standard serving strategy set, respectively. Each image in the keyframe image set IA_i is subjected to badminton shuttlecock recognition and tracking to obtain the trajectory sequence of key points of badminton shuttlecock movement ((x1,y1,t1),(x2,y2,t2),(x3,y3,t3),...,(x j ,y j ,t j ), where (x j ,y j ,t j Let ) represent the x-coordinate, y-coordinate, and timestamp corresponding to the j-th key point; calculate the flight angle and initial velocity of the badminton using the trajectory sequence of the key points of the badminton movement, and use the flight angle as the serving angle in the standard serving strategy set; use the flight angle and initial velocity to obtain the hitting force of the badminton, and use the hitting force as the serving force in the standard serving strategy set; The above method is used to process the n standard badminton match videos of different difficulty levels to obtain n sets of standard serving strategies of different difficulty levels.

[0012] Furthermore, the standard battle video processing and analysis module specifically includes: Standard receiving feature set calculation unit: Label the two players in the i-th segment of the standard badminton match video as player A and player B respectively; identify and track player B in the standard badminton match video, locating m... i In each round, athlete B corresponds to m i Second shot image frames IB1~IB1 mi IB, respectively, for each shot image frame mi Centered on this, extract IB from the battle videos. mi k before and after i Zhang image frame, compared with the current hit image frame IB mi Together they form a total of 2k i +1 is the set of keyframe images of athlete B's i-th shot; Each image in the keyframe image set IB_i is identified and segmented to obtain the human body region image of athlete B. Key point detection is performed on the human body region image to obtain a set of key point spatial coordinates corresponding to a total of 14 key points, including the nose, neck, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees and left and right ankles. The joint angle feature set and joint distance feature set are obtained using the set of key point spatial coordinates. The joint angle feature set and joint distance feature set are concatenated to obtain a posture and action feature vector. The posture and action feature vector is input into a pre-trained posture and action recognition model for recognition to obtain the corresponding posture and action category. The posture and action category includes jumping, turning sideways, and raising arms. The posture and action category corresponding to each image in the keyframe image set IB_i is combined according to the timestamp order to obtain the posture and action category feature vector in the standard ball-catching feature set. Using the set of keypoint spatial coordinates of each adjacent image in the keyframe image set IB_i, the movement velocity sequence of each keypoint in the x and y directions is obtained, which serves as the keypoint movement velocity feature vector in the standard ball-catching feature set. Each image in the keyframe image set IB_i is identified and segmented to obtain a racket region image. The racket region image is then processed to calculate the area value of the minimum bounding rectangle and the centroid coordinate value of the minimum bounding rectangle corresponding to the racket region. For m respectively i Second shot image frames IB1~IB1 mi For each image in the data, racket and shuttlecock are identified, and the coordinates of the centroid of the minimum bounding rectangle of the racket area and the coordinates of the shuttlecock impact point are calculated to obtain the relative coordinates of the impact point. The area value, centroid coordinate value, and relative coordinate value of the ball impact point corresponding to each image in the keyframe image set IB_i are combined in the order of timestamps to obtain the racket motion feature vector in the standard ball receiving feature set; The above method is used to process the n standard badminton match videos of different difficulty levels to obtain n standard receiving feature sets of different difficulty levels.

[0013] Furthermore, the serve control analysis module specifically includes: Real-time ball receiving feature set calculation unit: The real-time ball receiving feature set of the trainees includes the ball receiving result of the trainees corresponding to each ball and the feature vector of the trainees' posture and movement categories; The feature vector of the trainees' posture and movement categories is obtained by processing and analyzing the real-time ball receiving video of the trainees, and the specific calculation method is the same as the calculation method of the athlete's posture and movement category feature vector in the standard ball receiving feature set; Overall ball receiving feature set calculation unit: The overall ball receiving feature set of the trainee is obtained by processing and analyzing the trainee's real-time ball receiving video, and the specific calculation method is the same as the standard ball receiving feature set calculation method.

[0014] Furthermore, the serving strategy adjustment module specifically includes: If the receiving result in the real-time receiving feature set is a failure, and the similarity between the trainee's posture and movement category feature vector and the athlete's posture and movement category feature vector for the corresponding ball in the standard receiving feature set is less than a preset threshold T. p If the current serving strategy is repeated, the next serving strategy will be used; otherwise, the next serving strategy will be used according to the predetermined standard serving strategy. The step of determining and executing the next stage serving strategy using the standard receiving feature set and the overall receiving feature set of the trainees specifically includes: if the similarity between the overall receiving feature set of the trainees and the standard receiving feature set is less than a preset threshold T... w Furthermore, the overall receiving error rate is greater than the preset threshold T. n If the serve is successful, the next stage's serve strategy will repeat the current stage's serve strategy; otherwise, the receiving training corresponding to the current stage's serve strategy is considered satisfactory, and more difficult training can proceed to the next stage.

[0015] By adopting the above technical solution, the beneficial effects of the present invention compared with the prior art are as follows: This invention processes and analyzes a set of standard badminton match videos to obtain a set of standard serving strategies, which serves as the preset strategy set for an automatic badminton serving machine. The preset strategy set is derived from match videos of real athletes, making the serving method more consistent with the real-person match method.

[0016] This invention processes and analyzes a set of standard badminton match videos to obtain a set of standard receiving features. The standard receiving features are then used to compare and analyze the receiving performance of trainees. Based on the analysis results, the serving strategy of the automatic badminton serving machine for the next ball and the next stage is adjusted.

[0017] This invention uses artificial intelligence technology to process and analyze a set of standard badminton match videos, and obtains the serve position, serve height, serve angle and serve power from the set of standard serve strategies based on efficient image processing methods.

[0018] This invention uses artificial intelligence technology to process and analyze standard badminton match video sets and real-time receiving videos of trainees. Through various feature extraction and representation methods, it obtains feature vectors corresponding to movement posture, body movement information, and racket movement information, thereby improving the comprehensiveness of the feature vectors. At the same time, it simplifies the expression of standard receiving feature sets, real-time receiving feature sets of trainees, and overall receiving feature sets of trainees, thus improving the computational efficiency of feature vectors. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a badminton serve control method based on artificial intelligence according to the present invention; Figure 2 This is a flowchart illustrating the calculation of the standard serve strategy set in this invention; Figure 3 This is a flowchart illustrating the calculation of the standard ball-receiving feature set in this invention; Figure 4 This is a flowchart illustrating the calculation of the real-time ball-receiving feature set and the overall ball-receiving feature set of the trainees in this invention; Figure 5 A flowchart illustrating the process of determining the next ball and the next stage of the serving strategy in this invention; Figure 6 This is a functional block diagram of an artificial intelligence-based badminton serve control system according to the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1 like Figure 1 As shown, this embodiment provides a badminton serve control method based on artificial intelligence, including the following steps: A standard badminton match video set is collected, comprising n videos of different difficulty levels, wherein the i-th video segment includes m players from both sides. i A series of flawless rallies, where i ranges from 1 to n; the movement postures, body movements, and racket movements of both players in the standard badminton match video are analyzed to form n sets of standard serving strategies and standard receiving features of different difficulty levels; the standard serving strategy set includes m serves.i The system includes the following parameters: serving interval, serving position, serving height, serving angle, and serving power. The standard receiving feature set includes posture and movement category feature vectors, key point movement speed feature vectors, and racket movement feature vectors. When a training task begins, the automatic ball-serving machine controls the serving according to a standard serving strategy set at a certain difficulty level, and the trainee, as the receiver, trains to receive the ball. Real-time receiving videos of the trainee are collected and analyzed to obtain the trainee's real-time receiving feature set and overall receiving feature set. The trainee's real-time receiving feature set corresponds to the trainee's real-time receiving reaction in each serving strategy; the trainee's overall receiving feature set corresponds to the trainee's overall receiving reaction in this round of serving strategies. The trainee's real-time receiving feature set is used to determine and execute the serving strategy for the next ball; the standard receiving feature set and the trainee's overall receiving feature set are used to determine and execute the serving strategy for the next stage.

[0023] The standard badminton match video collection is a collection of videos recorded and processed from real matches between athletes. Each standard badminton match video corresponds to a match between athletes of different skill levels. In order to facilitate the analysis of the videos and form a coherent serving strategy, the match video records several rallies between the two athletes without any mistakes.

[0024] Example 2 like Figure 2 As shown, this embodiment provides a badminton serve control method based on artificial intelligence, wherein n standard serve strategy sets with different difficulty levels are formed, specifically including: Label the two players in the i-th segment of the standard badminton match video as Player A and Player B, respectively; identify and track Player A in the standard badminton match video, locating m... i In each round, athlete A corresponds to m i Second shot image frames IA1~IA mi Each shot image frame IA mi Centered on this, extract IA from the battle videos. mi The after k i Zhang image frame, compared with the current hit image frame IA mi Together they form a total quantity of k i +1 is the set of keyframe images IA_i for athlete A's i-th shot.

[0025] Calculate m i Second shot image frames IA1~IA mi The timestamp difference between consecutive frames in the data is used to obtain m. i -1 timestamp difference, used as the service interval time in the standard service strategy set; Construct a spatial data model corresponding to a badminton court and establish a coordinate mapping model between the pixel coordinate system and the court plane coordinate system; For m respectively i Second shot image frames IA1~IA mi Each image in the image is used to identify and segment the half-court area, resulting in a half-court area image including athlete A's shoes and shuttlecock. Contour detection is performed on athlete A's shoes and shuttlecock in the half-court area image to obtain shoe and shuttlecock areas respectively. The two smallest bounding rectangles corresponding to the shoe and shuttlecock areas are calculated to obtain the centroid pixel coordinates of the shoe and shuttlecock. The height pixel coordinates of the shuttlecock are obtained by the relative position between the centroid pixel coordinates of the shoe and shuttlecock. The coordinate mapping model is used to obtain the ground coordinates of the shoe and the height coordinates of the shuttlecock. The ground coordinates of the shoe and the height coordinates of the shuttlecock are used as the serving position and serving height in the standard serving strategy set, respectively.

[0026] The ball-hitting behavior of athlete A is analyzed to form a set of serving strategies. To simplify the computation, the image frames of athlete A's shots are first located. By analyzing a single frame at the moment of impact, the position and height of athlete A's shot can be determined.

[0027] Each image in the keyframe image set IA_i is subjected to badminton shuttlecock recognition and tracking to obtain the trajectory sequence of key points of badminton shuttlecock movement ((x1,y1,t1),(x2,y2,t2),(x3,y3,t3),...,(x j ,y j ,t j ), where (x j ,y j ,t j Let represent the x-coordinate, y-coordinate, and timestamp corresponding to the j-th key point; calculate the flight angle and initial velocity of the shuttlecock using the trajectory sequence of the key points of the badminton movement, and use the flight angle as the serving angle in the standard serving strategy set; use the flight angle and initial velocity to obtain the hitting force of the shuttlecock, and use the hitting force as the serving force in the standard serving strategy set.

[0028] Starting with the initial frame of the shot image, extracting a certain number of subsequent keyframes allows analysis of the dynamic characteristics of athlete A's shot, including the shuttlecock's flight angle and initial velocity. First, the equations of motion for the shuttlecock in the x and y directions are calculated. The force of the shot is closely related to the racket swing speed, shot conversion rate, and the shuttlecock's flight angle and velocity. In specific calculations, factors such as the shuttlecock's mass and air resistance need to be considered. By measuring the shuttlecock's flight velocity and angle, and combining this with the equations of motion, the force of the shot can be estimated. The specific equations of motion are referenced from existing physics equations and will not be elaborated here.

[0029] The above method is used to process the n standard badminton match videos of different difficulty levels to obtain n sets of standard serving strategies of different difficulty levels.

[0030] Example 3 like Figure 3 As shown, this embodiment provides a badminton serve control method based on artificial intelligence, wherein n standard receiving feature sets with different difficulty levels are formed, specifically including: Label the two players in the i-th segment of the standard badminton match video as Player A and Player B, respectively; identify and track Player B in the standard badminton match video, locating m... i In each round, athlete B corresponds to m i Second shot image frames IB1~IB1 mi IB, respectively, for each shot image frame mi Centered on this, extract IB from the battle videos. mi k before and after i Zhang image frame, compared with the current hit image frame IB mi Together they form a total of 2k i +1 is the set of keyframe images of athlete B's i-th shot.

[0031] The ball-hitting behavior of athlete B is analyzed to form a standard ball-receiving feature set. First, the image frames of athlete B's ball-hitting action are located. Centered on the single frame image at the moment of impact, a certain number of image frames are located before and after it. These image frames allow for the analysis of the static and dynamic characteristics of athlete B's ball-hitting action, thus collectively forming the standard ball-receiving feature set.

[0032] Each image in the keyframe image set IB_i is identified and segmented to obtain the human body region image of athlete B. Key point detection is performed on the human body region image to obtain a set of key point spatial coordinates corresponding to a total of 14 key points, including the nose, neck, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees and left and right ankles. The joint angle feature set and joint distance feature set are obtained using the set of key point spatial coordinates. The joint angle feature set and joint distance feature set are concatenated to obtain a posture action feature vector. The posture action feature vector is input into a pre-trained posture action recognition model for recognition to obtain the corresponding posture action category. The posture action category includes jumping, turning sideways, and raising arms. The posture action category corresponding to each image in the keyframe image set IB_i is combined according to the timestamp order to obtain the posture action category feature vector in the standard ball receiving feature set.

[0033] Based on the human skeletal structure and the set of spatial coordinates of key human points, the extension angles of each joint and the distances between joints can be calculated. These represent the spatial geometric features of human posture, i.e., static features, which can effectively identify the posture category. In badminton, key posture categories during a shot include jumping, turning sideways, and raising the arm. This embodiment pre-trains a posture recognition model for the above-mentioned movement categories. The posture recognition model is based on artificial convolutional neural networks, such as mature models like CNNs. After identifying the posture category corresponding to each image, they are combined into a sequence of actions according to time sequence and represented as a posture action category feature vector, facilitating subsequent similarity calculations.

[0034] Using the set of keypoint spatial coordinates of each adjacent image in the keyframe image set IB_i, the movement velocity sequence of each keypoint in the x and y directions is obtained, which serves as the keypoint movement velocity feature vector in the standard ball-catching feature set. The movement speed characteristics of key points on the human body in the video reflect the changes of the human body in continuous time. It belongs to dynamic features. The calculation method is to divide the movement distance of the key point by the movement time. The movement speed corresponding to each key point is summarized and normalized, and represented in the form of feature vector.

[0035] Each image in the keyframe image set IB_i is identified and segmented to obtain a racket region image. The racket region image is then processed to calculate the area value of the minimum bounding rectangle and the centroid coordinate value of the minimum bounding rectangle corresponding to the racket region. For m respectively i Second shot image frames IB1~IB1 mi For each image in the data, racket and shuttlecock are identified, and the coordinates of the centroid of the minimum bounding rectangle of the racket area and the coordinates of the shuttlecock impact point are calculated to obtain the relative coordinates of the impact point. The area value, centroid coordinate value, and relative coordinate value of the ball impact point corresponding to each image in the keyframe image set IB_i are combined in the order of timestamps to obtain the racket motion feature vector in the standard ball receiving feature set.

[0036] A player's use of the racket when hitting the shuttlecock reflects their hitting technique. Features such as the racket's movement, the point of contact between the racket and the shuttlecock, and the swing angle all reflect the hitting method to some extent. By tracking the racket's center of mass, the trajectory characteristics of the racket can be obtained. The area of ​​the minimum bounding rectangle corresponding to the racket's region reflects the angle of the racket face. The coordinates of the center of mass of the minimum bounding rectangle of the racket's region and the coordinates of the shuttlecock's contact point indicate which areas of the racket the hitting point is located in.

[0037] The above method is used to process the n standard badminton match videos of different difficulty levels to obtain n standard receiving feature sets of different difficulty levels.

[0038] Example 4 like Figure 4 As shown, this embodiment provides a badminton serve control method based on artificial intelligence, wherein the real-time receiving feature set of the trainee and the overall receiving feature set of the trainee specifically include: The real-time ball-catching feature set of the trainees includes the ball-catching result of the trainees and the feature vector of the trainees' posture and movement categories corresponding to each ball. The feature vector of the trainees' posture and movement categories is obtained by processing and analyzing the real-time ball-catching video of the trainees, and the specific calculation method is the same as that of the athlete posture and movement category feature vector in the standard ball-catching feature set. The overall ball-catching feature set of the trainees is obtained by processing and analyzing the real-time ball-catching video of the trainees, and the specific calculation method is the same as that of the standard ball-catching feature set.

[0039] Example 5 like Figure 5 As shown, this embodiment provides a badminton serve control method based on artificial intelligence. Specifically, it utilizes the real-time reception feature set of the trainee to determine and execute the serve strategy for the next ball. This includes: if the reception result in the real-time reception feature set is a failure, and the similarity between the trainee's posture and movement category feature vector and the athlete's posture and movement category feature vector for the corresponding ball in the standard reception feature set is less than a preset threshold T... p If the current serving strategy is repeated, the next serving strategy will be used; otherwise, the next serving strategy will be used according to the predetermined standard serving strategy. The step of determining and executing the next stage serving strategy using the standard receiving feature set and the overall receiving feature set of the trainees specifically includes: if the similarity between the overall receiving feature set of the trainees and the standard receiving feature set is less than a preset threshold T... w Furthermore, the overall receiving error rate is greater than the preset threshold T. n If the serve is successful, the next stage's serve strategy will repeat the current stage's serve strategy; otherwise, the receiving training corresponding to the current stage's serve strategy is considered satisfactory, and more difficult training can proceed to the next stage.

[0040] Example 6 like Figure 6 As shown, this embodiment provides a badminton serve control system based on artificial intelligence, including the following functional modules: The standard badminton match video processing and analysis module includes a standard serve strategy set calculation unit and a standard receive feature set calculation unit. It collects a set of standard badminton match videos, which includes n segments of standard badminton match videos at different difficulty levels, where the i-th segment includes m segments of both players. i A series of flawless rallies, where i ranges from 1 to n; the movement postures, body movements, and racket movements of both players in the standard badminton match video are analyzed to form n sets of standard serving strategies and standard receiving features of different difficulty levels; the standard serving strategy set includes m serves. i The standard receiving feature set includes the following parameters: serving interval, serving position, serving height, serving angle, and serving power; the standard receiving feature set includes posture and movement category feature vectors, key point movement speed feature vectors, and racket motion feature vectors. The serve control analysis module includes a real-time receiving feature set calculation unit and an overall receiving feature set calculation unit: When a training task begins, the automatic serve machine implements serve control according to a standard serve strategy set at a certain difficulty level, and the trainee, as the receiver, conducts receive training; real-time receive video of the trainee is collected and analyzed to obtain the trainee's real-time receive feature set and the trainee's overall receive feature set; the trainee's real-time receive feature set corresponds to the trainee's real-time receive reaction in each serve strategy; the trainee's overall receive feature set corresponds to the trainee's overall receive reaction in this round of serve strategies; Serving strategy adjustment module: Determines and executes the serving strategy for the next ball using the real-time receiving feature set of the trainees; determines and executes the serving strategy for the next stage using the standard receiving feature set and the overall receiving feature set of the trainees.

[0041] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, computer devices, or computer-readable storage media. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0042] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0043] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Based on the technical essence of the present invention, any simple modifications, equivalent substitutions, and improvements made to the above embodiments within the spirit and principles of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A badminton serve control method based on artificial intelligence, characterized in that: The steps include: A standard badminton match video set is collected, wherein the standard badminton match video set includes n standard badminton match videos of different difficulty levels, wherein the i-th standard badminton match video includes m players from both sides. i The standard badminton match video is used to analyze the sports postures, body movement information and racket movement information of both players, and form n standard serving strategy sets with different difficulty levels and n standard receiving feature sets with different difficulty levels; the standard serving strategy set includes the number of serves m i , serving interval time, serving position, serving height, serving angle and serving strength; the standard ball receiving feature set includes posture action category feature vector, key point movement speed feature vector and racket movement feature vector; when the training task starts, the automatic serving machine realizes serving control according to the standard serving strategy set under a certain difficulty level, and the trainee performs receiving training as the receiving party; the real-time receiving video of the trainee is collected and analyzed to obtain the real-time receiving feature set of the trainee and the overall receiving feature set of the trainee; the real-time receiving feature set of the trainee corresponds to the real-time receiving reaction of the trainee in each serving strategy; the overall receiving feature set of the trainee corresponds to the overall receiving reaction of the trainee in this round of serving strategy; the serving strategy of the next ball is determined and executed by using the real-time receiving feature set of the trainee; the serving strategy of the next stage is determined and executed by using the standard receiving feature set and the overall receiving feature set of the trainee.

2. A badminton serve control method based on artificial intelligence as claimed in claim 1, characterized in that: The formation of n standard serving strategy sets of different difficulty levels specifically includes: The two athletes in the i-th standard badminton match video are marked as athlete A and athlete B respectively; athlete A in the standard badminton match video is identified and tracked, and the location m i The m corresponding to player A in the round i The batting image frames IA1~IA mi , respectively, with each hitting image frame IA mi Centered on the battle video, extract IA mi The back k i image frame, and the current hitting image frame IA mi Together, the total number is k i +1: the key frame image set IA_i of the player A’s i-th shot; Calculate m i The batting image frames IA1~IA mi The timestamp difference between the adjacent frames before and after is obtained i -1 timestamp difference, used as the serve interval in the standard serve strategy set; Construct a spatial data model corresponding to a badminton court, and establish a coordinate mapping model between a pixel coordinate system and a court plane coordinate system; For m i The batting image frames IA1~IA mi Performing half-court court area identification and segmentation on each of the images to obtain a half-court court area image including the sneakers and badminton of athlete A; performing contour detection on the sneakers and badminton of athlete A in the half-court court area image to obtain a sneaker area and a badminton area, respectively calculating two minimum circumscribed rectangles corresponding to the sneaker area and the badminton area, respectively obtaining the sneaker centroid pixel coordinates and the badminton centroid pixel coordinates, obtaining the badminton height pixel coordinates through the relative positions between the sneaker centroid pixel coordinates and the badminton centroid pixel coordinates, obtaining the sneaker ground coordinates and the badminton height coordinates by using the coordinate mapping model, and using the sneaker ground coordinates and the badminton height coordinates as the serving position and serving height in the standard serving strategy set, respectively; Badminton recognition and tracking are performed on each image in the key frame image set IA_i to obtain a badminton motion key point trajectory sequence ((x1, y1, t1), (x2, y2, t2), (x3, y3, t3), ..., (x j ,y j ,t j )), where (x j ,y j ,t j ) represents the abscissa, ordinate and timestamp corresponding to the j-th key point; using the badminton motion key point trajectory sequence to calculate the flight angle and initial speed of the badminton, and using the flight angle as the serving angle in the standard serving strategy set; using the flight angle and initial speed to obtain the hitting force of the badminton, and using the hitting force as the serving force in the standard serving strategy set; According to the above method, the n standard badminton match videos of different difficulty levels are processed respectively to obtain n standard serving strategy sets of different difficulty levels.

3. A badminton serve control method based on artificial intelligence as claimed in claim 1, characterized in that: The forming of n standard ball catching feature sets of different difficulty levels specifically includes: The two athletes in the i-th standard badminton match video are marked as athlete A and athlete B respectively; the athlete B in the standard badminton match video is identified and tracked, and the location m i The m corresponding to player B in the round i The batting image frames IB1~IB mi , respectively, with each hitting image frame IB mi As the center, extract IB in the battle video mi The k before and after i image frames, and the current hitting image frame IB mi Together the total number is 2k i +1: the key frame image set IB_i of the i-th shot of player B; Respectively identify and segment the athlete B for each image in the key frame image set IB_i to obtain a human body region image of the athlete B, perform key point detection on the human body region image to obtain a key point spatial coordinate set corresponding to a total of 14 key points including the nose, neck, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles; Using the key point spatial coordinate set to obtain a joint angle feature set and a joint distance feature set, splicing the joint angle feature set and the joint distance feature set to obtain a posture action feature vector, inputting the posture action feature vector into a pre-trained posture action recognition model for recognition, and obtaining a corresponding posture action category, wherein the posture action category includes jumping, sideways, and arm raising; combining the posture action category corresponding to each image in the key frame image set IB_i in timestamp order to obtain a posture action category feature vector in a standard ball catching feature set; Using the key point spatial coordinate set of each adjacent image in the key frame image set IB_i, a moving speed sequence of each key point in the x and y directions is obtained as a key point moving speed feature vector in the standard ball receiving feature set; Respectively perform racket recognition and segmentation on each image in the key frame image set IB_i to obtain a racket area image, process the racket area image, and calculate the minimum circumscribed rectangle area value and the minimum circumscribed rectangle centroid coordinate value corresponding to the racket area; For m i The batting image frames IB1~IB mi For each image in the image, the racket and badminton body are identified, the coordinate value of the center of mass of the minimum circumscribed rectangle of the racket area and the coordinate value of the badminton collision point are calculated, and the relative coordinate value of the collision point is obtained; The area value, the center of mass coordinate value and the relative coordinate value of the ball-collision point corresponding to each image in the key frame image set IB_i are combined in the order of timestamps to obtain a racket motion feature vector in a standard ball-catching feature set; According to the above method, the n standard badminton game videos of different difficulty levels are processed respectively to obtain n standard ball receiving feature sets of different difficulty levels.

4. A badminton serve control method based on artificial intelligence as claimed in claim 2 or 3, characterized in that: The real-time ball receiving feature set of the training personnel and the overall ball receiving feature set of the training personnel specifically include: The trainer's real-time ball catching feature set includes the trainer's ball catching results and the trainer's posture and action category feature vectors corresponding to each ball; the trainer's posture and action category feature vectors are obtained by processing and analyzing the trainer's real-time ball catching video, and the specific calculation method is the same as the calculation method of the athlete's posture and action category feature vectors in the standard ball catching feature set; the trainer's overall ball catching feature set is obtained by processing and analyzing the trainer's real-time ball catching video, and the specific calculation method is the same as the calculation method of the standard ball catching feature set.

5. The badminton serve control method based on artificial intelligence as claimed in claim 1, characterized in that: The method of using the real-time receiving feature set of the training personnel to determine the serving strategy for the next ball and execute it specifically includes: if the receiving result in the real-time receiving feature set is a failure, and the similarity between the training personnel's posture action category feature vector and the corresponding player's posture action category feature vector in the standard receiving feature set is less than a preset threshold value T p , the serving strategy for the next ball repeats the current serving strategy, otherwise, the serving strategy for the next ball corresponding to the predetermined standard serving strategy is used; the use of the standard receiving feature set and the overall receiving feature set of the training personnel to determine the serving strategy for the next stage and execute it specifically includes: if the similarity between the overall receiving feature set of the training personnel and the standard receiving feature set is less than a preset threshold value T w , and the overall ball receiving error rate is greater than the preset threshold T n , then the serving strategy of the next stage repeats the serving strategy of this stage. Otherwise, it is considered that the receiving training corresponding to the serving strategy of this stage is qualified, and a more difficult training can be carried out in the next stage.

6. A badminton serve control system based on artificial intelligence, characterized in that: Includes the following functional modules: Standard battle video processing and analysis module: collects a standard badminton battle video set, wherein the standard badminton battle video set includes n standard badminton battle videos of different difficulty levels, wherein the i-th standard badminton battle video includes m players from both sides. i The standard badminton match video is used to analyze the sports postures, body movement information and racket movement information of both players, and form n standard serving strategy sets and standard receiving feature sets of different difficulty levels; the standard serving strategy set includes the number of serves m i , serving interval time, serving position, serving height, serving angle and serving strength; the standard receiving feature set includes posture action category feature vector, key point moving speed feature vector and racket movement feature vector; Serving control analysis module: when the training task starts, the automatic serving machine implements serving control according to a standard serving strategy set under a certain difficulty level, and the trainee performs receiving training as the receiving party; the real-time receiving video of the trainee is collected and analyzed to obtain the real-time receiving feature set of the trainee and the overall receiving feature set of the trainee; the real-time receiving feature set of the trainee corresponds to the real-time receiving reaction of the trainee in each serving strategy; the overall receiving feature set of the trainee corresponds to the overall receiving reaction of the trainee in this round of serving strategy; Serving strategy adjustment module: Use the real-time receiving feature set of the trainer to determine and execute the serving strategy for the next ball; use the standard receiving feature set and the overall receiving feature set of the trainer to determine and execute the serving strategy for the next stage.

7. The artificial intelligence-based badminton serve control system according to claim 6, characterized in that: The standard battle video processing and analysis module specifically includes: Standard serve strategy set calculation unit: mark the two players in the i-th standard badminton match video as player A and player B respectively; identify and track player A in the standard badminton match video, and locate m i The m corresponding to player A in the round i The batting image frames IA1~IA mi , respectively, with each hitting image frame IA mi Centered on the battle video, extract IA mi The back k i image frame, and the current hitting image frame IA mi Together, the total number is k i +1: the key frame image set IA_i of the player A’s i-th shot; Calculate m i The batting image frames IA1~IA mi The timestamp difference between the adjacent frames before and after is obtained i -1 timestamp difference, used as the serve interval in the standard serve strategy set; Construct a spatial data model corresponding to a badminton court, and establish a coordinate mapping model between a pixel coordinate system and a court plane coordinate system; For m i The batting image frames IA1~IA mi Performing half-court court area identification and segmentation on each of the images to obtain a half-court court area image including the sneakers and badminton of athlete A; performing contour detection on the sneakers and badminton of athlete A in the half-court court area image to obtain a sneaker area and a badminton area, respectively calculating two minimum circumscribed rectangles corresponding to the sneaker area and the badminton area, respectively obtaining the sneaker centroid pixel coordinates and the badminton centroid pixel coordinates, obtaining the badminton height pixel coordinates through the relative positions between the sneaker centroid pixel coordinates and the badminton centroid pixel coordinates, obtaining the sneaker ground coordinates and the badminton height coordinates by using the coordinate mapping model, and using the sneaker ground coordinates and the badminton height coordinates as the serving position and serving height in the standard serving strategy set, respectively; Badminton recognition and tracking are performed on each image in the key frame image set IA_i to obtain a badminton motion key point trajectory sequence ((x1, y1, t1), (x2, y2, t2), (x3, y3, t3), ..., (x j ,y j ,t j )), where (x j ,y j ,t j ) represents the abscissa, ordinate and timestamp corresponding to the j-th key point; using the badminton motion key point trajectory sequence to calculate the flight angle and initial speed of the badminton, and using the flight angle as the serving angle in the standard serving strategy set; using the flight angle and initial speed to obtain the hitting force of the badminton, and using the hitting force as the serving force in the standard serving strategy set; The above processing is performed on the n standard badminton match videos of different difficulty levels respectively to obtain n standard serving strategy sets of different difficulty levels.

8. The artificial intelligence-based badminton serve control system according to claim 6, characterized in that: The standard battle video processing and analysis module specifically includes: Standard catch feature set calculation unit: mark the two players in the i-th standard badminton match video as player A and player B respectively; identify and track player B in the standard badminton match video, and locate m i The m corresponding to player B in the round i The batting image frames IB1~IB mi , respectively, with each hitting image frame IB mi As the center, extract IB in the battle video mi The k before and after i image frames, and the current hitting image frame IB mi Together the total number is 2k i +1: the key frame image set IB_i of the i-th shot of player B; Respectively identify and segment the athlete B for each image in the key frame image set IB_i to obtain a human body region image of the athlete B, perform key point detection on the human body region image to obtain a key point spatial coordinate set corresponding to a total of 14 key points including the nose, neck, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles; Using the key point spatial coordinate set to obtain a joint angle feature set and a joint distance feature set, splicing the joint angle feature set and the joint distance feature set to obtain a posture action feature vector, inputting the posture action feature vector into a pre-trained posture action recognition model for recognition, and obtaining a corresponding posture action category, wherein the posture action category includes jumping, sideways, and arm raising; combining the posture action category corresponding to each image in the key frame image set IB_i in timestamp order to obtain a posture action category feature vector in a standard ball catching feature set; Using the key point spatial coordinate set of each adjacent image in the key frame image set IB_i, a moving speed sequence of each key point in the x and y directions is obtained as a key point moving speed feature vector in the standard ball receiving feature set; Respectively perform racket recognition and segmentation on each image in the key frame image set IB_i to obtain a racket area image, process the racket area image, and calculate the minimum circumscribed rectangle area value and the minimum circumscribed rectangle centroid coordinate value corresponding to the racket area; For m i The batting image frames IB1~IB mi For each image in the image, the racket and badminton body are identified, the coordinate value of the center of mass of the minimum circumscribed rectangle of the racket area and the coordinate value of the badminton collision point are calculated, and the relative coordinate value of the collision point is obtained; The area value, the center of mass coordinate value and the relative coordinate value of the ball-collision point corresponding to each image in the key frame image set IB_i are combined in the order of timestamps to obtain a racket motion feature vector in a standard ball-catching feature set; The above processing is performed on the n standard badminton match videos of different difficulty levels respectively to obtain n standard ball receiving feature sets of different difficulty levels.

9. A badminton serve control system based on artificial intelligence as claimed in claim 7 or 8, characterized in that: The serve control analysis module specifically includes: Real-time ball receiving feature set calculation unit: the trainer's real-time ball receiving feature set includes the trainer's ball receiving results and the trainer's posture and action category feature vectors corresponding to each ball; the trainer's posture and action category feature vectors are obtained by processing and analyzing the trainer's real-time ball receiving video, and the specific calculation method is the same as the athlete's posture and action category feature vector calculation method in the standard ball receiving feature set; Overall ball receiving feature set calculation unit: The overall ball receiving feature set of the trainee is obtained by processing and analyzing the real-time ball receiving video of the trainee, and the specific calculation method is the same as the standard ball receiving feature set calculation method.

10. The artificial intelligence-based badminton serve control system according to claim 6, characterized in that: The serving strategy adjustment module specifically includes: If the result of the catch in the real-time catch feature set is a failure, and the similarity between the training personnel's posture action category feature vector and the corresponding player's posture action category feature vector in the standard catch feature set is less than the preset threshold T p , the serving strategy for the next ball repeats the current serving strategy, otherwise, the serving strategy for the next ball corresponding to the predetermined standard serving strategy is used; the use of the standard receiving feature set and the overall receiving feature set of the training personnel to determine the serving strategy for the next stage and execute it specifically includes: if the similarity between the overall receiving feature set of the training personnel and the standard receiving feature set is less than a preset threshold value T w , and the overall ball receiving error rate is greater than the preset threshold T n , then the serving strategy of the next stage repeats the serving strategy of this stage. Otherwise, it is considered that the receiving training corresponding to the serving strategy of this stage is qualified, and a more difficult training can be carried out in the next stage.

Images