Intelligent golf scoring method and device and storage medium

Abstract

The invention discloses an intelligent golf scoring method and device and a storage medium, and relates to the technical field of data processing.The intelligent golf scoring method comprises the steps that in response to scoring starting operation of a user, point cloud data and robot vision data are fused, and behavior feature data of the user are generated; judging the movement intention of the user according to the behavior characteristic data; triggering a corresponding scoring mode according to the movement intention to collect the total pole number of the user; and based on a scoring rule corresponding to the target task, calculating the score of the target hole according to the total pole number, and synchronously rendering the score to a vehicle-mounted screen for display. The golf scoring method and device achieve the technical effect of improving golf scoring precision.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a golf intelligent scoring method, device, and storage medium. Background Art

[0002] At present, the traditional golf scoring method relies on manual handwritten scorecard recording. Users need to pause the game after hitting the ball to manually record the number of strokes. The manual recording process is affected by environmental interference and subjective judgment differences, and is prone to omissions and errors. This leads to deviations between the scoring data and the actual movement status, which in turn affects the scoring accuracy.

[0003] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a golf intelligent scoring method, device and storage medium, aiming to solve the technical problem of how to improve the accuracy of golf scoring.

[0005] To achieve the above objectives, the present application proposes a golf intelligent scoring method, which includes: In response to a scoring start operation by a user, fusing the point cloud data with the robot vision data to generate behavioral feature data of the user; determining the user's movement intention based on the behavioral characteristic data; triggering a corresponding scoring mode according to the movement intention to collect the total score of the user; Based on the scoring rules corresponding to the target task, the score of the target hole is calculated according to the total number of strokes and synchronously rendered to the in-vehicle screen for display.

[0006] In one embodiment, the step of generating the user's behavioral feature data by fusing point cloud data with robot vision data in response to the user's scoring start operation includes: Upon receiving a scoring start instruction from the user, activating a sensor array to acquire the point cloud data in real time, and capturing the robot visual data through an RGB camera; Removing outliers from the point cloud data through statistical filtering, and separating user point cloud data from background point cloud data based on a clustering algorithm; Extracting the coordinates of the user's skeletal joints from the robot's visual data, calculating a dense optical flow field through an algorithm, and generating motion vector data of the user; The user point cloud data and the motion vector data are synchronized based on a timestamp to determine user behavior feature data.

[0007] In one embodiment, after the step of triggering a corresponding scoring mode according to the movement intention to collect the total score of the user, the method further includes: Detecting the user's distance through a time-of-flight sensor to determine whether the user has entered a preset range; Based on the RGB camera, face recognition or gait analysis is performed to verify the user's identity and determine whether the user is the target user; If it is detected that the target user enters the preset range, the shot counting is triggered and the shot count of the target user is updated.

[0008] In one embodiment, the step of determining the user's movement intention based on the behavior characteristic data includes: Inputting the behavioral feature data into a trained neural network model; Analyzing the behavior feature data through the neural network model and outputting the movement intention category and the corresponding probability; The user's movement intention is determined according to the movement intention category and the corresponding probability.

[0009] In one embodiment, the step of triggering a corresponding scoring mode according to the movement intention to collect the total score of the user includes: If the probability that the movement intention is movement is greater than a preset threshold, activating the navigation system, entering a follow-up counting mode, and counting the number of strokes; The positioning system obtains the coordinates of the golf cart in real time. If the coordinates are detected to be within a preset green coordinate area, the system switches to a putting mode and counts the number of putts. The total number of strokes of the user is updated according to the number of strokes and the number of putts.

[0010] In one embodiment, after the step of calculating the score of the target hole according to the total number of strokes based on the scoring rules corresponding to the target task and synchronously rendering the score to the in-vehicle screen for display, the following steps are included: Establishing a communication connection with at least one golf cart in a team through a wireless communication module to form a vehicle ad hoc network; The scoring data of the golf carts in the team is received and analyzed, and dynamically rendered to the on-board screen according to a preset display template.

[0011] In one embodiment, the golf intelligent scoring method further includes: In response to a long press operation of the in-vehicle remote control by the user, determining that the ball is out of bounds, and recording the number of penalty strokes based on the corresponding penalty rules; In response to a short press operation of the vehicle-mounted remote controller by the user, entering a completion scoring mode, receiving the missed shot information input by the user, and completing and updating the shot count; According to the number of penalty strokes and the completed number of strokes, the user's total number of strokes is updated, the score is recalculated and rendered to the in-vehicle screen in real time.

[0012] In one embodiment, the step of entering the scoring completion mode in response to a short press of the vehicle-mounted remote controller by the user, receiving the missed shot information input by the user, and completing and updating the shot count includes: Generate user location coordinates based on visual recognition data and lidar point cloud data; If the distance between the shot coordinates in the missed shot information input by the user and the user's position coordinates is less than a distance threshold, determining that the missed shot information is a duplicate score, and rendering a prompt interface to the vehicle screen; A deletion operation is received from the user on the prompt interface, and the missed shot information confirmed by the user is deleted.

[0013] In addition, to achieve the above-mentioned objectives, the present application also proposes a golf intelligent scoring device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the golf intelligent scoring method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the steps of the golf intelligent scoring method described above are implemented.

[0015] This application provides an intelligent golf scoring method. This application first responds to a user's scoring initiation action by fusing point cloud data with robot vision data to generate user behavioral feature data. Based on this behavioral feature data, the application determines the user's movement intent. Based on this movement intent, a corresponding scoring mode is triggered to collect the user's total score. Based on the scoring rules corresponding to the target task, the score for the target hole is calculated based on the total score and simultaneously rendered to the vehicle's screen for display. By fusing lidar point cloud data with machine vision data, this application improves motion capture accuracy, constructs user behavioral features in real time, analyzes movement intent based on a neural network model, triggers a corresponding scoring mode, collects the user's total score, and improves the real-time nature of scoring. The user's score is calculated according to preset rules and synchronized to the vehicle's screen in real time, enabling the full golf scoring process and improving golf scoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of the first embodiment of the golf intelligent scoring method of the present application is provided; Figure 2 A flowchart of the second embodiment of the golf intelligent scoring method of this application is provided; Figure 3 A flowchart of the third embodiment of the golf intelligent scoring method of this application is provided; Figure 4 A flowchart illustrating a fourth embodiment of the golf intelligent scoring method of the present application is provided; Figure 5 A flowchart of the fifth embodiment of the golf intelligent scoring method of the present application is provided; Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the golf intelligent scoring method in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] The main solutions of the embodiments of this application are: At present, the traditional golf scoring method relies on manual handwritten scorecard recording. Users need to pause the game after hitting the ball to manually record the number of strokes. The manual recording process is affected by environmental interference and subjective judgment differences, and is prone to omissions and errors. This leads to deviations between the scoring data and the actual movement status, which in turn affects the scoring accuracy.

[0023] This application improves the accuracy of motion capture by integrating lidar point cloud and machine vision data, builds user behavior characteristics in real time, analyzes movement intentions based on neural network models and triggers corresponding scoring modes, collects the user's total number of strokes, improves the real-time nature of scoring, calculates the user's score according to preset rules and synchronizes it to the car screen in real time, realizes the full process of golf scoring, and improves the accuracy of golf scoring.

[0024] It should be noted that the execution entity of this embodiment can be a golf smart scoring system, or a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, or mobile phone, or a golf smart scoring system control device capable of implementing the aforementioned functions. This embodiment is not specifically limited to these. The following describes this embodiment and the following embodiments using the golf smart scoring system as the execution entity.

[0025] Example 1 Based on this, this application proposes a first embodiment of a golf intelligent scoring method, please refer to Figure 1 , the golf intelligent scoring method includes: Step S10 , in response to the user's scoring start operation, fusing the point cloud data with the robot vision data to generate the user's behavior feature data.

[0026] By fusing multimodal sensor data, a three-dimensional motion model of user behavior is constructed to provide input for subsequent intent recognition and scoring triggering, avoiding incomplete motion capture or misjudgment caused by environmental interference from a single data source.

[0027] In this embodiment, point cloud data is a 3D coordinate sequence of the user's skeletal joints generated by LiDAR scanning. Robot vision data is an RGB image stream and depth map captured by a Time of Flight (TOF) sensor or RGB camera, combined with computer vision algorithms to extract dynamic user behavior features. Behavioral feature data is a multidimensional time-series feature vector that fuses point cloud skeletal node displacements with visual optical flow vectors.

[0028] As an optional implementation, when the user activates the scoring function, the lidar and time-of-flight sensor begin operating simultaneously. The lidar emits a laser beam at a specific scanning frequency, receives reflected light, and generates point cloud data containing the user's location information. The time-of-flight sensor captures a depth image of the user at a specific frame rate and uses a depth image processing algorithm to extract the user's position and posture information. This point cloud data is then fused with the depth image acquired by the time-of-flight sensor to generate user behavioral profile data.

[0029] As another optional implementation, when the user activates the scoring function, the lidar is activated to emit a laser beam at a certain scanning frequency, receive reflected light, and generate point cloud data containing the user's location information. Simultaneously, the camera captures images and uses a target detection algorithm to identify the user and extract characteristic information such as the user's position and posture in the image. This point cloud data is then fused with the visual information and converted from the lidar coordinate system to the camera coordinate system through coordinate transformation to generate user behavioral feature data.

[0030] Optionally, step S10 includes: Step S11: receiving the scoring start instruction from the user, activating the sensor array to acquire the point cloud data in real time, and capturing the robot vision data through the RGB camera.

[0031] It should be noted that the sensor array includes a collection of sensors such as LiDAR, which is used to collect real-time three-dimensional spatial data of the user and the environment. The RGB camera is a visual sensor that supports high-resolution color image acquisition, which is used to capture user movement details and output visual data in RGB format.

[0032] Optionally, the sensor array may also include a time-of-flight sensor, which is a sensor technology that uses the flight time of a light pulse to measure the distance between a target object and the sensor. It obtains depth information by emitting modulated infrared light and measuring the phase difference or time difference of the reflected light relative to the emitted light, thereby generating three-dimensional point cloud data.

[0033] As an optional implementation, after receiving the user's scoring start instruction, the lidar is controlled to start scanning at a preset scanning frequency to obtain point cloud data of the surrounding environment, and at the same time, the RGB camera is started to capture the user's visual data at a preset frame rate.

[0034] Step S12: removing outliers from the point cloud data through statistical filtering, and separating the user point cloud data from the background point cloud data based on a clustering algorithm.

[0035] The acquired point cloud data is preprocessed to remove abnormal points and separate user point cloud data from background point cloud data to improve data accuracy.

[0036] It should be noted that statistical filtering is a filtering method based on the statistical characteristics of data and is used to remove outliers in point cloud data. Clustering algorithms are algorithms that divide points in a dataset into different clusters based on similarity and are used to separate user point cloud data from background point cloud data.

[0037] For example, distance-based statistical filtering is used to calculate the distance statistics between each point and its neighboring points, removing outliers that are too far away. A K-means clustering algorithm is then applied to the filtered point cloud data for cluster analysis, separating the user point cloud data from the background point cloud data based on features such as point density or distance.

[0038] Step S13: extract the coordinates of the user's skeletal joints from the robot vision data, calculate the dense optical flow field through an algorithm, and generate the user's motion vector data.

[0039] It's important to note that skeletal joint coordinates describe the locations of key points on the human skeleton and are used to represent human posture. Dense optical flow is a vector field that describes the direction and velocity of motion for each pixel in an image and is used to capture object motion information. Motion vector data represents the direction and velocity of motion of an object or person in an image sequence.

[0040] As an optional implementation, a human pose estimation algorithm is used to process the RGB image and extract the coordinates of the user's skeletal joints. An optical flow algorithm is then used to calculate the dense optical flow field between adjacent frames, generating a motion vector for each pixel. Based on the skeletal joint coordinates and the dense optical flow field, motion vector data is generated to describe the user's motion state.

[0041] Step S14: Synchronize the user point cloud data and the motion vector data based on the timestamp to determine the user's behavior feature data.

[0042] The user point cloud data and motion vector data are synchronized based on timestamps, integrated to generate user behavior feature data, and provide data support for subsequent intent recognition and scoring.

[0043] It should be noted that timestamp-based synchronization aligns data from different sources based on their time stamps to ensure data synchronization. Behavioral feature data is data that integrates multiple aspects of user information such as location, posture, and movement, and is used to describe user behavioral characteristics.

[0044] Exemplarily, based on the timestamps of the point cloud data and the motion vector data, the data corresponding to the timestamps are matched, the synchronized data are fused, and the position information in the point cloud data is combined with the motion information in the motion vector data to generate complete behavioral feature data.

[0045] Optionally, for data with time differences, an interpolation method is used to process the data to ensure data synchronization.

[0046] Step S20: determining the user's movement intention based on the behavior characteristic data.

[0047] Analyze and predict the user's behavioral characteristics to accurately judge the user's movement intention, control the navigation system to follow, and count the user's number of hits.

[0048] In this embodiment, the movement intention is the user's intention in motion, including walking, stopping, etc.

[0049] As an optional implementation, the preprocessed behavioral feature vector sequence is input into a trained neural network model, and the model outputs the user's intention probability distribution and confidence score. The user's intention is determined based on the probability distribution and confidence score.

[0050] As another optional implementation, the extracted behavioral features are matched against pre-set rule templates. The similarity between the feature vector and the template is measured using methods such as Euclidean distance and cosine similarity. The similarity is calculated and, based on the matching results, the movement intention corresponding to the rule template with the highest similarity is selected as the judgment result. The pre-set rule templates are a series of rule templates defined based on domain knowledge and experience, used to describe the behavioral feature patterns corresponding to different movement intentions.

[0051] Optionally, step S20 includes: Step S21: input the behavior feature data into the trained neural network model.

[0052] It should be noted that the neural network model is a time series classification model based on the LSTM-TCN hybrid architecture. It takes a behavior feature vector as input and outputs a probability distribution of movement intention and a confidence score. The LSTM-TCN hybrid architecture is a neural network architecture that combines a long short-term memory network (LSTM) and a temporal convolutional network (TCN).

[0053] Optionally, a time series classification neural network model based on the LSTM-TCN hybrid architecture is constructed. The LSTM layer is used to encode the behavioral feature vector sequence to capture the long-term dependencies in the time series data. The output of the LSTM is passed through the TCN layer, and dilated convolution is used to capture local features and enhance the expressiveness of the model. A fully connected layer is added to map the hybrid features to the probability distribution of mobile intent and calculate the confidence score.

[0054] Optionally, collect a large amount of user behavior feature data, label it with the corresponding mobile intent categories, and construct a training dataset. Use an optimization objective such as the cross-entropy loss function to train the model through a backpropagation algorithm, adjusting the model parameters so that the model can accurately predict mobile intent and output the corresponding probability distribution and confidence score.

[0055] Step S22: parsing the behavior feature data through the neural network model, and outputting the movement intention category and the corresponding probability.

[0056] The behavioral feature data is analyzed through a neural network model to output the user's movement intention probability, providing a basis for subsequent navigation activation and shot counting.

[0057] For example, the preprocessed behavioral feature data is fed into a trained LSTM-TCN hybrid neural network model. The model encodes the time series data through the LSTM layer to capture long-term dependencies, and uses dilated convolutions in the TCN layer to capture local features, outputting a probability distribution of the user's movement intention.

[0058] Step S23: determining the user's movement intention according to the movement intention category and the corresponding probability.

[0059] For example, based on the probability distribution output by the model, the movement intention category with the highest probability is selected. If the model outputs a walking intention probability of 0.98 and a stationary intention probability of 0.02, the user's movement intention is walking.

[0060] Step S30: triggering a corresponding scoring mode according to the movement intention to collect the total score of the user.

[0061] In this embodiment, scoring modes utilize different scoring rules and data collection methods triggered by movement intent. User movement triggers follow-up counting mode, while detection of entry into the putting green triggers putting mode. Total strokes, including stroke count and putts, are used to evaluate the user's performance.

[0062] Optionally, the movement intention may further include a swing and a putting action, wherein the swing action triggers a shot scoring mode, and the putting action triggers a putting scoring mode.

[0063] For example, based on the recognized movement intention, the system automatically switches to the corresponding scoring mode. If a swing is recognized, the stroke scoring mode is activated and the number of strokes is recorded. The system also detects in real time whether the user has entered the preset green coordinate area. If so, the system automatically switches to the putting mode and begins counting putts.

[0064] Optionally, step S30 includes: Step S31: If the probability that the movement intention is movement is greater than a preset threshold, the navigation system is activated, enters a follow-up counting mode, and counts the number of strokes.

[0065] It should be noted that the preset threshold is a pre-set probability value threshold used to determine the reliability of the movement intention. The navigation system is a system built into the golf bag cart for achieving autonomous navigation, which can plan a path based on the user's movement intention and control the device to follow it.

[0066] For example, if the probability of movement is 0.7, which is greater than the preset threshold of 0.6, the navigation system is activated to start following the user and record the number of shots.

[0067] For example, in follow-count mode, sensors continuously monitor the user's motion status. If the user is detected to be motionless for a certain period of time, the user is deemed to have stopped moving, and the follow-up operation is stopped. The number of strokes is updated to the total number of strokes, so that the next time the user moves, the number of strokes can be counted again.

[0068] Optionally, each time the user's stroke count is updated, a voice announcement is made so that the user can check the stroke count information.

[0069] Step S32: The position coordinates of the golf bag cart are acquired in real time through the positioning system. If it is detected that the position coordinates are located in a preset green coordinate area, the mode is switched to putting mode and the number of putts is counted.

[0070] In this embodiment, the green coordinate area is a coordinate range of a green area pre-set in a golf course map.

[0071] It should be noted that in golf, the putting green is a key part of the game, and its scoring rules differ from those of other areas of the course. When a user enters the putting green, switching to putting mode and counting putts can more accurately record the user's performance on the green, providing accurate data for subsequent scoring. At the same time, putting mode may involve different navigation strategies and scoring rules, so it is necessary to switch the system mode promptly to adapt to the green environment.

[0072] Optionally, the coordinates of the boundary points of the green are obtained through a global positioning system (GPS) and stored in the system.

[0073] Optionally, the user's location information is acquired in real time, and the relative position between the user and the device is continuously updated via sensors. Based on the acquired location information, the difference between the current distance and a preset following distance is calculated. If the current distance is greater than the preset distance, the device accelerates forward to close the gap; if the current distance is less than the preset distance, the device decelerates or moves backward to maintain the distance.

[0074] As an optional implementation, the golf cart's real-time coordinates are acquired through a positioning system. These coordinates are then matched against a preset green coordinate area. If the coordinates are within the green coordinate area, the user is deemed to have entered the green. Upon determining that the user has entered the green area, the system automatically switches to putting mode. Sensors capture the user's putting motion characteristics, and image processing and pattern recognition algorithms are used to detect movements such as arm swings and club movements. When motions matching the putting characteristics are detected, the putt count is incremented.

[0075] Optionally, the number of putts may be counted in the same manner as the number of strokes, with follow-up scoring being used on the green, with only the scoring data of the two being differentiated, without distinguishing the scoring methods.

[0076] Step S33: updating the total number of strokes of the user according to the number of strokes and the number of putts.

[0077] It should be noted that the total number of strokes is the total number of strokes taken by the user in golf, including the number of strokes taken for long-distance shots on the course and the number of putts taken on the green.

[0078] For example, based on the new number of strokes and putts, the user's scoring data is updated, "total number of strokes = number of strokes + number of putts".

[0079] As an optional implementation, the system identifies the user's strokes and records the precise time of each stroke using a built-in high-precision clock. This time is used to analyze the user's stroke rhythm and timing management. A positioning system is used to obtain the real-time coordinates of the golf ball's impact point and, in conjunction with a laser rangefinder, measure the distance from the impact point to the impact point, recording the start and end positions of each stroke. The collected time and position data is filtered to remove abnormal data, and the time, position, and total stroke count are integrated into a stroke data table. Based on the information recorded in the stroke data table, the system analyzes the user's stroke performance and provides personalized training recommendations based on the data analysis results.

[0080] Optionally, a pressure sensor is provided on the golf club of the golf cart to measure the force exerted by the golf club on the ball at the moment of hitting the ball, and the force and speed of the hitting are calculated through the sensor data.

[0081] Step S40 , based on the scoring rules corresponding to the target task, the score of the target hole is calculated according to the total number of strokes, and is synchronously rendered to the vehicle screen for display.

[0082] In this embodiment, the target task refers to the type of golf tournament the user is currently participating in, including Stableford, Stroke Play, Foursomes, etc. Different tournaments correspond to different scoring rules and strategies. Scoring rules are the rules used to calculate scores based on the rules and standards of the target task.

[0083] As an optional implementation, data on the number of strokes and putts for the current hole is obtained. Based on the scoring rules corresponding to the target task, a formula and parameters for calculating the score are determined. The formula can be: "Target hole score = total strokes x coefficient." The total strokes obtained are substituted into the scoring formula to calculate the score. The score data is transmitted to the screen's graphics processing unit via the in-vehicle network. A graphics rendering engine converts the score information into an image signal for real-time display on the in-vehicle screen.

[0084] Optionally, if the scoring rule is total strokes minus par, obtain the par specified by the course and calculate the score.

[0085] Optionally, data from the golf course's wind speed sensors and slope meters can be collected to monitor wind speed, direction, and slope in different areas in real time. Combined with the golf cart's positioning data, this data can be used to capture real-time environmental factors at the time of each shot. Based on the impact of these environmental factors on scores, a correction algorithm can be designed. When calculating the score for the target hole, the algorithm can be used to make corresponding corrections and adjustments. The impact of these environmental factors on the score, along with the corrected score, can be displayed on the cart's screen.

[0086] For example, wind speed will affect the flight distance of a golf ball. When the wind is with you, the ball will fly farther; when the wind is against you, the ball will fly closer. Use the formula to make corrections, the formula is "corrected distance = actual distance × (1 + k × wind speed)", where k is the wind speed correction factor, determined by prior testing or experience. The slope will affect the force of the shot. When going uphill, greater force is required; when going downhill, the force can be smaller. Use the formula to make corrections, the formula is "corrected force = actual force × (1 + m × slope)", where m is the slope correction factor, determined by prior testing or experience. Combining factors such as wind speed and slope, a comprehensive correction formula is designed, the formula is "corrected score = actual score × (1 + k × wind speed + m × slope)".

[0087] This embodiment provides an intelligent golf scoring method. This embodiment first improves the accuracy of motion capture by integrating lidar point cloud and machine vision data, builds user behavior characteristics in real time, analyzes movement intentions based on a neural network model and triggers corresponding scoring modes, collects the user's total number of strokes, improves the real-time nature of scoring, calculates the user's score according to preset rules and synchronizes it to the vehicle screen in real time, realizes the full process of golf scoring, and improves golf scoring accuracy.

[0088] Based on Example 1, Example 2 of this application proposes a golf intelligent scoring method, referring to Figure 2 , after step S30, the following steps are included: Optionally, in addition to counting when the golf bag cart follows the user, it can also count when the user approaches the golf bag cart, and determine whether the user is approaching by judging the distance between the user and the golf bag cart.

[0089] It should be noted that, since golf clubs need to be frequently changed, when the user approaches, it can be determined that the user has changed clubs, and thus the stroke count is performed.

[0090] Step S50: detecting the user distance by a time-of-flight sensor to determine whether the user enters a preset range.

[0091] It should be noted that time-of-flight sensors calculate the distance to an object by measuring the time difference between the emitted light pulse and the received reflected light. This generates a depth image and provides highly accurate distance measurement. The preset range is a distance interval pre-set based on the specific application scenario, used to determine whether the user is within the effective range required for interaction.

[0092] As an optional implementation, a time-of-flight sensor emits infrared light pulses at a set frequency and receives reflected light to calculate the real-time distance between the user and the sensor. The collected distance data is filtered to remove outliers and compared to a preset range. If the distance data is within the preset range, the user is considered to have entered the preset range, triggering further verification.

[0093] Step S60: Based on the RGB camera, face recognition or gait analysis is performed to verify the user's identity and determine whether the user is the target user.

[0094] It should be noted that an RGB camera is capable of capturing color images and outputs image data in RGB format. Face recognition is a facial feature extraction and matching algorithm based on convolutional neural networks. It extracts facial features and compares them to known facial features in a database to identify and verify an individual's identity. Gait analysis extracts walking posture features from a time-series sequence of skeletal joints for authentication purposes. It is applicable when a clear facial image is unavailable.

[0095] It should be noted that when a user starts the scoring mode, face recognition or gait analysis is performed, and the user's face and gait are saved in the database as the target user.

[0096] As an optional implementation, an RGB camera is used to capture the facial image of the user to be detected, a face detection algorithm is used to detect the face area in the image, facial features are extracted, and compared with the facial features of the target user in the database. Based on the results of the facial feature comparison, a similarity score is calculated. If the similarity score is higher than a set threshold, the current user is determined to be the target user.

[0097] As another optional implementation, a full-body image of the user to be detected is captured by an RGB camera, and gait features such as the user's body posture, step length, and step frequency when walking are extracted. The gait features are matched with the target user's gait features through a machine learning model. Based on the results of the gait feature comparison, a similarity score is calculated. If the similarity score is higher than the set threshold, the current user is determined to be the target user.

[0098] Step S70: If it is detected that the target user enters a preset range, a shot counting is triggered and the shot count of the target user is updated.

[0099] As an optional implementation, when the target user enters the preset range, the shot count is automatically triggered, and the number of shots of the target user is directly increased.

[0100] As another optional implementation, after the target user enters a preset range, sensors collect the user's motion data in real time. A camera captures the user's batting motion, and an accelerometer and gyroscope collect arm acceleration and rotational angular velocity data during the batting. This collected data is then preprocessed. By analyzing the preprocessed data for changes in ball displacement, club trajectory, or sudden changes in acceleration and angular velocity, a determination is made as to whether a batting action has occurred. When an action matching batting characteristics is detected, a batting counter is triggered, incrementing the batting count by one.

[0101] This embodiment provides an intelligent golf scoring method. This embodiment first uses a time-of-flight sensor to perform high-precision distance measurement to accurately determine whether the user has entered a preset range. By combining facial recognition and gait analysis, multimodal biometrics are used to improve the accuracy of identity authentication, precisely trigger shot counting, and improve scoring accuracy.

[0102] Based on the first embodiment, the third embodiment of the present application proposes a golf intelligent scoring method, referring to Figure 3 , after step S40, the following steps are included: Step S80: establishing a communication connection with at least one golf cart in a team through a wireless communication module to form a vehicle ad hoc network.

[0103] Through the wireless communication module, a communication connection is established with the golf carts in the team to form a vehicle self-organizing network, realizing data sharing and collaborative work between vehicles.

[0104] It should be noted that wireless communication modules are wireless communication devices within golf carts, including Wi-Fi modules, Bluetooth modules, and 4G / 5G modules, used to enable wireless data transmission between vehicles. Team golf carts are multiple golf carts participating in a team, requiring communication and collaboration to achieve data sharing and coordination. A vehicle-based ad hoc network (VAN) is a network spontaneously formed by multiple team golf carts using wireless communication modules. Team golf carts can directly communicate and exchange data through the VAN.

[0105] As an optional implementation, the golf cart's wireless communication module is activated, entering scanning and discovery mode to automatically search for nearby teamed golf carts. Upon detecting other carts, a connection request is initiated based on user input, establishing a communication link and forming a vehicle-to-vehicle network. Each teamed golf cart is associated with its corresponding user's information, allowing them to communicate and transmit data, including location information, scoring data, and user identity information.

[0106] Optionally, a wireless communication module is installed on each golf cart, and network parameters are configured, with the same network name, password, and communication protocol set to ensure that the communication modules of all golf carts operate on the same frequency band and channel.

[0107] Step S90: receiving and analyzing the score data of the golf cart team, and dynamically rendering the score data to the on-board screen according to a preset display template.

[0108] Receive and analyze the scoring data sent by the team golf carts, and dynamically render it to the on-board screen according to the preset display template, so as to realize the real-time display and sharing of the scores of each golf cart.

[0109] It should be noted that score data refers to a user's golf score information, including strokes, putts, hole scores, and other information, used to evaluate the user's performance. Pre-set display templates are pre-designed interface layouts and styles for displaying score data, including tables, charts, leaderboards, and other formats.

[0110] For example, the wireless communication module receives score data packets from the team golf cart in real time, parses the received data packets, and extracts key information such as user ID, hole number, number of strokes, number of putts, and score. Based on a preset display template, the parsed score data is bound to the corresponding display element, and the bound display template is converted into an image signal, which is dynamically rendered and displayed on the vehicle screen.

[0111] Optionally, each time the score data is updated, the updated data packet is transmitted to all teamed golf carts in the vehicle ad hoc network.

[0112] This embodiment provides a smart golf scoring method. First, this embodiment establishes a connection between multiple golf carts through a wireless communication module to achieve real-time data transmission and sharing, improve the collaboration efficiency between teams, and dynamically render the scoring data of the team golf carts to the on-board screen so that users can view the latest scores in real time.

[0113] Based on the first embodiment, the fourth embodiment of the present application proposes a golf intelligent scoring method, referring to Figure 4 , the golf intelligent scoring method further includes: Step A10 , in response to the user's long press operation on the vehicle-mounted remote control, determining that the ball is out of bounds, and recording the number of penalty strokes based on the corresponding penalty rules.

[0114] In golf, when the ball goes out of bounds, the penalty strokes are recorded according to the penalty rules. By long-pressing the in-car remote control, you can quickly determine that the ball is out of bounds and record the penalty strokes, ensuring accurate scoring.

[0115] It should be noted that the on-board remote control is a remote control device installed on the golf cart, which allows users to interact with the scoring system through key operations. A long press operation is when the user continuously presses a button on the remote control for longer than a preset time to trigger the penalty stroke function.

[0116] For example, when it is detected that the button is pressed for more than 2 seconds, it is judged as a long press operation. When the long press operation is detected, the number of penalty strokes is increased according to the preset penalty rules. If the penalty rule of the current target task is that the ball out of bounds is penalized 1 stroke, the number of penalty strokes is increased by 1, and the penalty stroke is recorded in the current user's scoring data.

[0117] Optionally, a prompt message is displayed on the vehicle screen, or the number of penalty strokes is prompted to the user through a voice module.

[0118] Optionally, the golf bag cart may further include an integrated physical button array, including at least one penalty stroke button and a make-up button, for user-assisted scoring.

[0119] It should be noted that the physical button array is a collection of multiple physical buttons installed on the golf cart, each with a specific function, including penalty stroke recording and score completion. The penalty button is used to record penalty strokes. When the ball goes out of bounds or other penalty strokes are required, the user can long-press this button to trigger the penalty stroke recording function. The re-record button is used to enter the re-record mode. When the user needs to complete or correct shot information, they can long-press this button to trigger the re-record function.

[0120] Alternatively, there may be one physical button, with different functions being executed by different button operations. The physical button is connected to the control system of the golf bag cart, and each button has an independent circuit connection to ensure that the corresponding function can be accurately triggered when pressed.

[0121] Step A20 , in response to a short press operation of the vehicle-mounted remote controller by the user, enters a scoring completion mode, receives the missed shot information input by the user, and completes and updates the shot count.

[0122] It should be noted that the short press operation is a user quickly pressing and releasing a button on the remote control to trigger the completion scoring function.

[0123] As an optional embodiment, when a short press of the vehicle remote control is detected, the system enters a scoring completion mode and displays a prompt message on the vehicle screen. The score is completed based on the received key press. When a single press of the key is detected, the score count is increased. When a double press of the key is detected, the score count is canceled to prevent users from accidentally operating the count.

[0124] As another optional implementation, the missed shot information input by the user is received through the input device on the remote control, including the number of missed shots, shot positions and other information, and the missed shot information input by the user is integrated into the original scoring data to update the number of strokes.

[0125] Optionally, the physical button array can be used to complete the scoring. Upon detecting that the user has long-pressed the "complete" button for a predetermined period of time, the system enters a complete scoring mode, prompting the user to enter the missed shot information. The user's input is then verified to ensure its validity. The user's inputted missed shot information is then integrated into the original score data, and the stroke count is updated.

[0126] Optionally, after entering the completion scoring mode, the input interface is rendered on the onboard screen of the golf bag cart, allowing the user to input the missed shot information through the onboard screen touch screen or other buttons in the physical button array.

[0127] Step A30: updating the user's total score based on the number of penalty strokes and the completed stroke count, recalculating the score and rendering it to the vehicle screen in real time.

[0128] For example, the scoring module obtains the number of penalty strokes and the completed stroke count data to update the total stroke count: "Total strokes = strokes + penalty strokes." Based on the preset scoring rules, the formula is "score = total strokes × weight coefficient." The score data is recalculated and rendered on the in-vehicle screen according to the preset display template.

[0129] This embodiment provides a smart golf scoring method. First, through the vehicle-mounted remote control, this embodiment allows the user to perform penalty strokes for out-of-bounds shots and complete missed shot information, thereby improving the integrity and accuracy of scoring data.

[0130] Based on the fourth embodiment, the fifth embodiment of the present application proposes a golf intelligent scoring method, referring to Figure 5 , after step A20, including: Step A40: Generate user location coordinates based on visual recognition data and lidar point cloud data.

[0131] It should be noted that visual recognition data is image data captured by a camera, processed by object detection and recognition algorithms, and then used to obtain information about the user's location. LiDAR point cloud data is data containing three-dimensional point coordinates generated by a LiDAR scanning environment, reflecting the user's precise position in space.

[0132] As an optional implementation, cameras and lidar sensors collect visual recognition data and point cloud data in real time. Target detection and tracking are performed on the visual recognition data to extract the user's position in the image. The lidar point cloud data is filtered and clustered to isolate the user-related point cloud. The two-dimensional position information in the visual recognition data is converted to the lidar's three-dimensional coordinate system. The two data sources are then fused using a Kalman filter algorithm to generate the user's position coordinates.

[0133] Step A50: If the distance between the shot coordinates in the missed shot information input by the user and the user position coordinates is less than a distance threshold, the missed shot information is determined to be a duplicate score, and a prompt interface is rendered to the vehicle screen.

[0134] It should be noted that the hitting coordinates are the hitting position information input by the user in the complete scoring mode.

[0135] Exemplarily, the Euclidean distance between the hitting coordinates input by the user and the user's position coordinates is calculated, and the calculated distance is compared with a preset distance threshold. If the distance is less than the threshold, it is determined to be a duplicate score, and a prompt interface is rendered on the vehicle screen to ask the user whether to delete it.

[0136] Alternatively, if the missed shot information only includes the information of the user's key scoring but does not include the shot coordinate information, it is only necessary to detect whether the user's current shot has been counted in the number of strokes. This can be determined based on the scoring time. If the golf cart has already recorded a shot within the time threshold, the missed shot information is determined to be a duplicate score.

[0137] Step A60: receiving a deletion operation from the user on the prompt interface, and deleting the missed shot information confirmed by the user.

[0138] Receive the user's deletion operation in the prompt interface, remove the missed shot information confirmed by the user from the scoring data, ensure the accuracy and completeness of the scoring data, and avoid the impact of duplicate scoring on the final score.

[0139] Exemplarily, the user's operation on the prompt interface is detected. If the user chooses to delete the missed shot information of the repeated scoring, the corresponding missed shot information is removed from the scoring data, and the scoring data is updated.

[0140] Optionally, if the user chooses to retain the missed shot information in the prompt interface, the scoring data remains unchanged.

[0141] This embodiment provides an intelligent golf scoring method. By combining visual recognition data and LiDAR point cloud data, this embodiment accurately generates the user's position coordinates in three-dimensional space. By calculating the distance between the shot coordinates and the user's position coordinates and comparing them with a distance threshold, it effectively detects whether missed shot information entered by the user constitutes a duplicate score, improving scoring accuracy. Upon user deletion, confirmed missed shot information is removed from the scoring data, ensuring the accuracy and integrity of the scoring data and preventing duplicate scores from impacting the final score.

[0142] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the golf intelligent scoring method of the present application. Simple transformations in more forms based on this technical concept are all within the scope of protection of the present application.

[0143] The present application provides a golf smart scoring device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the golf smart scoring method of the first embodiment described above.

[0144] Reference below Figure 6 , which shows a schematic diagram of the structure of a golf smart scoring device suitable for implementing embodiments of the present application. The golf smart scoring device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as desktop computers. Figure 6 The golf smart scoring device shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0145] like Figure 6As shown, the golf intelligent scoring device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the golf intelligent scoring device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 may allow the golf smart scoring device to communicate with other devices wirelessly or wired to exchange data. While the figure shows a golf smart scoring device with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0146] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0147] The intelligent golf scoring device provided in this application utilizes the intelligent golf scoring method described in the aforementioned embodiment to address the technical problem of improving golf scoring accuracy. Compared to the prior art, the beneficial effects of the intelligent golf scoring device provided in this application are the same as those of the intelligent golf scoring method described in the aforementioned embodiment. Other technical features of the intelligent golf scoring device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0148] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0149] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0150] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the golf intelligent scoring method in the above-mentioned embodiment.

[0151] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0152] The computer-readable storage medium may be included in the golf intelligent scoring device; or it may exist independently without being assembled into the golf intelligent scoring device.

[0153] The computer-readable storage medium carries one or more programs that, when executed by the golf smart scoring device, enable the golf smart scoring device to write computer program code for performing the operations of the present application in one or more programming languages, or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0155] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0156] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned intelligent golf scoring method, thereby solving the technical problem of improving golf scoring accuracy. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the intelligent golf scoring method provided in the aforementioned embodiments, and are not further elaborated here.

[0157] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A golf intelligent scoring method, characterized in that: The golf intelligent scoring method includes: In response to a scoring start operation by a user, fusing the point cloud data with the robot vision data to generate behavioral feature data of the user; determining the user's movement intention based on the behavioral characteristic data; triggering a corresponding scoring mode according to the movement intention to collect the total score of the user; Based on the scoring rules corresponding to the target task, the score of the target hole is calculated according to the total number of strokes and synchronously rendered to the in-vehicle screen for display.

2. The golf intelligent scoring method according to claim 1, wherein: The step of generating the user's behavior feature data by fusing the point cloud data with the robot vision data in response to the user's scoring start operation includes: Upon receiving a scoring start instruction from the user, activating a sensor array to acquire the point cloud data in real time, and capturing the robot visual data through an RGB camera; Removing outliers from the point cloud data through statistical filtering, and separating user point cloud data from background point cloud data based on a clustering algorithm; Extracting the coordinates of the user's skeletal joints from the robot's visual data, calculating a dense optical flow field through an algorithm, and generating motion vector data of the user; The user point cloud data and the motion vector data are synchronized based on a timestamp to determine user behavior feature data.

3. The golf intelligent scoring method according to claim 1, wherein: After the step of triggering a corresponding scoring mode according to the movement intention to collect the total score of the user, the method further includes: Detecting the user's distance through a time-of-flight sensor to determine whether the user has entered a preset range; Based on the RGB camera, face recognition or gait analysis is performed to verify the user's identity and determine whether the user is the target user; If it is detected that the target user enters the preset range, the shot counting is triggered and the shot count of the target user is updated.

4. The golf intelligent scoring method according to claim 1, wherein: The step of determining the user's movement intention based on the behavior characteristic data includes: Inputting the behavioral feature data into a trained neural network model; Analyzing the behavior feature data through the neural network model and outputting the movement intention category and the corresponding probability; The user's movement intention is determined according to the movement intention category and the corresponding probability.

5. The golf intelligent scoring method according to claim 1, wherein: The step of triggering a corresponding scoring mode according to the movement intention to collect the total score of the user includes: If the probability that the movement intention is movement is greater than a preset threshold, activating the navigation system, entering a follow-up counting mode, and counting the number of strokes; The positioning system obtains the coordinates of the golf cart in real time. If the coordinates are detected to be within a preset green coordinate area, the system switches to a putting mode and counts the number of putts. The total number of strokes of the user is updated according to the number of strokes and the number of putts.

6. The golf intelligent scoring method according to claim 1, wherein: After the step of calculating the score of the target hole according to the total number of strokes based on the scoring rules corresponding to the target task and synchronously rendering it to the vehicle-mounted screen for display, the method includes: Establishing a communication connection with at least one golf cart in a team through a wireless communication module to form a vehicle ad hoc network; The scoring data of the golf carts in the team is received and analyzed, and dynamically rendered to the on-board screen according to a preset display template.

7. The golf intelligent scoring method according to claim 1, wherein: The golf intelligent scoring method further includes: In response to a long press operation of the in-vehicle remote control by the user, determining that the ball is out of bounds, and recording the number of penalty strokes based on the corresponding penalty rules; In response to a short press operation of the vehicle-mounted remote controller by the user, entering a completion scoring mode, receiving the missed shot information input by the user, and completing and updating the shot count; According to the number of penalty strokes and the completed number of strokes, the user's total number of strokes is updated, the score is recalculated and rendered to the in-vehicle screen in real time.

8. The golf intelligent scoring method according to claim 7, wherein: After the step of entering the scoring completion mode in response to a short press operation of the vehicle-mounted remote controller by the user, receiving the missed shot information input by the user, and completing and updating the shot count, the method includes: Generate user location coordinates based on visual recognition data and lidar point cloud data; If the distance between the shot coordinates in the missed shot information input by the user and the user's position coordinates is less than a distance threshold, determining that the missed shot information is a duplicate score, and rendering a prompt interface to the vehicle screen; A deletion operation is received from the user on the prompt interface, and the missed shot information confirmed by the user is deleted.

9. A golf intelligent scoring device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the golf intelligent scoring method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the golf intelligent scoring method according to any one of claims 1 to 8 are implemented.

Images