基于图优化 DWA 算法的篮球运动员运球轨迹实时识别方法

Real-Time Recognition Method of Basketball Player's Dribbling Trajectory Based on Graph Optimization DWA Algorithm

摘要

针对篮球运动高速运球动作中, 球员突破时会产生位移模糊及运动模糊效应, 难以获取篮球运动员运球轨迹图, 导致运球与实际轨迹间存在偏差的问题, 提出基于图优化 DWA(Dynamic Window Approach)算法的篮球运动员运球轨迹实时识别方法。 获取目标运动员点云数据, 并针对篮球场地及障碍项(其他运动员), 建立栅格地图, 构建运动学模型并建立动态窗口, 模拟出目标运动员的多条运球预测轨迹, 通过动态窗口判定轨迹安全情况, 从多个维度评价确定最佳运球预测轨迹。 根据所预测的轨迹, 获取运球过程中的转折点及路径点, 结合 A^*算法获取动态避障路线, 通过剪枝算法得出轨迹图模型。 通过设计启发函数构建最终评价函数, 根据评价结果, 确定轨迹图模型中的最优轨迹点, 并利用贝塞尔曲线平滑处理所得轨迹, 通过遍历图模型确定轨迹点优先级别, 综合处理坐标得出平滑性较好的轨迹并可视化输出结果。 实验结果表明, 该方法所得识别的运动员运球与实际轨迹间的偏差小于 5 cm, 证明该方法识别篮球运动员运球轨迹准确性较高。

Abstract

During the high-speed dribbling action in basketball, when a player breaks through, displacement blurring occurs, resulting in a motion blurring effect. It is difficult to obtain the dribbling trajectory map of a basketball player, leading to a deviation between the dribbling trajectory and the actual trajectory. Therefore, a real-time recognition method for basketball players' dribbling trajectories based on the graph optimization DWA (Dynamic Window Approach) algorithm is proposed. Obtaining the point cloud data of the target athlete, and for the basketball court and obstacle events (other athletes), establishing a raster map, a kinematic model is constructed and a dynamic window is established to simulate multiple dribbling prediction trajectories of the target athlete. The trajectory safety is determined through the dynamic window and the best dribbling prediction trajectory from multiple dimensions is evaluated and determined. Based on the predicted trajectory, the turning points and path points during the dribbling process are obtained. Combined with the A ^* algorithm, the dynamic obstacle avoidance route is acquired, and the trajectory graph model is derived through the pruning algorithm. The final evaluation function is constructed by designing the heuristic function. According to the evaluation results, the optimal trajectory points in the trajectory graph model are determined, and the obtained trajectories are smoothed using Bezier curves. The priority level of the trajectory points is determined by traversing the graph model, and the trajectories with better smoothness are obtained by comprehensively processing the coordinates and visualizing the output results. The experimental results show that the deviation between the dribbling trajectories of the athletes identified by this method and the actual trajectories is less than 5cm, indicating that the dribbling trajectories of basketball players identified by this method have relatively high accuracy.

关键词

图优化 DWA 算法 / 轨迹图模型 / 动态窗口 / 栅格地图 / 贝塞尔曲线

Key words

graph optimization dynamic window approach(DWA) algorithm / trajectory diagram model / dynamic windows / raster maps / Bezier curves

参考文献

[1] 苏玺霖, 樊春玲, 张春堂. 基于机器视觉的爬管机器人路径信息识别算法[J]. 电子测量技术, 2022, 45(22): 92-98.

[2] SU X L, FAN C L, ZHANG C T. Path Information Recognition Algorithm of Tube Climbing Robot Based on Machine Vision[J]. Electronic Measurement Technology, 2022, 45(22): 92-98.

[3] 刘锋, 夏铁牛, 李亚卫. 双闭环 PID 应用下投篮机器人路径跟踪控制研究[J]. 机械设计与制造, 2024(1): 374-378.

[4] LIU F, XIA T N, LI Y W. Research on Path Tracking Control of Shooting Robot with Double Closed Loop PID Application[J]. Machinery Design & Manufacture, 2024(1): 374-378.

[5] 向红标, 杨大虎, 杨璐, 等. 复杂环境下磁弹性微型游泳机器人的路径规划与识别跟踪[J]. 机械工程学报, 2023, 59(5): 89-99.

[6] XIANG H B, YANG D H, YANG L, et al. Path Planning and Recognition Tracking of a Magnetoelastic Miniature Swimmer in Complex Environment[J]. Journal of Mechanical Engineering, 2023, 59(5): 89-99.

[7] 马佳玮, 孙菁伯, 迟关心, 等. 基于立体视觉和 YOLO 深度学习框架的焊缝识别与机器人路径规划算法[J]. 焊接学报, 2024, 45(11): 45-49.

[8] MA J W, SUN J B, CHI G X, et al. Weld Identification and Robot Path Planning Algorithm Based on Stereo Vision and YOLO Deep Learning Framework[J]. Transactions of the China Welding Institution, 2024, 45(11): 45-49.

[9] 朱立学, 莫冬炎, 官金炫, 等. 基于 U-Net 的肉鸽养殖场机器人视觉导航路径识别方法[J]. 中国农机化学报, 2023, 44(10): 217-223.

[10] ZHU L X, MO D Y, GUAN J X, et al. Path Recognition Method of Robot Visual Navigation for Meat Pigeon Breeding Farm Based on U-Net[J]. Journal of Chinese Agricultural Mechanization, 2023, 44(10): 217-223.

[11] 蒋华扬, 吴涛, 任建鑫, 等. 基于改进 DWA 算法的移动机器人局部路径规划[J]. 机械设计与研究, 2024, 40(5): 229-234.

[12] JIANG H Y, WU T, REN J X, et al. Research on Local Path Planning of Mobile Robot Based on Improved DWA Algorithm[J]. Machine Design and Research, 2024, 40(5): 229-234.

[13] 冯新, 杨雄, 曾豫豪. 多场景下基于 IGJO-DWA 算法的机器人路径规划[J]. 传感器与微系统, 2024, 43(11): 131-134, 138.

[14] FENG X, YANG X, ZENG Y H, et al. Robot Path Planning Based on IGJO-DWA Algorithm in Multiple Scenarios[J]. Transducer and Microsystem Technologies, 2024, 43(11): 131-134, 138.

[15] 刘宙浩, 万超一, 尹明锋, 等. 改进 A^* 算法与 DWA 融合的移动机器人的路径规划算法研究 [J]. 制造业自动化, 2023, 45(12): 55-60.

[16] LIU Y H, WAN C Y, YIN M F, et al. Research on Path Planning Algorithm of Mobile Robot Based on Improved A^* Algorithm and Dynamic Window Approach [J]. Manufacturing Automation, 2023, 45(12): 55-60.

[17] 李成, 黄学能, 石习双, 等. 超特高压输电线路导线非线性运动轨迹识别[J]. 电子设计工程, 2025, 33(9): 140-143, 148.

[18] LI C, HUANG X N, SHI X S, et al. Nonlinear Motion Trajectory Recognition of Ultra-High Voltage Transmission Line Conductors[J]. Electronic Design Engineering, 2025, 33(9): 140-143, 148.

[19] 毕松, 余鑫. 基于 3D 点云分析的果园行间穿梭机器人路径规划方法[J]. 农业机械学报, 2024, 55(10): 37-50.

[20] BI S, YU X. Path Planning Method for Inter-Row Shuttle in Densely Planted Orchards[J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(10): 37-50.

[21] 赵倩, 石宇强. 融合改进 A^*算法与 DWA 的 AGV 实时路径规划及避障研究 [J]. 现代制造工程, 2025(5): 91-98.

[22] ZHAO Q, SHI Y Q. Research on Real Time Path Planning and Obstacle Avoidance of AGV by Integrating Improved A^* Algorithm and DWA [J]. Modern Manufacturing Engineering, 2025(5): 91-98.

[23] 齐款款, 李二超, 毛玉燕. 改进 A^*算法融合自适应 DWA 的移动机器人动态路径规划 [J]. 数据采集与处理, 2023, 38(2): 451-467.

[24] QI K K, LI E C, MAO Y Y. Dynamic Path Planning of Mobile Robot Based on Improved A^* Algorithm and Adaptive DWA [J]. Journal of Data Acquisition and Processing, 2023, 38(2): 451-467.

[25] 郭文豪, 陈炎, 余任凭, 等. 融合跳点搜索和动态窗口算法的 AGV 路径规划[J]. 云南大学学报(自然科学版), 2025, 47(2): 233-243.

[26] GUO W H, CHEN Y, YU R P, et al. AGV Path Planning Combining Jump Point Search and Dynamic Window Algorithm[J]. Journal of Yunnan University (Natural Sciences Edition), 2025, 47(2): 233-243.

[27] 谢赛宝, 刘春阳, 陈帆, 等. 基于视觉的自主机器人障碍识别与路径规划[J]. 电子测量与仪器学报, 2022, 36(12): 185-192.

[28] XIE S B, LIU C Y, CHEN F, et al. Obstacle Recognition and Path Planning Method Based on Mobile Robot[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(12): 185-192.

[29] 刘钰铭, 黄海松, 范青松, 等. 基于改进 A^*-DWA 算法的移动机器人路径规划 [J]. 计算机集成制造系统, 2024, 30(1): 158-171.

[30] LIU Y M, HUANG H S, FAN Q S, et al. Mobile Robot Path Planning Based on Improved A^*-DWA Algorithm [J]. Computer Integrated Manufacturing Systems, 2024, 30(1): 158-171.

基金资助

陕西省体育局常规课题基金资助项目(2020348)

河北省高等教育学会“十四五”规划基金资助项目(GJXH2024-354)

河北省人力资源和社会保障厅基金资助项目(JRS-2024-1073)