基于单目视频的跳台滑雪飞行阶段数据提取方法

doi:10.16182/j.issn1004731x.joss.22-1408

系统仿真学报 ›› 2023, Vol. 35 ›› Issue (9): 2035-2044.doi: 10.16182/j.issn1004731x.joss.22-1408

基于单目视频的跳台滑雪飞行阶段数据提取方法

沈梓祎¹(), 杨猛¹^,²(), 杨超¹, 唐伟棣³, 伍勰³, 刘宇³, 盛斌⁴

^1.北京林业大学信息学院, 北京 100083
^2.国家林业草原林业智能信息处理工程技术研究中心, 北京 100083
^3.上海体育学院, 上海 200438
^4.上海交通大学计算机科学与工程系, 上海 200240

收稿日期:2022-11-23 修回日期:2023-01-30 出版日期:2023-09-25 发布日期:2023-09-19
通讯作者: 杨猛 E-mail:shenzyiii@foxmail.com;yangmeng@bjfu.edu.cn
第一作者简介:沈梓祎（1998-），女，硕士生，研究方向为图像与视频处理、虚拟现实。E-mail：shenzyiii@foxmail.com
基金资助:
国家重点研发计划(2019YFC1521104)

Method for Extracting Data During Flight Phase of Ski Jumping Based on Monocular Video

Shen Ziyi¹(), Yang Meng¹^,²(), Yang Chao¹, Tang Weidi³, Wu Xie³, Liu Yu³, Sheng Bin⁴

^1.School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
^2.Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China
^3.Shanghai Institute of Physical Education, Shanghai 200438, China
^4.Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2022-11-23 Revised:2023-01-30 Online:2023-09-25 Published:2023-09-19
Contact: Yang Meng E-mail:shenzyiii@foxmail.com;yangmeng@bjfu.edu.cn

摘要/Abstract

摘要：

针对跳台滑雪运动难度系数高，穿戴式传感器等入侵式设备易发生危险且价格昂贵而导致该运动数据提取困难的问题，提出了一种基于单目视频的跳台滑雪飞行阶段的数据提取方法。针对单目视频存在畸变和画面背景杂乱的问题进行预处理，通过标定相机参数对拍摄画面进行畸变矫正，并使用帧间差分法去除背景；利用OpenPose人体姿态识别库对运动员的关节位置进行初步识别，得到每一帧各个关节点的二维像素坐标；结合跳台滑雪运动员的姿态特性，针对识别出现误差的关节点，提出一种迭代拟合算法对其进行修正；根据修正后的关节点对运动员的运动特征进行提取与计算，并应用生成的人体模型与视频中运动员姿态进行动作比对。实验结果表明，迭代拟合算法提高了关节点识别准确率和识别精度，且修正关节点后生成的SMPL(skinned multi-person linear)三维人体模型更加贴合实际，证明了该算法对关节点修正的有效性。

关键词: 跳台滑雪飞行阶段, 人体关节点检测, 坐标修正, 二维轨迹提取, 三维人体模型对比

Abstract:

To solve the problem of the high difficulty factor of ski jumping and the difficulty of extracting data of this sport due to the danger of invasive devices such as wearable sensors and high price, a method for extracting data during the flight phase of ski jumping based on monocular video is proposed. The distortion and background clutter of the monocular video are preprocessed.The distortion of the captured images is corrected by calibrating camera parameters, and the background is removed by the inter-frame difference method. The human pose recognition library, namely OpenPose is used to initially identify the joint position of the athlete and obtain the 2Dpixel coordinates of each joint point in each frame. An iterative fitting algorithm is proposed to correct the joint points with errors in recognition by combining the pose characteristics of the athlete. The athletes' motion features are extracted and calculated according to the modified joint points, and the generated human models are applied to compare with the athletes' poses in the video. The experimental results show that the iterative fitting algorithm improves the accuracy and precision of joint point recognition, and the SMPL(skinned multi-person linear) 3D human body model generated after joint point correction is more suitable for reality, which proves the effectiveness of the algorithm for joint point correction.

Key words: flight phase of ski jumping, human joint point detection, coordinate correction, 2D track extraction, comparison of 3D human body model

中图分类号:

TP391.9

沈梓祎,杨猛,杨超等 . 基于单目视频的跳台滑雪飞行阶段数据提取方法[J]. 系统仿真学报, 2023, 35(9): 2035-2044.

Shen Ziyi,Yang Meng,Yang Chao,et al . Method for Extracting Data During Flight Phase of Ski Jumping Based on Monocular Video[J]. Journal of System Simulation, 2023, 35(9): 2035-2044.

图/表 16

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

各关节角角度 (°)

关节角	角度
$α 0$	39.73
$α 1$	53.62
$α 2$	40.58
$α 3$	22.76
$α 4$	30.86

表1

图11

图12

图13

表2

图14

参考文献 20

1	Andriluka M, Roth S, Schiele B. Pictorial Structures Revisited: People Detection and Articulated Pose Estimation[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2009: 1014-1021.
2	Wang Jingdong, Sun Ke, Cheng Tianheng, et al. Deep High-resolution Representation Learning for Visual Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10): 3349-3364.
3	Xiao Bin, Wu Haiping, Wei Yichen. Simple Baselines for Human Pose Estimation and Tracking[C]//Computer Vision-ECCV 2018. Cham: Springer International Publishing, 2018: 472-487.
4	Cao Zhe, Simon T, Wei S E, et al. Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2017: 1302-1310.
5	Yu Changqian, Xiao Bin, Gao Changxin, et al. Lite-HRNet: A Lightweight High-resolution Network[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2021: 10435-10445.
6	Zhao Tianhao, Li Songnan, Ngan K N, et al. 3-D Reconstruction of Human Body Shape From a Single Commodity Depth Camera[J]. IEEE Transactions on Multimedia, 2019, 21(1): 114-123.
7	Xu Yuanlu, Zhu Songchun, Tung T. DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-compare[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ, USA: IEEE, 2019: 7759-7769.
8	Kocabas M, Athanasiou N, Black M J. VIBE: Video Inference for Human Body Pose and Shape Estimation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2020: 5252-5262.
9	Loper M, Mahmood N, Romero J, et al. SMPL: A Skinned Multi-person Linear Model[J]. ACM Transactions on Graphics, 2015, 34(6): 248.
10	Bogo F, Kanazawa A, Lassner C, et al. Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape From a Single Image[C]//Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 561-578.
11	Pavlakos G, Choutas V, Ghorbani N, et al. Expressive Body Capture: 3D Hands, Face, and Body From a Single Image[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2019: 10967-10977.
12	Santesteban I, Garces E, Otaduy M A, et al. SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans[J]. Computer Graphics Forum, 2020, 39(2): 65-75.
13	李琪, 墨瀚林, 王向东, 等. 短道速滑场景下的多目标跟踪与运动仿真[J]. 系统仿真学报, 2021, 33(5): 1039-1050.
	Li Qi, Mo Hanlin, Wang Xiangdong, et al. Multiple Object Tracking and Kinematic Simulation for Short Track Speed Skating[J]. Journal of System Simulation, 2021, 33(5): 1039-1050.
14	Elfmark O, Ettema G, Groos D, et al. Performance Analysis in Ski Jumping with a Differential Global Navigation Satellite System and Video-based Pose Estimation[J]. Sensors, 2021, 21(16): 5318.
15	伍勰, 曲毅, 刘思平, 等. 跳台滑雪技术生物力学智能分析与反馈系统的研发与应用[J]. 中国体育科技, 2021, 57(12): 3-8.
	Wu Xie, Qu Yi, Liu Siping, et al. An Intelligent Motion Capture and Feedback System Developed for Ski Jumping Technique Analysis[J]. China Sport Science and Technology, 2021, 57(12): 3-8.
16	Bessone V, Petrat J, Schwirtz A. Ground Reaction Forces and Kinematics of Ski Jump Landing Using Wearable Sensors[J]. Sensors, 2019, 19(9): 2011.
17	曹峰锐, 伍勰, 唐伟棣, 等. 跳台滑雪起跳和早期飞行阶段生物力学研究进展[J]. 北京体育大学学报, 2022, 45(1): 35-44.
	Cao Fengrui, Wu Xie, Tang Weidi, et al. A Systematic Review of Research on the Biomechanics of Take-off and Early Flight of Ski Jumping[J]. Journal of Beijing Sport University, 2022, 45(1): 35-44.
18	王蔚, 冯亚琴, 杨再兴, 等. 基于体感交互设备的人体重心计算方法[J]. 数据采集与处理, 2018, 33(4): 595-602.
	Wang Wei, Feng Yaqin, Yang Zaixing, et al. Calculation Method for Human Center of Gravity Based on Somatosensory Interaction[J]. Journal of Data Acquisition and Processing, 2018, 33(4): 595-602.
19	应响. 基于Openpose的姿态匹配研究及其在体育教学中的应用[D]. 南京: 南京师范大学, 2021.
20	Vodičar Janez, Čoh Milan, Jošt Bojan. Kinematic Structure at the Early Flight Position in Ski Jumping[J]. Journal of Human Kinetics, 2012, 35(1): 35-45.

算法	PCKh	mAP
OpenPose	63.24	67.91
本文修正后	78.56	85.08
Lite-HRNet	66.13	70.27
本文修正后	79.52	83.26

[1]	董志明, 胡忠奇, 戴浩然, 高建成. 基于大语言模型的作战仿真想定自动化生成方法[J]. 系统仿真学报, 2026, 38(5): 1129-1145.
[2]	李校男, 晁涛, 马萍, 杨明, 王玉轩. 基于期望最大化方法的非线性SSM黑箱鲁棒辨识[J]. 系统仿真学报, 2026, 38(5): 1146-1158.
[3]	刘银钢, 马明, 张荣华. 基于大语言模型的兵棋推演动态任务规划[J]. 系统仿真学报, 2026, 38(5): 1187-1204.
[4]	苏泓嘉, 张成, 刘飞. 基于模糊功能依赖网分析的体系效能评估方法[J]. 系统仿真学报, 2026, 38(5): 1224-1238.
[5]	梅华威, 杨鹏慧, 余洋. 计及数据漂移改进PatchTST的超短期光伏功率预测[J]. 系统仿真学报, 2026, 38(5): 1239-1254.
[6]	李权, 苏鹏, 万海英, 张承玺, 何志坚, 倪艺洋, 赵忠盖, 刘飞. 基于多阶段LHS-EPRCC方法的青霉素发酵过程建模[J]. 系统仿真学报, 2026, 38(5): 1255-1276.
[7]	周子聪, 曾俊杰, 胡越, 朱正秋, 尹全军. 基于次优示例引导的兵棋推演多智能体强化学习方法[J]. 系统仿真学报, 2026, 38(5): 1277-1289.
[8]	石敏, 郭诗盛, 王素琴, 李兆歆, 朱登明. 融合物理与几何先验的无抓取标注6-DoF抓取检测方法[J]. 系统仿真学报, 2026, 38(5): 1290-1302.
[9]	姜彦吉, 肖星佚, 董浩, 于淼, 黄金山, 刘大千, 费博雯. 融合点线特征的图关系优化3D车道线检测方法[J]. 系统仿真学报, 2026, 38(5): 1303-1319.
[10]	张鑫, 张平, 张琛, 刘威, 韩博阳. 非均质土壤条件下挖掘阻力计算模型研究[J]. 系统仿真学报, 2026, 38(5): 1320-1332.
[11]	王伟, 刘东, 崔新豪, 李博, 肖依永, 任羿. 复杂项目多级动态挣值管理数字化模型及应用[J]. 系统仿真学报, 2026, 38(5): 1350-1364.
[12]	彭莉峻, 苏庭琪, 刘沛津, 何林, 周协武, 张闽心. 融合人体关键点的实验室PPE规范穿戴检测方法[J]. 系统仿真学报, 2026, 38(5): 1365-1382.
[13]	滕靖, 童文聪, 张中杰, 姚幸, 李君羡. 有轨电车交叉口速度自动引导方法及仿真评价[J]. 系统仿真学报, 2026, 38(5): 1426-1439.
[14]	蒋圣超, 裴云庆, 翟宏营, 吴国键, 高放. 基于块编码绝热量子牛顿‒拉夫逊法的潮流计算[J]. 系统仿真学报, 2026, 38(5): 1453-1465.
[15]	秦浪, 谢嘉成, 乔晓军, 王学文, 肖智杰. 执行器位姿异常的机器人轨迹规划调整方法[J]. 系统仿真学报, 2026, 38(5): 1466-1483.

基于单目视频的跳台滑雪飞行阶段数据提取方法

Method for Extracting Data During Flight Phase of Ski Jumping Based on Monocular Video

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价