利用无标记动作捕捉技术对立定跳远测量的研究

Research on Measurement of Standing Long Jump with Unmarked Motion Capture Technology

目的:旨在探究无标记动作捕捉技术在立定跳远距离测量中的应用。方法:采用RGB-D深度相机进行动作捕捉,运用关键帧提取、图像分割和边缘检测等图像处理技术,结合机器学习算法,实现无标记精准测量立定跳远距离,并通过信效度分析检证其精准性和可靠性。结果:通过51个标准距离重复测量,重测信度检验得到克隆巴赫系数α=0.999和组内相关系数ICC=0.998,重测精准性达到99.64%;通过306次立定跳远试跳实测,标准效度检验的Pearson相关系数r=0.999,稳定可靠性达到99.69%。结论:本研究成功开发并验证了一种基于无标记动作捕捉技术的立定跳远距离测量方法,极高的精准性和可靠性展示了该方法的创新性和实用价值。

This study aimed to explore the application of unmarked motion capture technology in the measurement of standing long jump.RGB-D depth camera was used for motion capture,and image processing techniques such as key frame extraction,image segmentation,and edge detection were used in combination with machine learning algorithms to achieve the accurate measurement of standing long jump distance in an unmarked way.The accuracy and reliability are verified through reliability and validity analysis.Through repeated measurements of 51 standard distances,the Cronbach's alpha coefficient“α”was 0.999 for the test-retest reliability and the intra-class correlation coefficient(ICC)was 0.998,and the accuracy of the retest reached 99.64%.Through 306 actual measurements of standing long jump trials,the Pearson correlation coefficient“r”was 0.999 obtained for criterion-related validity,and the stability and reliability reached 99.69%.It could be seen that this study successfully developed and validated an unmarked motion capture technologybased method for measuring standing long jump distance,which demonstrated its innovative and practical value with high accuracy and reliability.