Graduate School of Engineering, Hiroshima University, 1-4-1 Kagamiyama, Higashi-Hiroshima, Hiroshima, 739-8527, Japan.
Graduate School of Human and Environmental Studies, Kyoto University, Yoshida-Nihonmatsu-Cho, Sakyo-Ku, Kyoto, 606-8507, Japan.
Sci Rep. 2020 Jul 9;10(1):11266. doi: 10.1038/s41598-020-67855-0.
This study proposes a quantitative evaluation support system for infant motor development and uses the system to analyze hands-and-knees creeping and belly crawling. This system measures movements using two video cameras and extracts movement features via background and inter-frame subtractions of original images. Eight evaluation indices for each crawling cycle are calculated, enabling markerless movement analysis of infants. Cross-sectional analysis of 16 10-month-olds confirmed significant differences between hands-and-knees creeping and belly crawling in five of the eight indices, demonstrating the system capability to quantitatively differentiate between creeping and crawling. Longitudinal analysis of one infant (aged 7-10 months) also suggested that the proposed quantitative indices can follow changes in crawling characteristics and evaluate infants' motor development process. The results from the experiments suggest that the proposed system may enable diagnosis support in clinical practice.
本研究提出了一种用于婴儿运动发育的定量评估支持系统，并使用该系统对双手双膝爬行和腹部爬行进行分析。该系统使用两个摄像机测量运动，并通过原始图像的背景和帧间相减来提取运动特征。每个爬行周期计算 8 个评估指标，实现了对婴儿无标记运动的分析。对 16 名 10 个月大婴儿的横断面分析证实，在 8 个指标中有 5 个指标在双手双膝爬行和腹部爬行之间存在显著差异，表明该系统能够定量区分爬行和爬行。对一名婴儿（7-10 个月大）的纵向分析也表明，所提出的定量指标可以跟踪爬行特征的变化，并评估婴儿的运动发育过程。实验结果表明，该系统可用于临床实践中的诊断支持。
