Video-based evaluation of infant crawling toward quantitative assessment of motor development

Abstract

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 interframe 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.

Measurement and Analysis of Human Infant Crawling for Rehabilitation: A Narrative Review

“…This technique has been studied extensively in the field of gait analysis ( 38 , 39 ), but the application of this technology in the field of crawling motion detection is sparse. Recently, Kawashima et al verified the possibility of using computer vision–based technology to distinguish different crawling postures from video images for the first time ( 19 ). The features of infant crawling were extracted from the recorded video images based on image processing, and then evaluation indices based on video images are calculated for the movement feature extraction and analysis, as shown in Figure 5 .…”

“…Thus, quantifying muscle contraction and kinematics during crawling appear to be more likely to uncover the abnormal muscle control strategy that related to the changes/impairments of the CNS (18). With the advancements of wearable sensors and motion capture techniques in recent years, increasing research work has been carried out on the measurement and analysis of infant crawling (19)(20)(21). However, to the best of the authors' knowledge, there is still a lack of review work that can provide an overview of the measurement and analysis of infant crawling.…”

Markerless Video Analysis of Spontaneous Bodily Movements in 4-Month-Old Infants Predicts Autism-like Behavior in 18-Month-Olds

“…The primary goal of the present study was to examine whether bodily movement patterns during early infancy are predictive of the ASD risk, which becomes evident later in the development in a prospective design. To achieve this goal, we video-recorded spontaneous bodily movements in 4-month-old infants and quantified their features using a novel markerless system for infant movement evaluation (Osawa et al, 2009; Tsuji et al, 2020; Kinoshita et al, 2020; Kawashima et al, 2020; Tacchino et al, 2021). Classifiers were trained for predicting the ASD risk in 18-month-old infants, based on their bodily movement patterns at 4 months of age.…”