뇌성마비 환자의 자세 불균형 탐지를 위한 스마트폰 동영상 기반 보행 분석 시스템 = Smartphone-based Gait Analysis System for the Detection of Postural Imbalance in Patients with Cerebral Palsy

다국어 초록 (Multilingual Abstract)

Gait analysis is an important tool in the clinical management of cerebral palsy, allowing for the assessment of condition severity, identification of potential gait abnormalities, planning and evaluation of interventions, and providing a baseline for future comparisons. However, traditional methods of gait analysis are costly and time-consuming, leading to a need for a more convenient and continuous method. This paper proposes a method for analyzing the posture of cerebral palsy patients using only smartphone videos and deep learning models, including a ResNet-based image tilt correction, AlphaPose for human pose estimation, and SmoothNet for temporal smoothing. The indicators employed in medical practice, such as the imbalance angles of shoulder and pelvis and the joint angles of spine-thighs, knees and ankles, were precisely examined. The proposed system surpassed pose estimation alone, reducing the mean absolute error for imbalance angles in frontal videos from 4.196° to 2.971° and for joint angles in sagittal videos from 5.889° to 5.442°.

참고문헌 (Reference)

1 이길재 ; 이태수, "의료영상 분석에서 인공지능 이용 동향" 한국방사선학회 16 (16): 453-462, 2022

2 홍은빈 ; 전준호 ; 조성현 ; 이승용, "딥러닝을 이용한 영상 수평 보정" (사)한국컴퓨터그래픽스학회 23 (23): 95-103, 2017

3 황수진 ; 하승희, "뇌성마비 아동의 재활치료에 있어서 부모 참여에 대한 고찰" 한국장애인재활협회 부설 재활연구소 17 (17): 309-328, 2013

4 S. Jin, "Whole-body Human Pose Estimation in the Wild" 196-214, 2020

5 G. Tolias, "Speeded-up, Relaxed Spatial Matching" 1653-1660, 2011

6 A. Zeng, "Smoothnet: a Plug-and-play Network for Refining Human Poses in Videos" 625-642, 2022

7 Z. Cao, "Realtime Multi-person 2d Pose Estimation Using Part Affinity Fields" 7291-7299, 2017

8 J. H. Shin, "Quantitative Gait Analysis Using a Pose-estimation Algorithm with a Single 2D-video of Parkinson’s Disease Patients" 11 (11): 1271-1283, 2021

9 Y. Chen, "Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods" 192 (192): 2020

10 T. Y. Lin, "Microsoft coco:Common Objects in Context" 740-755, 2014

11 D. Qiao, "Measuring Heart Rate and Heart Rate Variability with Smartphone Camera" 248-249, 2021

12 C. Ionescu, "Human3.6m: Large Scale Datasets and Predictive Methods for 3d Human Sensing in Natural Environments" 36 (36): 1325-1339, 2013

13 J. Li, "Human Pose Regression with Residual Log-likelihood Estimation" 11025-11034, 2021

14 A. Mirelman, "Gait impairments in Parkinson's Disease" 18 (18): 697-708, 2019

15 K. Sun, "Deep High-resolution Representation Learning for Human Pose Estimation" 5693-5703, 2019

16 H. S. Fang, "AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time" 2022

17 M. Andriluka, "2d Human Pose Estimation: New Benchmark and State of the Art Analysis" 3686-3693, 2014