ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 Hierarchical Pose Classification for Infant Action Analysis and Mental Development Assessment
Cited 0 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
Jianxiong Zhou, Zhongyu Jiang, 유장희, Jenq-Neng Hwang
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021, pp.1340-1344
21HS1200, 영유아/아동의 발달장애 조기선별을 위한 행동·반응 심리인지 AI 기술 개발, 유장희
Based on Alberta Infant Motor Scale (AIMS), a questionnaire that tracks an infant's motor function, an infant's mental development can be evaluated by recording poses a baby can achieve. Therefore, it is meaningful to propose a systematic image-based pose classifier to classify infant actions based on AIMS to provide early diagnosis of a potential developmental disorder such as Autism. This paper presents a hierarchical pose classifier, given a baby image frame that combines the benefits of 3D human pose estimation and scene context information. Due to privacy policies, we cannot collect enough real infant images/videos for experiments. Instead, we generate synthetic baby images with the help of the Skinned Multi-Infant Linear (SMIL) model. Images are first fed into a ResNet-50 for coarse-level pose classification. A stacked hourglass CNN and a hierarchical 3D pose estimation scheme are used for 2D/3D pose estimation. Finally, an innovative Hierarchical Infant Pose Classifier (HIPC) takes the estimated 3D keypoints and coarse-level pose classification confidence scores to give the fine-level baby pose classification results. Our experimental results show that our hierarchical pose classifier achieves accurate and stable performance on infant pose recognition.
Deep Learning, Hierarchical Classification, HIPC, Human Pose Estimation, ResNet
KSP 제안 키워드
3D human pose estimation, 3D pose estimation, Action Analysis, Context Information, Developmental disorder, Early diagnosis, Image-based, Mental development, Motor function, Motor scale, Pose classification