ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Automatic Recognition of Children Engagement from Facial Video using Convolutional Neural Networks
Cited 29 time in scopus Download 26 time Share share facebook twitter linkedin kakaostory
저자
윤우한, 이동진, 박찬규, 김재홍, 김준모
발행일
202010
출처
IEEE Transactions on Affective Computing, v.11 no.4, pp.696-707
ISSN
1949-3045
출판사
IEEE
DOI
https://dx.doi.org/10.1109/TAFFC.2018.2834350
협약과제
15MC2100, 잠재 역량 진단을 위한 감정특이점 기반 맞춤형 인지센싱 및 플랫폼 기술개발, 윤호섭
초록
Automatic engagement recognition is a technique that is used to measure the engagement level of people in a specific task. Although previous research has utilized expensive and intrusive devices such as physiological sensors and pressure-sensing chairs, methods using RGB video cameras have become the most common because of the cost efficiency and noninvasiveness of video cameras. Automatic engagement recognition methods using video cameras are usually based on hand-crafted features and a statistical temporal dynamics modeling algorithm. This paper proposes a data-driven convolutional neural networks (CNNs)-based engagement recognition method that uses only facial images from input videos. As the amount of data in a dataset of children's engagement is insufficient for deep learning, pre-trained CNNs are utilized for low-level feature extraction from each video frame. In particular, a new layer combination for temporal dynamics modeling is employed to extract high-level features from low-level features. Experimental results on a database created using images of children from kindergarten demonstrate that the performance of the proposed method is superior to that of previous methods. The results indicate that the engagement level of children can be gauged automatically via deep learning even when the available database is deficient.
KSP 제안 키워드
Automatic recognition, Convolution neural network(CNN), Cost Efficiency, Data-Driven, Dynamics modeling, Facial image, Facial video, High-level features, Layer combination, Recognition method, Temporal Dynamics