ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Eyeball tracking and Object Detection in Smart Glasses
Cited 0 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
김광용, 송기봉
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1799-1801
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289447
협약과제
20HB1500, 포스트 스마트폰 시대를 대비한 Trusted Reality 핵심기술 개발, 송기봉
초록
We have implemented a system that uses a micro camera to detect the central position of eyeball through smart glasses, tracks the area and position of the object seen from the smart glasses, and recognizes the object. Here, we use the MobileNet single shot detector and convolutional neural network model provided by the OpenCV library to detect the region and center position of the observed object. In the future, we will implement a smart communication system based on viewing communication that includes not only the information seen through smart glasses, but also traditional information exchange functions such as telephone, text message, and e-mail. Finally, what we aim for is to expect a new era of communication that allows users to communicate easily and conveniently with the observed object through the eye and intuitively with the observed object while the user is free to use their hands.
키워드
Eyeball tracking, Object detection, Smart glass
KSP 제안 키워드
Communication system, Convolution neural network(CNN), E-Mail, Information Exchange, Object detection, OpenCV library, Single-shot, Smart communication, Text message, neural network model, smart glasses