http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
전진우(Jin-woo Jeon),우운택(Woontack Woo) 한국HCI학회 2017 한국HCI학회 학술대회 Vol.2017 No.2
본 논문은 AR 환경에서 이용 가능한 실내 공간내에서 공간과 평면을 분리하여 인식하는 평면 추정방법을 제안한다. 깊이 영상 카메라로부터 지역 법선벡터를 계산한 후 방위, 고도, 거리 정보를 이용하여 비슷한 법선 벡터끼리 군집화한 후 평면을 추정한다. 그 후 평면 영역들로부터 객체 영역을 분리한다. 이 정보를 이용하여 3 차원 공간에서 공간 영역과 물체영역을 분리하여 증강 현실 분야에서 독립적인 응용이 가능하다.
Socially aware tv program recommender for multiple viewers
Choonsung Shin,Woontack Woo IEEE 2009 IEEE transactions on consumer electronics Vol.55 No.2
<P>With the increasing amount of research on smart TVs, users are interacting with them in an evermore convenient way. However, current program recommendations mainly focus on using individual profiles and require users' active participation when multiple viewers coexist. In this paper, we propose a socially aware program recommender for multiple viewers of a digital TV that rates and selects TV programs based on individual and group preferences. For this task, the proposed recommender generates recommendations for users by merging user profiles and combining their common interests. In this way, programs that all users prefer are automatically selected and ambiguous or conflicting programs are mediated based on user feedback. Through subsequent experiments with a smart TV equipped with the program recommender, we found that the performance of group recommendations improved when individual profiles and the group's common interests were used, and that users preferred different strategies when they were with other people.</P>
Silhouette Segmentation in Multiple Views
Wonwoo Lee,Woontack Woo,Boyer, E IEEE 2011 IEEE transactions on pattern analysis and machine Vol.33 No.7
<P>In this paper, we present a method for extracting consistent foreground regions when multiple views of a scene are available. We propose a framework that automatically identifies such regions in images under the assumption that, in each image, background and foreground regions present different color properties. To achieve this task, monocular color information is not sufficient and we exploit the spatial consistency constraint that several image projections of the same space region must satisfy. Combining the monocular color consistency constraint with multiview spatial constraints allows us to automatically and simultaneously segment the foreground and background regions in multiview images. In contrast to standard background subtraction methods, the proposed approach does not require a priori knowledge of the background nor user interaction. Experimental results under realistic scenarios demonstrate the effectiveness of the method for multiple camera set ups.</P>