넓은 실내 공간에서 수평 선분을 이용한 비전 기반의 지도 작성 및 위치 인식
안수용, 강정관, 이래경 et al. · 제어로봇시스템학회 국내학술대회 논문집 · 2009
This paper presents a simultaneous localization and mapping (SLAM) of a large indoor environment using Rao-Blackwellized particle filter (RBPF) along with a line segment as a landmark. A horizontal line segment is extracted from an edge image using Hough transform and is also tracked by an optical flow method. Successive observation of a line segment gives initial state of the line in 3D space. For data association, registered feature and observed feature are matched through a degree of overlap, orientation of line, and distance between two lines. Experiments show that a compact environmental map is constructed using small number of horizontal line features in real-time.
Cited by 0 works.