Active segmentation for robotics

TitleActive segmentation for robotics
Publication TypeConference Papers
Year of Publication2009
AuthorsMishra A, Aloimonos Y, Fermüller C
Conference NameIEEE/RSJ International Conference on Intelligent Robots and Systems, 2009. IROS 2009
Date Published2009/10/10/15
ISBN Number978-1-4244-3803-7
Keywordsbinocular cues, image colour analysis, Image segmentation, Image texture, Intelligent robots, Layout, Machine vision, monocular cues, Navigation, optical flow, Orbital robotics, Robot sensing systems, robot vision, Robot vision systems, robotics active segmentation, Robotics and automation, semantic robot, Simultaneous localization and mapping, stereo disparity, stereo image processing

The semantic robots of the immediate future are robots that will be able to find and recognize objects in any environment. They need the capability of segmenting objects in their visual field. In this paper, we propose a novel approach to segmentation based on the operation of fixation by an active observer. Our approach is different from current approaches: while existing works attempt to segment the whole scene at once into many areas, we segment only one image region, specifically the one containing the fixation point. Furthermore, our solution integrates monocular cues (color, texture) with binocular cues (stereo disparities and optical flow). Experiments with real imagery collected by our active robot and from the known databases demonstrate the promise of the approach.