Active 3D scene segmentation and detection of unknown objects

We present an active vision system for segmentation of visual scenes based on integration of several cues. The system serves as a visual front end for generation of object hypotheses for new, previously unseen objects in natural scenes. The system combines a set of foveal and peripheral cameras where, through a stereo based fixation process, object hypotheses are generated. In addition to considering the segmentation process in 3D, the main contribution of the paper is integration of different cues in a temporal framework and improvement of initial hypotheses over time.

[1]  R. B. Potts.  Some generalized order-disorder transformations , 1952, Mathematical Proceedings of the Cambridge Philosophical Society.

[2]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[3]  Donald Geman,et al.  Boundary Detection by Constrained Optimization , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Yair Weiss,et al.  Correctness of Local Probability Propagation in Graphical Models with Loops , 2000, Neural Computation.

[6]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  David Melcher,et al.  Persistence of visual memory for scenes , 2001, Nature.

[8]  Radim Sára.  Finding the Largest Unambiguous Component of Stereo Matching , 2002, ECCV.

[9]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[10]  Danica Kragic,et al.  Vision for robotic object manipulation in domestic settings , 2005, Robotics Auton. Syst..

[11]  T. Asfour,et al.  ARMAR-III : A HUMANOID PLATFORM FOR PERCEPTION-ACTION INTEGRATION , 2006 .

[12]  Gordon Cheng,et al.  Making Object Learning and Recognition an Active Process , 2008, Int. J. Humanoid Robotics.

[13]  Danica Kragic,et al.  Integration of Visual and Shape Attributes for Object Action Complexes , 2008, ICVS.

[14]  Danica Kragic,et al.  An Active Vision System for Detecting, Fixating and Manipulating Objects in the Real World , 2010, Int. J. Robotics Res..