A Portable Active Binocular Robot Vision Architecture for Scene Exploration

We present a portable active binocular robot vision architecture that integrates a number of visual behaviours. This vision architecture inherits the abilities of vergence, localisation, recognition and simultaneous identification of multiple target object instances. To demonstrate the portability of our vision architecture, we carry out qualitative and comparative analysis under two different hardware robotic settings, feature extraction techniques and viewpoints. Our portable active binocular robot vision architecture achieved average recognition rates of 93.5 % for fronto-parallel viewpoints and, 83 % percentage for anthropomorphic viewpoints, respectively.

[1]  James J. Little,et al.  Viewpoint detection models for sequential embodied object category recognition , 2010, 2010 IEEE International Conference on Robotics and Automation.

[2]  Michael A. Arbib,et al.  Neurorobotics: From Vision to Action , 2008, Springer Handbook of Robotics.

[3]  J. Paul Siebert,et al.  Towards a unified visual framework in a binocular active robot vision system , 2010, Robotics Auton. Syst..

[4]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[5]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[6]  Wilsaan M. Joiner,et al.  Neuronal mechanisms for visual stability: progress and problems , 2011, Philosophical Transactions of the Royal Society B: Biological Sciences.

[7]  Shengyong Chen,et al.  Active vision in robotic systems: A survey of recent developments , 2011, Int. J. Robotics Res..

[8]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[9]  Robin R. Murphy,et al.  Lessons learned in integrating sensing into autonomous mobile robot architectures , 1997, J. Exp. Theor. Artif. Intell..

[10]  J. Paul Siebert,et al.  Unsupervised clustering in Hough space for recognition of multiple instances of the same object in a cluttered scene , 2010, Pattern Recognit. Lett..

[11]  Pittsburgh,et al.  The MOPED framework: Object recognition and pose estimation for manipulation , 2011 .

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

[13]  Joel W. Burdick,et al.  A probabilistic framework for object search with 6-DOF pose estimation , 2011, Int. J. Robotics Res..

[14]  Patric Jensfelt,et al.  Exploiting and modeling local 3D structure for predicting object locations , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[16]  Jan Paul Siebert,et al.  A Hierarchy of Visual Behaviours in an Active Binocular Robot Head , 2009 .

[17]  David Whitney,et al.  Saccadic remapping of object-selective information , 2014, Attention, perception & psychophysics.

[18]  Li Sun,et al.  Accurate garment surface analysis using an active stereo robot head with application to dual-arm flattening , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Siddhartha S. Srinivasa,et al.  Object search by manipulation , 2014, Auton. Robots.

[20]  Adrien Bartoli,et al.  KAZE Features , 2012, ECCV.

[21]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..