Making Object Learning and Recognition an Active Process

The exploration and learning of new objects is an essential capability of a cognitive robot. In this paper we focus on making use of the robot's manipulation abilities to learn complete object representations suitable for 3D object recognition. Taking control of the object allows the robot to focus on relevant parts of the images, thus bypassing potential pitfalls of purely bottom-up attention and segmentation. The main contribution of the paper consists in integrated visuomotor processes that allow the robot to learn object representations by manipulation without having any prior knowledge about the objects. Our experimental results show that the acquired data is of sufficient quality to train a classifier that can recognize 3D objects independently of the viewpoint.

[1]  Jan-Olof Eklundh,et al.  Statistical background subtraction for a mobile observer , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[2]  Paul M. Fitzpatrick,et al.  First contact: an active vision approach to segmentation , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[3]  Koby Crammer,et al.  On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines , 2002, J. Mach. Learn. Res..

[4]  Pradeep K. Khosla,et al.  Strategies for Increasing the Tracking Region of an Eye-in-Hand System by Singularity and Joint Limit Avoidance , 1995, Int. J. Robotics Res..

[5]  Tsuneo Yoshikawa.  Basic optimization methods of redundant manipulators , 1996 .

[6]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[7]  Éric Marchand,et al.  Using the task function approach to avoid robot joint limits and kinematic singularities in visual servoing , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[8]  Giorgio Metta,et al.  Grounding vision through experimental manipulation , 2003, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[9]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  KrügerNorbert,et al.  Face Recognition by Elastic Bunch Graph Matching , 1997 .

[11]  Bernt Schiele,et al.  Recognition without Correspondence using Multidimensional Receptive Field Histograms , 2004, International Journal of Computer Vision.

[12]  B. M. Fulk.  MATH , 1992 .

[13]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[14]  David G. Lowe,et al.  Local feature view clustering for 3D object recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[15]  Gordon Cheng,et al.  Combining peripheral and foveal humanoid vision to detect, pursue, recognize and act , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[16]  Shaogang Gong,et al.  Tracking colour objects using adaptive mixture models , 1999, Image Vis. Comput..

[17]  Peter I. Corke,et al.  A tutorial on visual servo control , 1996, IEEE Trans. Robotics Autom..

[18]  Christian Wallraven,et al.  Learning from humans: Computational modeling of face recognition , 2004, Network.

[19]  Zhuowen Tu,et al.  Image Parsing: Unifying Segmentation, Detection, and Recognition , 2005, International Journal of Computer Vision.

[20]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

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