Object recognition on humanoids with poveated vision

Object recognition requires a robot to perform a number of nontrivial tasks such as finding objects of interest, directing its eyes towards the objects, pursuing them, and identifying the objects once they appear in the robot¿s central vision. In this paper we describe a system that make use of foveated vision to solve the problem of object recognition on a humanoid robot. The system employs a biologically motivated object representation scheme based on Gabor kernel functions to represent multiple views of objects. We demonstrate how to utilize support vector machines to identify known objects in foveal images using this representation. A mechanism for visual search is integrated into the system to find a salient region and to place an object of interest in the field of view of foveal cameras. The framework also includes a control scheme for eye movements, which are directed using the results of attentive processing in peripheral images.

[1]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[2]  Norbert Krüger,et al.  Face recognition by elastic bunch graph matching , 1997, Proceedings of International Conference on Image Processing.

[3]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[4]  J. Wolfe.  Moving towards solutions to some enduring controversies in visual search , 2003, Trends in Cognitive Sciences.

[5]  Stefan Schaal,et al.  Biomimetic Oculomotor Control , 2001, Adapt. Behav..

[6]  P. Verghese.  Visual Search and Attention A Signal Detection Theory Approach , 2001, Neuron.

[7]  Todd S. Horowitz,et al.  Visual search has no memory , 1998, Nature.

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

[9]  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).

[10]  G. Sandini,et al.  Babybot : an artificial developing robotic agent , 2000 .

[11]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Ales Ude,et al.  Probabilistic detection and tracking at high frame rates using affine warping , 2002, Object recognition supported by user interaction for service robots.

[13]  Gordon Cheng,et al.  Online learning of a motor map for humanoid robot reaching , 2003 .

[14]  Brian Scassellati,et al.  Eye Finding via Face Detection for a Foveated Active Vision System , 1998, AAAI/IAAI.

[15]  Heinrich H. Bülthoff,et al.  View-based dynamic object recognition based on human perception , 2002, Object recognition supported by user interaction for service robots.

[16]  Gordon Cheng,et al.  Continuous humanoid interaction: : An integrated perspective - gaining adaptivity, redundancy, flexibility - in one , 2001, Robotics Auton. Syst..

[17]  Brian Scassellati,et al.  Active vision for sociable robots , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[18]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[19]  Heinrich H. Bülthoff,et al.  Image-based object recognition , 1995 .

[20]  Heinrich H Bülthoff,et al.  Image-based object recognition in man, monkey and machine , 1998, Cognition.

[21]  Ales Ude,et al.  Online tracking and mimicking of human movements by a humanoid robot , 2003, Adv. Robotics.

[22]  H. Kozima,et al.  A Robot that Learns to Communicate with Human Caregivers , 2001 .

[23]  Joshua G. Hale,et al.  Using Humanoid Robots to Study Human Behavior , 2000, IEEE Intell. Syst..