Learning and recognition of objects inspired by early cognition

In this paper, we present a unifying approach for learning and recognition of objects in unstructured environments through exploration. Taking inspiration from how young infants learn objects, we establish four principles for object learning. First, early object detection is based on an attention mechanism detecting salient parts in the scene. Second, motion of the object allows more accurate object localization. Next, acquiring multiple observations of the object through manipulation allows a more robust representation of the object. And last, object recognition benefits from a multi-modal representation. Using these principles, we developed a unifying method including visual attention, smooth pursuit of the object, and a multi-view and multi-modal object representation. Our results indicate the effectiveness of this approach and the improvement of the system when multiple observations are acquired from active object manipulation.

[1]  J. Piaget.  The Grasp of Consciousness: Action and Concept in the Young Child , 1976 .

[2]  E. Spelke,et al.  Perception of objects and object boundaries by 3‐month‐old infants , 1987 .

[3]  A. Baddeley,et al.  Working memory and executive control. , 1996, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[4]  Thomas S. Huang,et al.  Content-based image retrieval with relevance feedback in MARS , 1997, Proceedings of International Conference on Image Processing.

[5]  James W. Davis,et al.  The Recognition of Human Movement Using Temporal Templates , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  David M. J. Tax,et al.  One-class classification , 2001 .

[7]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[10]  John,et al.  FOUR The development of visual attention and the brain , 2005 .

[11]  Heiko Wersing,et al.  Peripersonal space and object recognition for humanoids , 2005, 5th IEEE-RAS International Conference on Humanoid Robots, 2005..

[12]  Lucas Paletta,et al.  Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint , 2008, Lecture Notes in Computer Science.

[13]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  E. Knudsen.  Fundamental components of attention. , 2007, Annual review of neuroscience.

[15]  Gert Kootstra,et al.  Active exploration and keypoint clustering for object recognition , 2008, 2008 IEEE International Conference on Robotics and Automation.

[16]  G. Lupyan,et al.  Developing object concepts in infancy: an associative learning perspective. , 2008, Monographs of the Society for Research in Child Development.

[17]  John K. Tsotsos,et al.  Attention in Cognitive Systems, 5th International Workshop on Attention in Cognitive Systems, WAPCV 2008, Fira, Santorini, Greece, May 12, 2008, Revised Selected Papers , 2009, WAPCV.

[18]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[19]  David Zhang,et al.  Robust Object Tracking Using Joint Color-Texture Histogram , 2009, Int. J. Pattern Recognit. Artif. Intell..

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

[21]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Gert Kootstra,et al.  Using Symmetry to Select Fixation Points for Segmentation , 2010, 2010 20th International Conference on Pattern Recognition.

[23]  James J. Little,et al.  Curious George: An Integrated Visual Search Platform , 2010, 2010 Canadian Conference on Computer and Robot Vision.

[24]  Danica Kragic,et al.  Active 3D scene segmentation and detection of unknown objects , 2010, 2010 IEEE International Conference on Robotics and Automation.

[25]  Pieter P. Jonker,et al.  Saliency Detection and Object Localization in Indoor Environments , 2010, 2010 20th International Conference on Pattern Recognition.

[26]  Pieter P. Jonker,et al.  A fast and robust descriptor for multiple-view object recognition , 2010, 2010 11th International Conference on Control Automation Robotics & Vision.

[27]  Norbert Krüger,et al.  Temporal accumulation of oriented visual features , 2011, J. Vis. Commun. Image Represent..

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

[29]  David Vernon,et al.  A Roadmap for Cognitive Development in Humanoid Robots , 2011, Cognitive Systems Monographs.