Modes of Attention and Inattention for a Model of Robot Perception

This paper considers and compares several aspects of attention and awareness in the context of uniform field image (robotic) vision sensors and foveal (human) natural perception. It builds on a theory of abductive perception using feature clouds, a formal definition for a robot perceptual system, and proposes a unified model for bottomup and top-down attention. It highlights some shortcomings in existing bottom-up models and presents a uniform solution to them. Modes of attentional lapse, commonly referred to as inattentional blindness and change blindness, are also discussed in the context of the model presented.

[1]  Mark Witkowski,et al.  Abductive Visual Perception with Feature Clouds , 2006, KR.

[2]  D. Simons,et al.  Change Blindness in the Absence of a Visual Disruption , 2000, Perception.

[3]  L. Stark,et al.  Experimental metaphysics: The scanpath as an epistemological mechanism , 1996 .

[4]  D. Simons,et al.  Failure to detect changes to people during a real-world interaction , 1998 .

[5]  D. Simons,et al.  Failure to detect changes to attended objects in motion pictures , 1997 .

[6]  Laurent Itti,et al.  A Goal Oriented Attention Guidance Model , 2002, Biologically Motivated Computer Vision.

[7]  Andrew J. Davison,et al.  Real-time simultaneous localisation and mapping with a single camera , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[8]  Salvatore Gaglio,et al.  Understanding dynamic scenes , 2000, Artif. Intell..

[9]  Refractor.  Vision , 2000, The Lancet.

[10]  C. Chabris,et al.  Gorillas in Our Midst: Sustained Inattentional Blindness for Dynamic Events , 1999, Perception.

[11]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Brian J. Scholl,et al.  PSYCHE an interdisciplinary journal of research on consciousness Sustained Inattentional Blindness : The Role of Location in the Detection of Unexpected Dynamic Events , 2000 .

[13]  M. Posner,et al.  The attention system of the human brain. , 1990, Annual review of neuroscience.

[14]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[15]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[16]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[17]  Murray Shanahan,et al.  A Logic-Based Formulation of Active Visual Perception , 2004, KR.

[18]  Brian Scassellati,et al.  IEEE Intelligent Systems , 2018, Computer.

[19]  Yiannis Demiris,et al.  Compound Effects of Top-down and Bottom-up Influences on Visual Attention During Action Recognition , 2005, IJCAI.

[20]  Hugo Vieira Neto,et al.  Automated Exploration and Inspection: Comparing Two Visual Novelty Detectors , 2005 .

[21]  Jaakko Hintikka,et al.  On the Logic of Perception , 1969 .

[22]  Ronald A. Rensink,et al.  Change blindness: past, present, and future , 2005, Trends in Cognitive Sciences.

[23]  J. Wolfe.  Visual search in continuous, naturalistic stimuli , 1994, Vision Research.

[24]  G. Brelstaff,et al.  Is the Richness of Our Visual World an Illusion? Transsaccadic Memory for Complex Scenes , 1995, Perception.

[25]  Larry S. Davis,et al.  Model-based object pose in 25 lines of code , 1992, International Journal of Computer Vision.