Real-time estimation of human visual attention with MCMC-based particle filter

This report proposes a new method for achieving a precise estimation of human visual attention with considerably less execution time. The main contribution of this report is the incorporation of a particle filter with Markov chain Monte-Carlo (MCMC) sampling into a previously proposed stochastic model of saliency-based human visual attention. This enables us to introduce stream processing with such as graphics processing units (GPU) for the acceleration of the estmation. Experimental results indicate that the proposed method can estimate human visual attention more than 10 times faster and more precisely than previous methods.

[1]  Heinz Hügli,et al.  Robot self-localization using visual attention , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

[2]  Kazuhiro Otsuka,et al.  Real-time Visual Tracker by Stream Processing , 2009, J. Signal Process. Syst..

[3]  Shan Li,et al.  An Efficient Spatiotemporal Attention Model and Its Application to Shot Matching , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  A. Kingstone,et al.  Topic: Cognition , 2003 .

[5]  Pierre Baldi,et al.  A principled approach to detecting surprising events in video , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Bo Han,et al.  High Speed Visual Saliency Computation on GPU , 2007, 2007 IEEE International Conference on Image Processing.

[7]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[8]  Nuno Vasconcelos,et al.  Decision-Theoretic Saliency: Computational Principles, Biological Plausibility, and Implications for Neurophysiology and Psychophysics , 2009, Neural Computation.

[9]  Kimura Akisato,et al.  Saliency-based video segmentation with graph cuts and sequentially updated priors , 2009 .

[10]  Tingting Xu,et al.  Looking at the surprise: Bottom-up attentional control of an active camera system , 2008, 2008 10th International Conference on Control, Automation, Robotics and Vision.

[11]  Christian P. Robert,et al.  Monte Carlo Statistical Methods (Springer Texts in Statistics) , 2005 .

[12]  Kunio Kashino,et al.  A Computational Model of Saliency Depletion/Recovery Phenomena for the Salient Region Extraction of Videos , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[13]  Laurent Itti,et al.  Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Minho Lee,et al.  Stereo saliency map considering affective factors and selective motion analysis in a dynamic environment , 2008, Neural Networks.

[15]  William J. Dally,et al.  Programmable Stream Processors , 2003, Computer.

[16]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[17]  Joachim Hertzberg,et al.  Saliency-based object recognition in 3D data , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[18]  J. P. Thomas,et al.  A signal detection model predicts the effects of set size on visual search accuracy for feature, conjunction, triple conjunction, and disjunction displays , 2000, Perception & psychophysics.

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

[20]  Kunio Kashino,et al.  A stochastic model of selective visual attention with a dynamic Bayesian network , 2008, 2008 IEEE International Conference on Multimedia and Expo.

[21]  Branko Ristic,et al.  Beyond the Kalman Filter: Particle Filters for Tracking Applications , 2004 .