Selecting What Is Important: Training Visual Attention

We present a new, sophisticated algorithm to select suitable training images for our biologically motivated attention system VOCUS. The system detects regions of interest depending on bottom-up (scene-dependent) and top-down (target-specific) cues. The top-down cues are learned by VOCUS from one or several training images. We show that our algorithm chooses a subset of the training set that outperforms both the selection of one single image as well as simply using all available images for learning. With this algorithm, VOCUS is able to quickly and robustly detect targets in numerous real-world scenes.

[1]  Gerhard Krieger,et al.  Scene analysis with saccadic eye movements: Top-down and bottom-up modeling , 2001, J. Electronic Imaging.

[2]  Simone Frintrop,et al.  Goal-Directed Search with a Top-Down Modulated Computational Attention System , 2005, DAGM-Symposium.

[3]  L. Itti,et al.  Modeling the influence of task on attention , 2005, Vision Research.

[4]  Laurence R. Harris,et al.  Vision and Attention , 2001 .

[5]  Bärbel Mertsching,et al.  Data- and Model-Driven Gaze Control for an Active-Vision System , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  John K. Tsotsos,et al.  Complexity, Vision, and Attention , 2001 .

[7]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

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

[9]  S. Palmer.  Vision Science : Photons to Phenomenology , 1999 .

[10]  Simone Frintrop,et al.  VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search , 2006, Lecture Notes in Computer Science.

[11]  J. Wolfe,et al.  Guided Search 2.0 A revised model of visual search , 1994, Psychonomic bulletin & review.

[12]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[13]  Fred Henrik Hamker,et al.  Modeling Attention: From Computational Neuroscience to Computer Vision , 2004, WAPCV.

[14]  J. Theeuwes.  Top-down search strategies cannot override attentional capture , 2004, Psychonomic bulletin & review.

[15]  M. Corbetta,et al.  Control of goal-directed and stimulus-driven attention in the brain , 2002, Nature Reviews Neuroscience.

[16]  Robert B. Fisher,et al.  Object-based visual attention for computer vision , 2003, Artif. Intell..

[17]  Simone Frintrop,et al.  Robust Object Detection at Regions of Interest with an Application in Ball Recognition , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.