Using motion for foveated analysis of video

In this paper we address the problem of how the saccadic behavior of biological observers interacts with either unchanging and suddenly appearing elements in the scene. We will show how the optical flow information can be exploited to compute an alerting map, which is then used together with a static conspicuity map to generate gaze shifts.

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

[2]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[3]  Hanspeter A. Mallot,et al.  Saccadic object recognition with an active vision system , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[4]  M. Sommer,et al.  The spatial relationship between scanning saccades and express saccades , 1997, Vision Research.

[5]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[6]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[7]  Thierry Pun,et al.  Attentive mechanisms for dynamic and static scene analysis , 1995 .

[8]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[9]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.