A computational model of depth-based attention
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (10514651) , 734-739 vol.4
- https://doi.org/10.1109/icpr.1996.547661
Abstract
We present a computational model for attention. It consists of an early parallel stage with preattentive cues followed by a later serial stage, where the cues are integrated. We base the model on disparity image flow and motion. As one of the several possibilities we choose a depth-based criterion to integrate these cues, in such a way that the attention is maintained to the closest moving object. We demonstrate the technique by experiments in which a moving observer selectively mask our different moving objects in real scenes.Keywords
This publication has 6 references indexed in Scilit:
- Towards an active visual observerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Closing the loop: Pursuing a moving object by a moving observerPublished by Springer Nature ,1995
- A head-eye system—Analysis and designCVGIP: Image Understanding, 1992
- Data and model-driven selection using color regionsPublished by Springer Nature ,1992
- Serial and parallel processing of visual feature conjunctionsNature, 1986
- Preattentive processing in visionComputer Vision, Graphics, and Image Processing, 1985