| ECVision indexed and annotated bibliography of cognitive computer vision publications This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1 The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
S. Minut and S. Mahadevan
ABSTRACT
This paper proposes a model of selective attention for visual search tasks, based on a framework for sequential decision- making. The model is implemented using a xed pan-tilt- zoom camera in a visually cluttered lab environment, which samples the environment at discrete time steps. The agent has to decide where to xate next based purely on visual information, in order to reach the region where a target object is most likely to be found. The model consists of two inter- acting modules. A reinforcement learning module learns a policy on a set of regions in the room for reaching the target object, using as objective function the expected value of the sum of discounted rewards. By selecting an appropriate gaze direction at each step, this module provides top-down control in the selection of the next xation point. The sec- ond module performs \within xation{"} processing, based exclusively on visual information. Its purpose is twofold: to provide the agent with a set of locations of interest in the current image, and to perform the detection and identification of the target object. Detailed experimental results show that the number of saccades to a target object significantly decreases with the number of training epochs. The results also show the learned policy to nd the target object is invariant to small physical displacements as well as object inversion. |
|
| Site generated on Friday, 06 January 2006
|