- Abstract:
-
In this paper, a novel model of object-based visual attention extending Duncan's Inte- grated Competition Hypothesis [24] is presented. In contrast to the attention mechanisms used in most previous machine vision systems which drive attention based on the spa- tial location hypothesis, the mechanisms which direct visual attention in our system are object-driven as well as feature-driven. The competition to gain visual attention occurs not only within an object but also between objects. For this purpose, two new mecha- nisms in the proposed model are described and analyzed in detail. The rst mechanism computes the visual salience of objects and groupings; the second one implements the hierarchical selectivity of attentional shifts. The results of the new approach on synthetic and natural images are reported.
- Copyright:
- 2004 by The University of Edinburgh. All Rights Reserved
- Links To Paper
- 1st link
- Bibtex format
- @Article{EDI-INF-RR-0213,
- author = {
Yaoru Sun
and Robert Fisher
},
- title = {Object-Based Visual Attention for Computer Vision},
- journal = {Artificial Intelligence},
- publisher = {Elsevier},
- year = 2004,
- month = {Jun},
- volume = {# 146(1)},
- pages = {77-123},
- doi = {10.1016/S0004-3702(02)00399-5},
- url = {http://homepages.inf.ed.ac.uk/rbf/PAPERS/sun-AI1104.pdf},
- }
|
