Itti, Laurent and Koch, Christof (2001) Feature combination strategies for saliency-based visual attention systems. Journal of Electronic Imaging, 10 (1). pp. 161-169. ISSN 1017-9909. https://resolver.caltech.edu/CaltechAUTHORS:20161025-130455203
![]() |
PDF
- Published Version
See Usage Policy. 495Kb |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20161025-130455203
Abstract
Bottom-up or saliency-based visual attention allows primates to detect nonspecific conspicuous targets in cluttered scenes. A classical metaphor, derived from electrophysiological and psychophysical studies, describes attention as a rapidly shiftable “spotlight.” We use a model that reproduces the attentional scan paths of this spotlight. Simple multi-scale “feature maps” detect local spatial discontinuities in intensity, color, and orientation, and are combined into a unique “master” or “saliency” map. The saliency map is sequentially scanned, in order of decreasing saliency, by the focus of attention. We here study the problem of combining feature maps, from different visual modalities (such as color and orientation), into a unique saliency map. Four combination strategies are compared using three databases of natural color images: (1) Simple normalized summation, (2) linear combination with learned weights, (3) global nonlinear normalization followed by summation, and (4) local nonlinear competition between salient locations followed by summation. Performance was measured as the number of false detections before the most salient target was found. Strategy (1) always yielded poorest performance and (2) best performance, with a threefold to eightfold improvement in time to find a salient target. However, (2) yielded specialized systems with poor generalization. Interestingly, strategy (4) and its simplified, computationally efficient approximation (3) yielded significantly better performance than (1), with up to fourfold improvement, while preserving generality.
Item Type: | Article | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Related URLs: |
| |||||||||
ORCID: |
| |||||||||
Additional Information: | © 2001 SPIE and IS&T. Paper HVEI-10 received Aug. 9, 1999; revised manuscript received Aug. 25, 2000; accepted for publication Sep. 20, 2000. This work was supported by ONR, NIMH and NSF (Caltech ERC). The authors thank Daimler-Benz for providing them with some of the test images used in this study. | |||||||||
Funders: |
| |||||||||
Issue or Number: | 1 | |||||||||
Record Number: | CaltechAUTHORS:20161025-130455203 | |||||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20161025-130455203 | |||||||||
Official Citation: | Laurent Itti and Christof Koch "Feature combination strategies for saliency-based visual attention systems", J. Electron. Imaging. 10(1), 161-169 (Jan 01, 2001). ; http://dx.doi.org/10.1117/1.1333677 | |||||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | |||||||||
ID Code: | 71459 | |||||||||
Collection: | CaltechAUTHORS | |||||||||
Deposited By: | George Porter | |||||||||
Deposited On: | 25 Oct 2016 20:55 | |||||||||
Last Modified: | 03 Oct 2019 16:07 |
Repository Staff Only: item control page