Publication
Salience detection in time-evolving image sequences
Conference Article
Conference
International Conference on Hybrid Intelligent Systems (HIS)
Edition
3rd
Pages
852-860
Doc link
Authors
Projects associated
Abstract
This paper presents a new approach to detect salient regions in an image. A number of units is used to respond to the most salient regions, adapting their response to the size and range of colors present in each region. The system can be directly used on a sequence of images, continuously adapting its output with time. A quality estimation of each unit allows selecting the most relevant regions present in the image at any time. The output of this process can be used as a visual attention mechanism to determine what parts of the image deserve to be processed further.
Categories
mobile robots, robot vision.
Author keywords
salience detection
Scientific reference
E. Celaya and P. Jiménez. Salience detection in time-evolving image sequences, 3rd International Conference on Hybrid Intelligent Systems, 2003, Melbourne, in Design and application of hybrid intelligent systems, pp. 852-860, 2003, IOS Press, Amsterdam, Holanda.
Follow us!