CERES > School of Engineering (SoE) (2001-July 2014) > Staff publications - School of Engineering >

Please use this identifier to cite or link to this item: http://dspace.lib.cranfield.ac.uk/handle/1826/7590

Document Type: Conference paper
Title: Real-time visual saliency by division of Gaussians
Authors: Katramados, Ioannis
Breckon, Toby P.
Issue Date: 2011
Citation: Ioannis Katramados and Toby Breckon. Real-time visual saliency by division of Gaussians Proceedings of the 18th IEEE International Conference on Image Processing 2011, Brussels, Belgium, 11-14 September 2011, Pages 1701-1704
Abstract: This paper introduces a novel method for deriving visual saliency maps in real- time without compromising the quality of the output. This is achieved by replacing the computationally expensive centre-surround filters with a simpler mathematical model named Division of Gaussians (DIVoG). The results are compared to five other approaches, demonstrating at least six times faster execution than the current state-of-the-art whilst maintaining high detection accuracy. Given the multitude of computer vision applications that make use of visual saliency algorithms such a reduction in computational complexity is essential for improving their real-time performance.
URI: http://dx.doi.org/10.1109/ICIP.2011.6115785
Appears in Collections:Staff publications - School of Engineering

Files in This Item:

File Description SizeFormat
Real-time_visual_saliency-Gaussians-2011.pdf1.82 MBAdobe PDFView/Open

SFX Query

Items in CERES are protected by copyright, with all rights reserved, unless otherwise indicated.