Graphcut-based interactive segmentation using colour and depth cues

He, Hu, McKinnon, David, Warren, Michael and Upcroft, Ben (2010). Graphcut-based interactive segmentation using colour and depth cues. In: Gordon Wyeth and Ben Upcroft, Proceedings of the Australasian Conference on Robotics and Automation. Australasian Conference on Robotics and Automation 2010 (ACRA2010), Brisbane, QLD, Austalia, (). 1-3 December 2010.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
UQ222830_fulltext.pdf ERA evidence - not publicly available application/pdf 3.91MB 1
Author He, Hu
McKinnon, David
Warren, Michael
Upcroft, Ben
Title of paper Graphcut-based interactive segmentation using colour and depth cues
Conference name Australasian Conference on Robotics and Automation 2010 (ACRA2010)
Conference location Brisbane, QLD, Austalia
Conference dates 1-3 December 2010
Proceedings title Proceedings of the Australasian Conference on Robotics and Automation
Journal name Proceedings of the 2010 Australasian Conference on Robotics and Automation, ACRA 2010
Place of Publication Brisbane, QLD, Australia
Publisher Australian Robotics & Automation Association (ARAA)
Publication Year 2010
Sub-type Fully published paper
ISBN 9780980740417
Editor Gordon Wyeth
Ben Upcroft
Total pages 8
Language eng
Formatted Abstract/Summary
Segmentation of novel or dynamic objects in a scene, often referred to as background sub- traction or foreground segmentation, is critical for robust high level computer vision applica- tions such as object tracking, object classica- tion and recognition. However, automatic real- time segmentation for robotics still poses chal- lenges including global illumination changes, shadows, inter-re ections, colour similarity of foreground to background, and cluttered back- grounds. This paper introduces depth cues provided by structure from motion (SFM) for interactive segmentation to alleviate some of these challenges. In this paper, two prevailing interactive segmentation algorithms are com- pared; Lazysnapping [Li et al., 2004] and Grab- cut [Rother et al., 2004], both based on graph- cut optimisation [Boykov and Jolly, 2001]. The algorithms are extended to include depth cues rather than colour only as in the original pa- pers. Results show interactive segmentation based on colour and depth cues enhances the performance of segmentation with a lower er- ror with respect to ground truth.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Conference Paper
Collection: School of Mechanical & Mining Engineering Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Mon, 29 Nov 2010, 14:13:16 EST by Dr Benjamin Upcroft on behalf of School of Mechanical and Mining Engineering