A fast pipeline for textured object recognition in clutter using an RGB-D sensor

Wu, K; Ranasinghe, R; Dissanayake, G

A fast pipeline for textured object recognition in clutter using an RGB-D sensor

Wu, K Ranasinghe, R

Dissanayake, G

Permalink

Publication Type:: Conference Proceeding
Citation:: 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014, 2014, pp. 1650 - 1655
Issue Date:: 2014-01-01

Closed Access

	Filename	Description	Size
	Fr37.1-P0193.pdf	Published version	290.82 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wu, K	en_US
dc.contributor.author	Ranasinghe, R https://orcid.org/0000-0002-3785-3723	en_US
dc.contributor.author	Dissanayake, G https://orcid.org/0000-0002-7992-0680	en_US
dc.date.issued	2014-01-01	en_US
dc.identifier.citation	2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014, 2014, pp. 1650 - 1655	en_US
dc.identifier.isbn	9781479951994	en_US
dc.identifier.uri	http://hdl.handle.net/10453/33954
dc.description.abstract	© 2014 IEEE. This paper presents a modular algorithm pipeline for recognizing textured household objects in cluttered environment and estimating 6 DOF poses using an RGB-D sensor. The method draws from recent advances in this area and introduces a number of innovations that enable improved performances and faster operational speed in comparison with the state-of-the-art. The pipeline consists of (i) support plane subtraction (ii) SIFT feature extraction and approximate nearest neighbour based matching (iii) feature clustering using 3D Eculidean distances (iv) SVD based pose estimation in combination with a outlier rejection strategy named SORSAC (Spatially ORdered RAndom Consensus) and (v) a pose combination and refinement step to combine overlapping identical instances and to refine the pose estimation result by removing incorrect hypothesis. Quantitative comparisons with the MOPED [1] system on self-constructed dataset are presented to demonstrate the effectiveness of the pipeline.	en_US
dc.relation.ispartof	2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014	en_US
dc.relation.isbasedon	10.1109/ICARCV.2014.7064563	en_US
dc.title	A fast pipeline for textured object recognition in clutter using an RGB-D sensor	en_US
dc.type	Conference Proceeding
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1099 Other Technology	en_US
dc.location.activity	Marina Bay Sands, Singapore
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2014 IEEE. This paper presents a modular algorithm pipeline for recognizing textured household objects in cluttered environment and estimating 6 DOF poses using an RGB-D sensor. The method draws from recent advances in this area and introduces a number of innovations that enable improved performances and faster operational speed in comparison with the state-of-the-art. The pipeline consists of (i) support plane subtraction (ii) SIFT feature extraction and approximate nearest neighbour based matching (iii) feature clustering using 3D Eculidean distances (iv) SVD based pose estimation in combination with a outlier rejection strategy named SORSAC (Spatially ORdered RAndom Consensus) and (v) a pose combination and refinement step to combine overlapping identical instances and to refine the pose estimation result by removing incorrect hypothesis. Quantitative comparisons with the MOPED [1] system on self-constructed dataset are presented to demonstrate the effectiveness of the pipeline.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/33954