Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
HULÍK, R. ŠPANĚL, M. MATERNA, Z. SMRŽ, P.
Originální název
Continuous Plane Detection in Point-cloud Data Based on 3D Hough Transform
Typ
článek v časopise - ostatní, Jost
Jazyk
angličtina
Originální abstrakt
In modern robotics vision systems, a shape extraction from point clouds (or depth images) is an important and still discussed topic. We present significant optimizations of 3D Hough Transform for a plane extraction from point cloud data. The method aims to overcome noise present in these point clouds, high memory requirements for the parameter space and computational complexity of point accumulations. All these problems are further discussed and solutions are proposed to design a robust plane detector. The detector benefits from the key principle of the Hough transform, the accumulation of values in the parameter space, and processes continuous point cloud stream from the depth sensor for iterative refining of results. The proposed technique is compared against the optimized implementation of RANSAC-based plane detector in the well-known PCL library.
Klíčová slova
RGB-D sensor, point cloud, Hough transform, plane detection, PCL library, RANSAC, computer vision, shape extraction
Autoři
HULÍK, R.; ŠPANĚL, M.; MATERNA, Z.; SMRŽ, P.
Rok RIV
2013
Vydáno
28. 4. 2013
ISSN
1047-3203
Periodikum
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
Ročník
25
Číslo
1
Stát
Spojené státy americké
Strany od
86
Strany do
97
Strany počet
12
URL
http://www.sciencedirect.com/science/article/pii/S104732031300062X
BibTex
@article{BUT103422, author="Rostislav {Hulík} and Michal {Španěl} and Zdeněk {Materna} and Pavel {Smrž}", title="Continuous Plane Detection in Point-cloud Data Based on 3D Hough Transform", journal="JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION", year="2013", volume="25", number="1", pages="86--97", doi="10.1016/j.jvcir.2013.04.001", issn="1047-3203", url="http://www.sciencedirect.com/science/article/pii/S104732031300062X" }