Real-time enhancement of RGB-D point clouds using piecewise plane fitting

Kazuki Matsumoto, Francois De Sorbier, Hideo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper, we propose an efficient framework for reducing noise and holes in depth map captured with an RGB-D camera. This is performed by applying plane fitting to the groups of points assimilable to planar structures and filtering the curved surface points. We present a new method for finding global planar structures in a 3D scene by combining superpixel segmentation and graph component labeling. The superpixel segmentation is based on not only color information but also depth and normal maps. The labeling process is carried out by considering each normal in given superpixel's clusters. We evaluate the reliability of each plane structure and apply the plane fitting only to true planar surfaces. As a result, our system can reduce the noise of the depth map especially on planar area while preserving curved surfaces. The process is done in real-time thanks to GPGPU acceleration via CUDA architecture.

Original languageEnglish
Title of host publicationEUVIP 2014 - 5th European Workshop on Visual Information Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479945726
DOIs
Publication statusPublished - 2015 Jan 22
Event5th European Workshop on Visual Information Processing, EUVIP 2014 - Paris, France
Duration: 2014 Dec 102014 Dec 12

Other

Other5th European Workshop on Visual Information Processing, EUVIP 2014
CountryFrance
CityParis
Period14/12/1014/12/12

Fingerprint

Labeling
Cameras
Color

Keywords

  • GPU
  • Noise Reduction
  • Plane Fitting
  • RGB-D camera
  • Superpixel

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Information Systems
  • Signal Processing

Cite this

Matsumoto, K., De Sorbier, F., & Saito, H. (2015). Real-time enhancement of RGB-D point clouds using piecewise plane fitting. In EUVIP 2014 - 5th European Workshop on Visual Information Processing [7018365] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EUVIP.2014.7018365

Real-time enhancement of RGB-D point clouds using piecewise plane fitting. / Matsumoto, Kazuki; De Sorbier, Francois; Saito, Hideo.

EUVIP 2014 - 5th European Workshop on Visual Information Processing. Institute of Electrical and Electronics Engineers Inc., 2015. 7018365.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Matsumoto, K, De Sorbier, F & Saito, H 2015, Real-time enhancement of RGB-D point clouds using piecewise plane fitting. in EUVIP 2014 - 5th European Workshop on Visual Information Processing., 7018365, Institute of Electrical and Electronics Engineers Inc., 5th European Workshop on Visual Information Processing, EUVIP 2014, Paris, France, 14/12/10. https://doi.org/10.1109/EUVIP.2014.7018365
Matsumoto K, De Sorbier F, Saito H. Real-time enhancement of RGB-D point clouds using piecewise plane fitting. In EUVIP 2014 - 5th European Workshop on Visual Information Processing. Institute of Electrical and Electronics Engineers Inc. 2015. 7018365 https://doi.org/10.1109/EUVIP.2014.7018365
Matsumoto, Kazuki ; De Sorbier, Francois ; Saito, Hideo. / Real-time enhancement of RGB-D point clouds using piecewise plane fitting. EUVIP 2014 - 5th European Workshop on Visual Information Processing. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{771f03ab3af44ef09ea24f9cacceae30,
title = "Real-time enhancement of RGB-D point clouds using piecewise plane fitting",
abstract = "In this paper, we propose an efficient framework for reducing noise and holes in depth map captured with an RGB-D camera. This is performed by applying plane fitting to the groups of points assimilable to planar structures and filtering the curved surface points. We present a new method for finding global planar structures in a 3D scene by combining superpixel segmentation and graph component labeling. The superpixel segmentation is based on not only color information but also depth and normal maps. The labeling process is carried out by considering each normal in given superpixel's clusters. We evaluate the reliability of each plane structure and apply the plane fitting only to true planar surfaces. As a result, our system can reduce the noise of the depth map especially on planar area while preserving curved surfaces. The process is done in real-time thanks to GPGPU acceleration via CUDA architecture.",
keywords = "GPU, Noise Reduction, Plane Fitting, RGB-D camera, Superpixel",
author = "Kazuki Matsumoto and {De Sorbier}, Francois and Hideo Saito",
year = "2015",
month = "1",
day = "22",
doi = "10.1109/EUVIP.2014.7018365",
language = "English",
isbn = "9781479945726",
booktitle = "EUVIP 2014 - 5th European Workshop on Visual Information Processing",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Real-time enhancement of RGB-D point clouds using piecewise plane fitting

AU - Matsumoto, Kazuki

AU - De Sorbier, Francois

AU - Saito, Hideo

PY - 2015/1/22

Y1 - 2015/1/22

N2 - In this paper, we propose an efficient framework for reducing noise and holes in depth map captured with an RGB-D camera. This is performed by applying plane fitting to the groups of points assimilable to planar structures and filtering the curved surface points. We present a new method for finding global planar structures in a 3D scene by combining superpixel segmentation and graph component labeling. The superpixel segmentation is based on not only color information but also depth and normal maps. The labeling process is carried out by considering each normal in given superpixel's clusters. We evaluate the reliability of each plane structure and apply the plane fitting only to true planar surfaces. As a result, our system can reduce the noise of the depth map especially on planar area while preserving curved surfaces. The process is done in real-time thanks to GPGPU acceleration via CUDA architecture.

AB - In this paper, we propose an efficient framework for reducing noise and holes in depth map captured with an RGB-D camera. This is performed by applying plane fitting to the groups of points assimilable to planar structures and filtering the curved surface points. We present a new method for finding global planar structures in a 3D scene by combining superpixel segmentation and graph component labeling. The superpixel segmentation is based on not only color information but also depth and normal maps. The labeling process is carried out by considering each normal in given superpixel's clusters. We evaluate the reliability of each plane structure and apply the plane fitting only to true planar surfaces. As a result, our system can reduce the noise of the depth map especially on planar area while preserving curved surfaces. The process is done in real-time thanks to GPGPU acceleration via CUDA architecture.

KW - GPU

KW - Noise Reduction

KW - Plane Fitting

KW - RGB-D camera

KW - Superpixel

UR - http://www.scopus.com/inward/record.url?scp=84923531925&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923531925&partnerID=8YFLogxK

U2 - 10.1109/EUVIP.2014.7018365

DO - 10.1109/EUVIP.2014.7018365

M3 - Conference contribution

AN - SCOPUS:84923531925

SN - 9781479945726

BT - EUVIP 2014 - 5th European Workshop on Visual Information Processing

PB - Institute of Electrical and Electronics Engineers Inc.

ER -