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 language | English |
|---|---|
| Title of host publication | EUVIP 2014 - 5th European Workshop on Visual Information Processing |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Print) | 9781479945726 |
| DOIs | |
| Publication status | Published - 2015 Jan 22 |
| Event | 5th European Workshop on Visual Information Processing, EUVIP 2014 - Paris, France Duration: 2014 Dec 10 → 2014 Dec 12 |
Other
| Other | 5th European Workshop on Visual Information Processing, EUVIP 2014 |
|---|---|
| Country | France |
| City | Paris |
| Period | 14/12/10 → 14/12/12 |
Fingerprint
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
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 proceeding › Conference contribution
}
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 -