Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time

Kazuki Matsumoto, Francois De Sorbier, Hideo Saito

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

Abstract

Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.

Original languageEnglish
Title of host publicationICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings
PublisherSciTePress
Pages150-157
Number of pages8
Volume2
ISBN (Print)9789897580772
Publication statusPublished - 2015
Event4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015 - Lisbon, Portugal
Duration: 2015 Jan 102015 Jan 12

Other

Other4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015
CountryPortugal
CityLisbon
Period15/1/1015/1/12

Fingerprint

Cameras
Labeling
Interpolation
Color
Sensors
Processing

Keywords

  • Denoising
  • Depth map
  • GPU
  • Plane fitting
  • ToF depth sensor
  • Upsampling

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Matsumoto, K., De Sorbier, F., & Saito, H. (2015). Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time. In ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings (Vol. 2, pp. 150-157). SciTePress.

Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time. / Matsumoto, Kazuki; De Sorbier, Francois; Saito, Hideo.

ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings. Vol. 2 SciTePress, 2015. p. 150-157.

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

Matsumoto, K, De Sorbier, F & Saito, H 2015, Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time. in ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings. vol. 2, SciTePress, pp. 150-157, 4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015, Lisbon, Portugal, 15/1/10.
Matsumoto K, De Sorbier F, Saito H. Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time. In ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings. Vol. 2. SciTePress. 2015. p. 150-157
Matsumoto, Kazuki ; De Sorbier, Francois ; Saito, Hideo. / Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time. ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings. Vol. 2 SciTePress, 2015. pp. 150-157
@inproceedings{8e063f92def140958b402515dd69c6b4,
title = "Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time",
abstract = "Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.",
keywords = "Denoising, Depth map, GPU, Plane fitting, ToF depth sensor, Upsampling",
author = "Kazuki Matsumoto and {De Sorbier}, Francois and Hideo Saito",
year = "2015",
language = "English",
isbn = "9789897580772",
volume = "2",
pages = "150--157",
booktitle = "ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings",
publisher = "SciTePress",

}

TY - GEN

T1 - Plane fitting and depth variance based upsampling for noisy depth map from 3D-ToF cameras in real-time

AU - Matsumoto, Kazuki

AU - De Sorbier, Francois

AU - Saito, Hideo

PY - 2015

Y1 - 2015

N2 - Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.

AB - Recent advances of ToF depth sensor devices enables us to easily retrieve scene depth data with high frame rates. However, the resolution of the depth map captured from these devices is much lower than that of color images and the depth data suffers from the optical noise effects. In this paper, we propose an efficient algorithm that upsamples depth map captured by ToF depth cameras and reduces noise. The upsampling is carried out by applying plane based interpolation to the groups of points similar to planar structures and depth variance based joint bilateral upsampling to curved or bumpy surface points. For dividing the depth map into piecewise planar areas, we apply superpixel segmentation and graph component labeling. In order to distinguish planar areas and curved areas, we evaluate the reliability of detected plane structures. Compared with other state-of-the-art algorithms, our method is observed to produce an upsampled depth map that is smoothed and closer to the ground truth depth map both visually and numerically. Since the algorithm is parallelizable, it can work in real-time by utilizing highly parallel processing capabilities of modern commodity GPUs.

KW - Denoising

KW - Depth map

KW - GPU

KW - Plane fitting

KW - ToF depth sensor

KW - Upsampling

UR - http://www.scopus.com/inward/record.url?scp=84938839983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938839983&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84938839983

SN - 9789897580772

VL - 2

SP - 150

EP - 157

BT - ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings

PB - SciTePress

ER -