Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding

Francesco Verdoja, Diego Gabriel Francis Thomas, Akihiro Sugimoto

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

7 Citations (Scopus)

Abstract

Segmentation of 3D colored point clouds is a research field with renewed interest thanks to recent availability of inexpensive consumer RGB-D cameras and its importance as an unavoidable low-level step in many robotic applications. However, 3D data's nature makes the task challenging and, thus, many different techniques are being proposed, all of which require expensive computational costs. This paper presents a novel fast method for 3D colored point cloud segmentation. It starts with supervoxel partitioning of the cloud, i.e., an oversegmentation of the points in the cloud. Then it leverages on a novel metric exploiting both geometry and color to iteratively merge the supervoxels to obtain a 3D segmentation where the hierarchical structure of partitions is maintained. The algorithm also presents computational complexity linear to the size of the input. Experimental results over two publicly available datasets demonstrate that our proposed method outperforms state-of-the-art techniques.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Multimedia and Expo, ICME 2017
PublisherIEEE Computer Society
Pages1285-1290
Number of pages6
ISBN (Electronic)9781509060672
DOIs
Publication statusPublished - Aug 28 2017
Event2017 IEEE International Conference on Multimedia and Expo, ICME 2017 - Hong Kong, Hong Kong
Duration: Jul 10 2017Jul 14 2017

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Other

Other2017 IEEE International Conference on Multimedia and Expo, ICME 2017
CountryHong Kong
CityHong Kong
Period7/10/177/14/17

Fingerprint

Computational complexity
Robotics
Cameras
Availability
Color
Geometry
Costs

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Verdoja, F., Thomas, D. G. F., & Sugimoto, A. (2017). Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding. In 2017 IEEE International Conference on Multimedia and Expo, ICME 2017 (pp. 1285-1290). [8019382] (Proceedings - IEEE International Conference on Multimedia and Expo). IEEE Computer Society. https://doi.org/10.1109/ICME.2017.8019382

Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding. / Verdoja, Francesco; Thomas, Diego Gabriel Francis; Sugimoto, Akihiro.

2017 IEEE International Conference on Multimedia and Expo, ICME 2017. IEEE Computer Society, 2017. p. 1285-1290 8019382 (Proceedings - IEEE International Conference on Multimedia and Expo).

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

Verdoja, F, Thomas, DGF & Sugimoto, A 2017, Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding. in 2017 IEEE International Conference on Multimedia and Expo, ICME 2017., 8019382, Proceedings - IEEE International Conference on Multimedia and Expo, IEEE Computer Society, pp. 1285-1290, 2017 IEEE International Conference on Multimedia and Expo, ICME 2017, Hong Kong, Hong Kong, 7/10/17. https://doi.org/10.1109/ICME.2017.8019382
Verdoja F, Thomas DGF, Sugimoto A. Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding. In 2017 IEEE International Conference on Multimedia and Expo, ICME 2017. IEEE Computer Society. 2017. p. 1285-1290. 8019382. (Proceedings - IEEE International Conference on Multimedia and Expo). https://doi.org/10.1109/ICME.2017.8019382
Verdoja, Francesco ; Thomas, Diego Gabriel Francis ; Sugimoto, Akihiro. / Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding. 2017 IEEE International Conference on Multimedia and Expo, ICME 2017. IEEE Computer Society, 2017. pp. 1285-1290 (Proceedings - IEEE International Conference on Multimedia and Expo).
@inproceedings{5f0613e63fc6438d94b3638597dab073,
title = "Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding",
abstract = "Segmentation of 3D colored point clouds is a research field with renewed interest thanks to recent availability of inexpensive consumer RGB-D cameras and its importance as an unavoidable low-level step in many robotic applications. However, 3D data's nature makes the task challenging and, thus, many different techniques are being proposed, all of which require expensive computational costs. This paper presents a novel fast method for 3D colored point cloud segmentation. It starts with supervoxel partitioning of the cloud, i.e., an oversegmentation of the points in the cloud. Then it leverages on a novel metric exploiting both geometry and color to iteratively merge the supervoxels to obtain a 3D segmentation where the hierarchical structure of partitions is maintained. The algorithm also presents computational complexity linear to the size of the input. Experimental results over two publicly available datasets demonstrate that our proposed method outperforms state-of-the-art techniques.",
author = "Francesco Verdoja and Thomas, {Diego Gabriel Francis} and Akihiro Sugimoto",
year = "2017",
month = "8",
day = "28",
doi = "10.1109/ICME.2017.8019382",
language = "English",
series = "Proceedings - IEEE International Conference on Multimedia and Expo",
publisher = "IEEE Computer Society",
pages = "1285--1290",
booktitle = "2017 IEEE International Conference on Multimedia and Expo, ICME 2017",
address = "United States",

}

TY - GEN

T1 - Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding

AU - Verdoja, Francesco

AU - Thomas, Diego Gabriel Francis

AU - Sugimoto, Akihiro

PY - 2017/8/28

Y1 - 2017/8/28

N2 - Segmentation of 3D colored point clouds is a research field with renewed interest thanks to recent availability of inexpensive consumer RGB-D cameras and its importance as an unavoidable low-level step in many robotic applications. However, 3D data's nature makes the task challenging and, thus, many different techniques are being proposed, all of which require expensive computational costs. This paper presents a novel fast method for 3D colored point cloud segmentation. It starts with supervoxel partitioning of the cloud, i.e., an oversegmentation of the points in the cloud. Then it leverages on a novel metric exploiting both geometry and color to iteratively merge the supervoxels to obtain a 3D segmentation where the hierarchical structure of partitions is maintained. The algorithm also presents computational complexity linear to the size of the input. Experimental results over two publicly available datasets demonstrate that our proposed method outperforms state-of-the-art techniques.

AB - Segmentation of 3D colored point clouds is a research field with renewed interest thanks to recent availability of inexpensive consumer RGB-D cameras and its importance as an unavoidable low-level step in many robotic applications. However, 3D data's nature makes the task challenging and, thus, many different techniques are being proposed, all of which require expensive computational costs. This paper presents a novel fast method for 3D colored point cloud segmentation. It starts with supervoxel partitioning of the cloud, i.e., an oversegmentation of the points in the cloud. Then it leverages on a novel metric exploiting both geometry and color to iteratively merge the supervoxels to obtain a 3D segmentation where the hierarchical structure of partitions is maintained. The algorithm also presents computational complexity linear to the size of the input. Experimental results over two publicly available datasets demonstrate that our proposed method outperforms state-of-the-art techniques.

UR - http://www.scopus.com/inward/record.url?scp=85030221172&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030221172&partnerID=8YFLogxK

U2 - 10.1109/ICME.2017.8019382

DO - 10.1109/ICME.2017.8019382

M3 - Conference contribution

AN - SCOPUS:85030221172

T3 - Proceedings - IEEE International Conference on Multimedia and Expo

SP - 1285

EP - 1290

BT - 2017 IEEE International Conference on Multimedia and Expo, ICME 2017

PB - IEEE Computer Society

ER -