Point cloud segmentation method combining supervoxels and PFCM

ZHANG Shuyi; CHANG Jianhua; MAO Renxiang; LI Hongxu; ZHANG Luyao

doi:10.7510/jgjs.issn.1001-3806.2021.04.020

LASER TECHNOLOGY > 2021 > 45(4): 535-540. > DOI: 10.7510/jgjs.issn.1001-3806.2021.04.020

ZHANG Shuyi, CHANG Jianhua, MAO Renxiang, LI Hongxu, ZHANG Luyao. Point cloud segmentation method combining supervoxels and PFCM[J]. LASER TECHNOLOGY, 2021, 45(4): 535-540. DOI: 10.7510/jgjs.issn.1001-3806.2021.04.020

Citation:

PDF (1873 KB)

Point cloud segmentation method combining supervoxels and PFCM

1.
Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China
2.
Jiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science & Technology, Nanjing 210044, China

More Information

Received Date: July 06, 2020
Revised Date: September 11, 2020
Published Date: July 24, 2021

Graphical Abstract

Abstract

Abstract

In order to realize the area division of point cloud data, a segmentation algorithm (SPFCM) combining supervoxels and particle swarm optimization fuzzy C-means (PFCM) was proposed. A random sampling consensus algorithm was used to remove the point cloud plane. According to the spatial position, curvature and fast point feature histogram characteristics of the 3-D point cloud, the octree voxelization point cloud was used to obtain the supervoxel. The PFCM algorithm was used to preliminarily divide the superbody and subdivide the connected point cloud, which overcomes the shortcomings of the PFCM algorithm for stacking objects and over-segmentation of larger objects. The performance test of the SPFCM algorithm was performed on the OSD-v0.2 data set. The experimental results show that compared with the PFCM algorithm, it not only retains its advantages such as fewer parameters and simple operation, but also the index has been greatly improved, and the accuracy is up to 86%, while the recall rate reaches 83%. This research provides help and reference for the accurate segmentation of complex scenes in 3-D point clouds.
- laser technique,
- point cloud segmentation,
- supervoxel,
- fuzzy clustering,
- particle swarm optimization

FullText(HTML)

References (21)

References

[1]	IZADI S, KIM D, HILLIGES O, et al. Kinect fusion: Real-time 3-D reconstruction and interaction using a moving depth camera[C]// Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology. Los Angeles, USA: Association of Computing Machinery, 2011: 559-568.
[2]	NEWCOMBE R A, IZADI S, HILLIGES O, et al. KinectFusion: Real-time dense surface mapping and tracking[C]//Proceedings of the 2011 10th IEEE International Symposium on Mixed and Augmented Reality. New York, USA: IEEE, 2011: 127-136.
[3]	YANG Y T, HUANG G Y, ZHANG K, et al. An improved method of three-dimensional point cloud data segmentation based on curvature constraint[J]. Minicomputer System, 2017, 38 (11): 2573-2579(in Chinese).
[4]	WANG Z Y, MA H Ch, XU H G, et al. Fast edge extraction algorithm of massive point cloud[J]. Computer Engineering and Application, 2010, 46(36): 213-215(in Chinese).
[5]	BHANU B, LEE S, HO C, et al. Range data processing: Representation of surfaces by edges[C]// Proceedings of the Eighth International Conference on Pattern Recognition. New York, USA: IEEE, 1986: 236-238.
[6]	DING Ch J, SUN G, YIN L L, et al. Boundary extraction of scattered point cloud[J]. Computer Technology and Development, 2017, 27(7): 83-86(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTOTAL-WJFZ201707020.htm
[7]	BESL P J, JAIN R C. Segmentation through variable-order surface fitting[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1988, 10(2): 167-192. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=3881
[8]	STEIN S C, SCHOELER M, PAPON J, et al. Object partitioning using local convexity[C]//Computer Vision and Pattern Recognition. New York, USA: IEEE, 2014: 304-311.
[9]	LI R Zh, LIU Y Y, YANG M, et al. 3-D point cloud segmentation based on improved region growth[J]. Progress in Laser and Opto-electronics, 2018, 55(5): 051502(in Chinese). DOI: 10.3788/LOP55.051502
[10]	SHI H Y, GUO T, WANG D, et al. Power line suspension point location method based on laser point cloud[J]. Laser Technology, 2020, 44(3): 364-370 (in Chinese).
[11]	LIN Y, WANG C, ZHAI D, et al. Toward better boundary preserved supervoxel segmentation for 3-D point clouds[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2018, 143(9): 39-47. http://www.sciencedirect.com/science/article/pii/S0924271618301370
[12]	LI M L, ZONG W P, LI G Y, et al. Extraction of structure line segments from point clouds using voxel-based region growing[J]. Acta Optica Sinica, 2018, 38(1): 0112002 (in Chinese). DOI: 10.3788/AOS201838.0112002
[13]	WANG X H, WU L Sh, CHEN H W, et al. Regional segmentation of point cloud data by improved particle swarm optimization fuzzy clustering[J]. Optical Precision Engineering, 2017, 25 (4): 563-573(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTOTAL-GXJM201704034.htm
[14]	GUO B, HUANG X, ZHANG F, et al. Classification of airborne laser scanning data using JointBoost[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2015, 100(4): 71-83. http://www.sciencedirect.com/science/article/pii/S0924271614001105
[15]	LU X, YAO J, TU J, et al. Pairwise linkage for point cloud segmentation[J]. ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences, 2016, 3(3): 201-206. http://d.wanfangdata.com.cn/periodical/Doaj000004697245
[16]	BIOSCA J M, LERMA J L. Unsupervised robust planar segmentation of terrestrial laser scanner point clouds based on fuzzy clustering methods[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2008, 63(1): 84-98. http://www.sciencedirect.com/science/article/pii/S0924271607000809
[17]	CANG G H, YUE J P. Plane fitting of point clouds based on weighted total least square[J]. Laser Technology, 2014, 38(3): 307-310(in Chinese). http://en.cnki.com.cn/Article_en/CJFDTOTAL-JGJS201403005.htm
[18]	ANAND A, KOPPULA H S, JOACHIMS T, et al. Contextually guided semantic labeling and search for 3-D point clouds[J]. International Journal of Robotics Research, 2011, 32(1): 19-34. http://arxiv.org/abs/1111.5358
[19]	WOLF D, PRANKL J, VINCZE M. Fast semantic segmentation of 3-D point clouds using a dense CRF with learned parameters[C]//2015 IEEE International Conference on Robotics & Automation. New York, USA: IEEE, 2015: 4867-4873.
[20]	SHU Z, QI C, XIN S, et al. Unsupervised 3-D shape segmentation and co-segmentation via deep learning[J]. Computer Aided Geometric Design, 2016, 43(3): 39-52. http://www.sciencedirect.com/science/article/pii/S0167839616300164
[21]	RICHTSFELD A, MORWALD T, PRANKL J, et al. Segmentation of unknown objects in indoor environments[J]. Intelligent Robots and Systems, 2012, 17(7): 4791-4796. http://ieeexplore.ieee.org/document/6385661/

Cited By

Cited by

Periodical cited type(0)

Other cited types(6)

Get Citation

PDF

XML

Article views (16) PDF downloads (9) Cited by(6)

Turn off MathJax

Article Contents

Abstract

References

Point cloud segmentation method combining supervoxels and PFCM

Abstract

References

Cited by

Periodical cited type(0)

Other cited types(6)

Catalog

Links：

Point cloud segmentation method combining supervoxels and PFCM

Abstract

References

Cited by

Periodical cited type(0)

Other cited types(6)

Catalog

Links：

Export File

Citation

Format

Content