Donnarumma, Francesco, Lippiello, Vincenzo and Saveriano, Matteo (2012) Fast Incremental Clustering and Representation of a 3D Point Cloud Sequence with Planar Regions. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems October 7-12, 2012. Vilamoura, Algarve, Portugal. IEEE, pp. 3475-3480. ISBN 978-1-4673-1737-5
Preview |
Text
06385511.pdf Download (563kB) | Preview |
| Item Type: | Book Section |
|---|---|
| Resource language: | English |
| Title: | Fast Incremental Clustering and Representation of a 3D Point Cloud Sequence with Planar Regions |
| Creators: | Creators Email Donnarumma, Francesco UNSPECIFIED Lippiello, Vincenzo UNSPECIFIED Saveriano, Matteo UNSPECIFIED |
| Date: | 2012 |
| Number of Pages: | 6 |
| Institution: | Università degli Studi di Napoli Federico II |
| Department: | Ingegneria elettrica e delle Tecnologie dell'Informazione |
| Title of Book: | 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems October 7-12, 2012. Vilamoura, Algarve, Portugal |
| Publisher: | IEEE |
| Date: | 2012 |
| ISBN: | 978-1-4673-1737-5 |
| Page Range: | pp. 3475-3480 |
| Number of Pages: | 6 |
| Access rights: | Open access |
| Additional information: | AIRobots |
| Date Deposited: | 23 Jun 2014 13:36 |
| Last Modified: | 17 May 2017 17:29 |
| URI: | http://www.fedoa.unina.it/id/eprint/9590 |
Collection description
An incremental clustering technique to partition 3D point clouds into planar regions is presented in this paper. The algorithm works in real-time on unknown and noisy data, without any initial assumption. An iterative cluster growing technique is proposed in order to correctly classify a flow of 3D points and to merge close regions. The computational efficiency of the approach is achieved by using an Incremental Principal Component Analysis (IPCA) technique, and with the adoption of a compact geometrical representation based on the concave-hull computation of each cluster. This solution adds a more realistic representation of the observed environment and reduces the number of points needed to identify the cluster shape. The effectiveness of the proposed algorithm has been validated with both synthetic and real data sets
Downloads
Downloads per month over past year
Actions (login required)
 |
View Item |
