| Download | - View accepted manuscript: Rapid clustering from colorized 3D point cloud data for reconstructing building interiors (PDF, 459 KiB)
|
|---|
| Author | Search for: Kuldeep, K.; Search for: Knopf, G. K.; Search for: Canas, R.1 |
|---|
| Affiliation | - National Research Council of Canada. NRC Institute for Research in Construction
|
|---|
| Format | Text, Article |
|---|
| Conference | ISOT 2010 International Symposium on Optomechatronic Technologies: 25 October 2010, Toronto, ON |
|---|
| Abstract | This paper introduces a quick and effective segmentation technique for large volumes of colorized range scans from unknown building interiors and labeling clusters of points that represent distinct surfaces and objects in the scene. Rather than computing geometric parameters, the proposed technique uses a robust Hue, Saturation and Value (HSV) color model as an effective means of identifying rough clusters (objects) that are further refined by eliminating spurious and outlier points through region growth and a fixed distance neighbors (FDNs) analysis. The results demonstrate that the proposed method is effective in identifying continuous clusters and can extract meaningful object clusters, even from geometrically similar regions. |
|---|
| Publication date | 2010-10-25 |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NRC number | NRCC 53602
NRC-IRC-21332 |
|---|
| NPARC number | 20374253 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | db406f02-b814-49a9-9121-bcc7f30358fe |
|---|
| Record created | 2012-07-23 |
|---|
| Record modified | 2020-07-14 |
|---|
