Details
| Original language | English |
|---|---|
| Title of host publication | Joint Urban Remote Sensing Event 2013, JURSE 2013 |
| Publisher | IEEE Computer Society |
| Pages | 139-142 |
| Number of pages | 4 |
| ISBN (print) | 9781479902132 |
| Publication status | Published - 2013 |
| Event | 2013 Joint Urban Remote Sensing Event, JURSE 2013 - Sao Paulo, Brazil Duration: 21 Apr 2013 → 23 Apr 2013 |
Publication series
| Name | Joint Urban Remote Sensing Event 2013, JURSE 2013 |
|---|
Abstract
In this work we address the task of contextual classification of an airborne LiDAR point cloud. For that purpose, we integrate a Random Forest classifier into a Conditional Random Field (CRF) framework. A CRF has been shown to deliver good results discerning multiple classes. It is a flexible approach for obtaining a reliable classification even in complex urban scenes. The incorporation of multi-scale features improves the results further. Based on the classification results, 2D building and tree objects are generated and evaluated by the benchmark of ISPRS WG III/4.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Joint Urban Remote Sensing Event 2013, JURSE 2013. IEEE Computer Society, 2013. p. 139-142 6550685 (Joint Urban Remote Sensing Event 2013, JURSE 2013).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Classification of urban LiDAR data using conditional random field and random forests
AU - Niemeyer, Joachim
AU - Rottensteiner, Franz
AU - Soergel, Uwe
PY - 2013
Y1 - 2013
N2 - In this work we address the task of contextual classification of an airborne LiDAR point cloud. For that purpose, we integrate a Random Forest classifier into a Conditional Random Field (CRF) framework. A CRF has been shown to deliver good results discerning multiple classes. It is a flexible approach for obtaining a reliable classification even in complex urban scenes. The incorporation of multi-scale features improves the results further. Based on the classification results, 2D building and tree objects are generated and evaluated by the benchmark of ISPRS WG III/4.
AB - In this work we address the task of contextual classification of an airborne LiDAR point cloud. For that purpose, we integrate a Random Forest classifier into a Conditional Random Field (CRF) framework. A CRF has been shown to deliver good results discerning multiple classes. It is a flexible approach for obtaining a reliable classification even in complex urban scenes. The incorporation of multi-scale features improves the results further. Based on the classification results, 2D building and tree objects are generated and evaluated by the benchmark of ISPRS WG III/4.
UR - http://www.scopus.com/inward/record.url?scp=84881358566&partnerID=8YFLogxK
U2 - 10.1109/JURSE.2013.6550685
DO - 10.1109/JURSE.2013.6550685
M3 - Conference contribution
AN - SCOPUS:84881358566
SN - 9781479902132
T3 - Joint Urban Remote Sensing Event 2013, JURSE 2013
SP - 139
EP - 142
BT - Joint Urban Remote Sensing Event 2013, JURSE 2013
PB - IEEE Computer Society
T2 - 2013 Joint Urban Remote Sensing Event, JURSE 2013
Y2 - 21 April 2013 through 23 April 2013
ER -