Next Article in Journal
Monitoring Vegetation Phenological Cycles in Two Different Semi-Arid Environmental Settings Using a Ground-Based NDVI System: A Potential Approach to Improve Satellite Data Interpretation
Previous Article in Journal
Towards Multidecadal Consistent Meteosat Surface Albedo Time Series
Article Menu

Article Versions

Export Article

Open AccessArticle
Remote Sens. 2010, 2(4), 968-989; doi:10.3390/rs2040968

Comparative Analysis of Clustering-Based Approaches for 3-D Single Tree Detection Using Airborne Fullwave Lidar Data

Department of Remote Sensing and Landscape Information System (FeLis), Faculty of Forestry, Albert-Ludwigs University, Tennenbacher str. 4, 79106 Freiburg, i.Br., Germany
*
Author to whom correspondence should be addressed.
Received: 18 January 2010 / Revised: 20 February 2010 / Accepted: 27 February 2010 / Published: 1 April 2010
Download PDF [996 KB, uploaded 19 June 2014]

Abstract

In the past, many algorithms have been applied for three-dimensional (3-D) single tree extraction using Airborne Laser Scanner (ALS) data. Clustering based algorithms are widely used in different applications but rarely being they used in the field of forestry using ALS data as an input. In this paper, a comparative qualitative study was conducted using the iterative partitioning and hierarchical clustering based mechanisms and full waveform ALS data as an input to extract the individual trees/tree crowns in their most appropriate shape. The full waveform LIght Detection And Ranging (LIDAR) data was collected from the Waldkirch black forest area in the south-western part of Germany in August 2005 with density of 4–5 points/m2. Both the clustering algorithms were used in their original and modified form for a comparative qualitative analysis of the results obtained in the form of individual clusters containing 3-D points for each tree/tree crown. A total of 378 trees were found in all the 1.2 ha area with height ranging from 15 m to 50.9 m. The forest contains mainly older trees with deciduous, coniferous and mixed stands. The findings showed that among the three kind of clustering methods applied (normal k-means, modified k-means and hierarchical clustering), the modified k-means algorithm using external seed points and scaling down the height for initialization of the clustering process was the most promising method for the extraction of clusters of individual trees/tree crowns. A 3-D reconstruction of extracted individual clusters was carried out using QHull algorithm. In this study, the result was not possible to validate quantitatively due to lack of the field inventory data.
Keywords: LIDAR; clustering; pattern; k-means; hierarchical; 3-D; tree crown; QHull LIDAR; clustering; pattern; k-means; hierarchical; 3-D; tree crown; QHull
This is an open access article distributed under the Creative Commons Attribution License (CC BY 3.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Gupta, S.; Weinacker, H.; Koch, B. Comparative Analysis of Clustering-Based Approaches for 3-D Single Tree Detection Using Airborne Fullwave Lidar Data. Remote Sens. 2010, 2, 968-989.

Show more citation formats Show less citations formats

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top