Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 950-974 |
| Seitenumfang | 25 |
| Fachzeitschrift | Remote sensing |
| Jahrgang | 4 |
| Ausgabenummer | 4 |
| Publikationsstatus | Veröffentlicht - 30 März 2012 |
Abstract
The objective of the "Tree Extraction" project organized by EuroSDR (European Spatial data Research) and ISPRS (International Society of Photogrammetry and Remote Sensing) was to evaluate the quality, accuracy, and feasibility of automatic tree extraction methods, mainly based on laser scanner data. In the final report of the project, Kaartinen and Hyyppä (2008) reported a high variation in the quality of the published methods under boreal forest conditions and with varying laser point densities. This paper summarizes the findings beyond the final report after analyzing the results obtained in different tree height classes. Omission/Commission statistics as well as neighborhood relations are taken into account. Additionally, four automatic tree detection and extraction techniques were added to the test. Several methods in this experiment were superior to manual processing in the dominant, co-dominant and suppressed tree storeys. In general, as expected, the taller the tree, the better the location accuracy. The accuracy of tree height, after removing gross errors, was better than 0.5 m in all tree height classes with the best methods investigated in this experiment. For forest inventory, minimum curvature-based tree detection accompanied by point cloud-based cluster detection for suppressed trees is a solution that deserves attention in the future.
ASJC Scopus Sachgebiete
- Erdkunde und Planetologie (insg.)
- Allgemeine Erdkunde und Planetologie
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Remote sensing, Jahrgang 4, Nr. 4, 30.03.2012, S. 950-974.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - An International Comparison of Individual Tree Detection and Extraction Using Airborne Laser Scanning
AU - Kaartinen, Harri
AU - Hyyppä, Juha
AU - Yu, Xiaowei
AU - Vastaranta, Mikko
AU - Hyyppä, Hannu
AU - Kukko, Antero
AU - Holopainen, Markus
AU - Heipke, Christian
AU - Hirschmugl, Manuela
AU - Morsdorf, Felix
AU - Næsset, Erik
AU - Pitkänen, Juho
AU - Popescu, Sorin
AU - Solberg, Svein
AU - Wolf, Bernd Michael
AU - Wu, Jee Cheng
PY - 2012/3/30
Y1 - 2012/3/30
N2 - The objective of the "Tree Extraction" project organized by EuroSDR (European Spatial data Research) and ISPRS (International Society of Photogrammetry and Remote Sensing) was to evaluate the quality, accuracy, and feasibility of automatic tree extraction methods, mainly based on laser scanner data. In the final report of the project, Kaartinen and Hyyppä (2008) reported a high variation in the quality of the published methods under boreal forest conditions and with varying laser point densities. This paper summarizes the findings beyond the final report after analyzing the results obtained in different tree height classes. Omission/Commission statistics as well as neighborhood relations are taken into account. Additionally, four automatic tree detection and extraction techniques were added to the test. Several methods in this experiment were superior to manual processing in the dominant, co-dominant and suppressed tree storeys. In general, as expected, the taller the tree, the better the location accuracy. The accuracy of tree height, after removing gross errors, was better than 0.5 m in all tree height classes with the best methods investigated in this experiment. For forest inventory, minimum curvature-based tree detection accompanied by point cloud-based cluster detection for suppressed trees is a solution that deserves attention in the future.
AB - The objective of the "Tree Extraction" project organized by EuroSDR (European Spatial data Research) and ISPRS (International Society of Photogrammetry and Remote Sensing) was to evaluate the quality, accuracy, and feasibility of automatic tree extraction methods, mainly based on laser scanner data. In the final report of the project, Kaartinen and Hyyppä (2008) reported a high variation in the quality of the published methods under boreal forest conditions and with varying laser point densities. This paper summarizes the findings beyond the final report after analyzing the results obtained in different tree height classes. Omission/Commission statistics as well as neighborhood relations are taken into account. Additionally, four automatic tree detection and extraction techniques were added to the test. Several methods in this experiment were superior to manual processing in the dominant, co-dominant and suppressed tree storeys. In general, as expected, the taller the tree, the better the location accuracy. The accuracy of tree height, after removing gross errors, was better than 0.5 m in all tree height classes with the best methods investigated in this experiment. For forest inventory, minimum curvature-based tree detection accompanied by point cloud-based cluster detection for suppressed trees is a solution that deserves attention in the future.
KW - 3D
KW - Airborne laser scanning
KW - Crown delineation
KW - EuroSDR
KW - Individual tree inventory
KW - ISPRS
KW - Tree detection
KW - Tree extraction
UR - http://www.scopus.com/inward/record.url?scp=84861322415&partnerID=8YFLogxK
U2 - 10.3390/rs4040950
DO - 10.3390/rs4040950
M3 - Article
AN - SCOPUS:84861322415
VL - 4
SP - 950
EP - 974
JO - Remote sensing
JF - Remote sensing
SN - 2072-4292
IS - 4
ER -