Almengor Gonzalez, R. (2017): <b>OBIA: Automated delineation of Pine Plantations from Aerial Imagery in the southern Ecuadorian Paramos</b> Technische Universität München, <i>master thesis</i>
Resource Description
Title:
OBIA: Automated delineation of Pine Plantations from Aerial Imagery in the southern Ecuadorian Paramos
FOR816dw ID:
1657
Publication Date:
2017-08-13
License and Usage Rights:
PAK 823-825 data user agreement. (www.tropicalmountainforest.org/dataagreementp3.do)
Resource Owner(s):
Individual:
Roger Almengor Gonzalez
Contact:
email:
webmaster <at> tropicalmountainforest.org
Abstract:
Geographic Information Systems and Remote Sensing are important contributors to Sustainable<br/>
Forestry Management Plans. Remote sensing techniques for image interpretation provides the<br/>
means to extract valuable information that could be expensive and time-consuming to obtain<br/>
through field observations (Franklin et al. 2001).<br/>
Spatial Products derived from the interpretation of airborne and satellite borne images feed<br/>
Geographic Information Systems to develop strategies and methodologies for resource<br/>
management, harvest planning, fire management, map production, and model predictions.<br/>
(Yusmah et al. 2015)<br/>
This study has three important objectives: to test the feasibility of template matching for the<br/>
identification of single pine tree crowns, to conduct a delineation of pine plantations using<br/>
relational features and to evaluate how single tree crown size affects the accuracy of the<br/>
proposed method.<br/>
Templates of single trees were produced in the software eCognition Developer. The sampling<br/>
process comprised the random selection of 3000 single pine trees in 7 different test sites (test sites were grouped in 3 categories according to the single tree sizes). A first rule set to detect<br/>
single tree crowns was developed in eCognition Developer, using three different template groups (4, 8 and 16 templates). Through an analysis of variance, the number of single tree<br/>
crowns detected was compared for the different template groups.<br/>
Using a second rule set in eCognition, the template matching algorithm combined with<br/>
relational, spectral and contextual information were applied to delineate pine plantation areas.<br/>
An accuracy assessment was performed in the test sites for all thematic classes identified.<br/>
Finally, an Analysis of Variance evaluated the influence of single tree crown size on the overall<br/>
accuracy.<br/>
Potential applications and improvements to the proposed methodology for single tree crown detection and plantation delineation are proposed at the end of the document.
Additional Infos:
Master Thesis jointly supervised by Thomas Schneider and Patrick Hildebrandt (Project B5 and B3)
Keywords:
| reforestation | remote sensing | pine forest | Paramo | Cajas National Park | orthophotos |
Literature type specific fields:
THESIS
Degree:
master
Degree Institution:
Technische Universität München
Total Pages:
86
Metadata Provider:
Individual:
Carola Paul
Contact:
email:
carola.paul <at> tum.de
Center of Life and Food Sciences Weihenstephan
Institute of Forest Management
Technische Universität München
Hans-Carl-von-Carlowitz-Platz 2
85354 Freising
Germany
