World Library  


Add to Book Shelf
Flag as Inappropriate
Email this Book

Detection of Fallen Trees in Als Point Clouds by Learning the Normalized Cut Similarity Function from Simulated Samples : Volume Ii-3, Issue 1 (07/08/2014)

By Polewski, P.

Click here to view

Book Id: WPLBN0004013802
Format Type: PDF Article :
File Size: Pages 8
Reproduction Date: 2015

Title: Detection of Fallen Trees in Als Point Clouds by Learning the Normalized Cut Similarity Function from Simulated Samples : Volume Ii-3, Issue 1 (07/08/2014)  
Author: Polewski, P.
Volume: Vol. II-3, Issue 1
Language: English
Subject: Science, Isprs, Annals
Collections: Periodicals: Journal and Magazine Collection, Copernicus GmbH
Historic
Publication Date:
2014
Publisher: Copernicus Gmbh, Göttingen, Germany

Citation

APA MLA Chicago

Krzystek, P., Heurich, M., Yao, W., Polewski, P., & Stilla, U. (2014). Detection of Fallen Trees in Als Point Clouds by Learning the Normalized Cut Similarity Function from Simulated Samples : Volume Ii-3, Issue 1 (07/08/2014). Retrieved from http://worldpubliclibrary.org/


Description
Description: Dept. of Geoinformatics, Munich University of Applied Sciences, 80333 Munich, Germany. Fallen trees participate in several important forest processes, which motivates the need for information about their spatial distribution in forest ecosystems. Several studies have shown that airborne LiDAR is a valuable tool for obtaining such information. In this paper, we propose an integrated method of detecting fallen trees from ALS point clouds based on merging small segments into entire fallen stems via the Normalized Cut algorithm. A new approach to specifying the segment similarity function for the clustering algorithm is introduced, where the attribute weights are learned from labeled data instead of being determined manually. We notice the relationship between Normalized Cut’s similarity function and a class of regression models, which leads us to the idea of approximating the task of learning the similarity function with the simpler task of learning a classifier. Moreover, we set up a virtual fallen tree generation scheme to simulate complex forest scenarios with multiple overlapping fallen stems. The classifier trained on this simulated data yields a similarity function for Normalized Cut. Tests on two sample plots from the Bavarian Forest National Park with manually labeled reference data show that the trained function leads to high-quality segmentations. Our results indicate that the proposed data-driven approach can be a successful alternative to time consuming trial-and-error or grid search methods of finding good feature weights for graph cut algorithms. Also, the methodology can be generalized to other applications of graph cut clustering in remote sensing.

Summary
Detection of fallen trees in ALS point clouds by learning the Normalized Cut similarity function from simulated samples

 

Click To View

Additional Books


  • A Man-portable, Imu-free Mobile Mapping ... (by )
  • A Fast Matching Approach of Polygon Feat... (by )
  • The Impact of Varying Statutory Arrangem... (by )
  • High Resolution Deformation Time Series ... (by )
  • Measurement Precision and Accuracy of th... (by )
  • Object-based Image Analysis of Worldview... (by )
  • Evaluating the Potential of Multispectra... (by )
  • Geoarchaeological Site Documentation and... (by )
  • Incorporating Uncertanity Into Markov Ra... (by )
  • Comparative Study of Algorithms for Auto... (by )
  • Automatic Reconstruction of 3D Building ... (by )
  • Image Pre-processing for Optimizing Auto... (by )
Scroll Left
Scroll Right

 



Copyright © World Library Foundation. All rights reserved. eBooks from World Library are sponsored by the World Library Foundation,
a 501c(4) Member's Support Non-Profit Organization, and is NOT affiliated with any governmental agency or department.