World Library  


Add to Book Shelf
Flag as Inappropriate
Email this Book

Automatic Extraction of Insulators from 3D Lidar Data of an Electrical Substation : Volume Ii-5/W2, Issue 1 (16/10/2013)

By Arastounia, M.

Click here to view

Book Id: WPLBN0004014093
Format Type: PDF Article :
File Size: Pages 6
Reproduction Date: 2015

Title: Automatic Extraction of Insulators from 3D Lidar Data of an Electrical Substation : Volume Ii-5/W2, Issue 1 (16/10/2013)  
Author: Arastounia, M.
Volume: Vol. II-5/W2, Issue 1
Language: English
Subject: Science, Isprs, Annals
Collections: Periodicals: Journal and Magazine Collection, Copernicus GmbH
Historic
Publication Date:
2013
Publisher: Copernicus Gmbh, Göttingen, Germany
Member Page: Copernicus Publications

Citation

APA MLA Chicago

Lichti, D. D., & Arastounia, M. (2013). Automatic Extraction of Insulators from 3D Lidar Data of an Electrical Substation : Volume Ii-5/W2, Issue 1 (16/10/2013). Retrieved from http://www.ebooklibrary.org/


Description
Description: Department of Geomatics Eng, University of Calgary, Calgary, Canada. A considerable percentage of power outages are caused by animals that come into contact with conductive elements of electrical substations. These can be prevented by insulating conductive electrical objects, for which a 3D as-built plan of the substation is crucial. This research aims to create such a 3D as-built plan using terrestrial LiDAR data while in this paper the aim is to extract insulators, which are key objects in electrical substations. This paper proposes a segmentation method based on a new approach of finding the principle direction of points’ distribution. This is done by forming and analysing the distribution matrix whose elements are the range of points in 9 different directions in 3D space. Comparison of the computational performance of our method with PCA (principal component analysis) shows that our approach is 25% faster since it utilizes zero-order moments while PCA computes the first- and second-order moments, which is more time-consuming. A knowledge-based approach has been developed to automatically recognize points on insulators. The method utilizes known insulator properties such as diameter and the number and the spacing of their rings. The results achieved indicate that 24 out of 27 insulators could be recognized while the 3 un-recognized ones were highly occluded. Check point analysis was performed by manually cropping all points on insulators. The results of check point analysis show that the accuracy, precision and recall of insulator recognition are 98%, 86% and 81%, respectively. It is concluded that automatic object extraction from electrical substations using only LiDAR data is not only possible but also promising. Moreover, our developed approach to determine the directional distribution of points is computationally more efficient for segmentation of objects in electrical substations compared to PCA. Finally our knowledge-based method is promising to recognize points on electrical objects as it was successfully applied for insulators.

Summary
Automatic extraction of insulators from 3D LiDAR data of an electrical substation

 

Click To View

Additional Books


  • Qtrajectories: Improving the Quality of ... (by )
  • Discrimination of Urban Settlement Types... (by )
  • Land Use / Cover Change and Vulnerabilit... (by )
  • Effects of Building Primitive Library an... (by )
  • Development of a Flexible Higher Educati... (by )
  • Change Detection in Land-use and Land-co... (by )
  • Hyperspectral Dimension Reduction Using ... (by )
  • Wuda Geoinformatics Co., Ltd. (Geostar) ... 
  • Automatic Classification of Trees from L... (by )
  • Evaluating the Potential of Multispectra... (by )
  • Uav Platforms for Cultural Heritage Surv... (by )
  • Realtime Image Matching for Vision Based... (by )
Scroll Left
Scroll Right

 



Copyright © World Library Foundation. All rights reserved. eBooks from World eBook 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.