An algorithm of LiDAR building outline extraction by Delaunay triangle

2016 ◽  
Author(s):  
Nie Yu-ze ◽  
Cheng Ying-lei ◽  
Qiu Lang-bo ◽  
He Man-yun ◽  
Zhao Zi-hao ◽  
...  
Keyword(s):  
Delaunay Triangle ◽  
Outline Extraction

A New Approach for Fatigue Damage Modeling of Subsurface-Initiated Spalling in Large Rolling Contacts

2016 ◽  
Vol 139 (1) ◽  
Author(s):  
Aditya A. Walvekar ◽  
Neil Paulson ◽  
Farshid Sadeghi ◽  
Nick Weinzapfel ◽  
Martin Correns ◽  
...  
Keyword(s):  
Fatigue Damage ◽  
Damage Mechanics ◽  
Numerical Models ◽  
Rolling Contact ◽  
Fe Model ◽  
Triangle Mesh ◽  
Computationally Efficient ◽  
New Approach ◽  
Rolling Contacts ◽  
Delaunay Triangle

Large bearings employed in wind turbine applications have half-contact widths that are usually greater than 1 mm. Previous numerical models developed to investigate rolling contact fatigue (RCF) require significant computational effort to study large rolling contacts. This work presents a new computationally efficient approach to investigate RCF life scatter and spall formation in large bearings. The modeling approach incorporates damage mechanics constitutive relations in the finite element (FE) model to capture fatigue damage. It utilizes Voronoi tessellation to account for variability occurring due to the randomness in the material microstructure. However, to make the model computationally efficient, a Delaunay triangle mesh was used in the FE model to compute stresses during a rolling contact pass. The stresses were then mapped onto the Voronoi domain to evaluate the fatigue damage that leads to the formation of surface spall. The Delaunay triangle mesh was dynamically refined around the damaged elements to capture the stress concentration accurately. The new approach was validated against previous numerical model for small rolling contacts. The scatter in the RCF lives and the progression of fatigue spalling for large bearings obtained from the model show good agreement with experimental results available in the open literature. The ratio of L10 lives for different sized bearings computed from the model correlates well with the formula derived from the basic life rating for radial roller bearing as per ISO 281. The model was then extended to study the effect of initial internal voids on RCF life. It was found that for the same initial void density, the L10 life decreases with the increase in the bearing size.

Generating cancellable fingerprint templates based on Delaunay triangle feature set construction

2016 ◽  
Vol 5 (2) ◽  
pp. 131-139 ◽  
Author(s):  
Mulagala Sandhya ◽  
Munaga V.N.K. Prasad ◽  
Raghavendra Rao Chillarige
Keyword(s):  
Delaunay Triangle

E05 Self-positioning Specification System using the Satellite Tracking and Outline Extraction

2014 ◽  
Vol 2014.23 (0) ◽  
pp. _E05-1_-_E05-5_
Author(s):  
Kouji Nunomura ◽  
Chiharu Niwa ◽  
Kentarou Suda ◽  
Nobuto Hirakoso
Keyword(s):  
Satellite Tracking ◽  
Outline Extraction

scholarly journals A Boundary Regulated Network for Accurate Roof Segmentation and Outline Extraction

2018 ◽  
Vol 10 (8) ◽  
pp. 1195 ◽  
Author(s):  
Guangming Wu ◽  
Zhiling Guo ◽  
Xiaodan Shi ◽  
Qi Chen ◽  
Yongwei Xu ◽  
...  
Keyword(s):  
Model Performance ◽  
Feature Representation ◽  
Superior Performance ◽  
Aerial Image ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Net Method ◽  
Automatic Mapping ◽  
Outline Extraction ◽  
Improved Model

The automatic extraction of building outlines from aerial imagery for the purposes of navigation and urban planning is a long-standing problem in the field of remote sensing. Currently, most methods utilize variants of fully convolutional networks (FCNs), which have significantly improved model performance for this task. However, pursuing more accurate segmentation results is still critical for additional applications, such as automatic mapping and building change detection. In this study, we propose a boundary regulated network called BR-Net, which utilizes both local and global information, to perform roof segmentation and outline extraction. The BR-Net method consists of a shared backend utilizing a modified U-Net and a multitask framework to generate predictions for segmentation maps and building outlines based on a consistent feature representation from the shared backend. Because of the restriction and regulation of additional boundary information, the proposed model can achieve superior performance compared to existing methods. Experiments on an aerial image dataset covering 32 km2 and containing more than 58,000 buildings indicate that our method performs well at both roof segmentation and outline extraction. The proposed BR-Net method significantly outperforms the classic FCN8s model. Compared to the state-of-the-art U-Net model, our BR-Net achieves 6.2% (0.869 vs. 0.818), 10.6% (0.772 vs. 0.698), and 8.7% (0.840 vs. 0.773) improvements in F1 score, Jaccard index, and kappa coefficient, respectively.

scholarly journals Comprehensive approach for building outline extraction from LiDAR data with accent to a sparse laser scanning point cloud

2017 ◽  
Vol 16 (1) ◽  
pp. 91-102 ◽  
Author(s):  
Petr Hofman ◽  
Markéta Potůčková
Keyword(s):  
Urban Areas ◽  
Point Cloud ◽  
Laser Scanning ◽  
Normal Vector ◽  
Test Dataset ◽  
Roof Structure ◽  
Airborne Laser ◽  
Least Squares Adjustment ◽  
Outline Extraction ◽  
Normal Vectors

<em>The method of building outline extraction based on segmentation of airborne laser scanning data is proposed and tested on a dataset comprising 1,400 buildings typical for residential and industrial urban areas. The algorithm starts with setting a special threshold to separate building from bare earth points and low objects. Next, local planes are fitted to each point using RANSAC and further refined by least squares adjustment. A normal vector is assigned to each point. Similarities among normal vectors are evaluated in order to assemble planar or curved roof segments. Finally, building outlines are formed from detected segments using the a-shapes algorithm and further regularized. The extracted outlines were compared with reference polygons manually derived from the processed laser scanning point cloud and orthoimages. Area-based evaluation of accuracy of the proposed method revealed completeness and correctness of 87 % and 97 %, respectively, for the test dataset. The influence of parameters like number of points per roof segment, complexity of the roof structure, roof type, and overlap with vegetation on accuracy was evaluated and discussed.</em>

Sign in / Sign up

Export Citation Format

Share Document