Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images

This paper presents a novel approach to detect the buildings by automization of the training area collecting stage for supervised classification. The method based on the fact that a 3d building structure should cast a shadow under suitable imaging conditions. Therefore, the methodology begins with t...

Full description

Bibliographic Details
Main Author: S. Ghaffarian
Format: Article
Language:English
Published: Copernicus Publications 2014-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-3/101/2014/isprsarchives-XL-3-101-2014.pdf
id doaj-8e392aafb4d84e6697eec33841352521
record_format Article
spelling doaj-8e392aafb4d84e6697eec338413525212020-11-25T00:40:19ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342014-08-01XL-310110610.5194/isprsarchives-XL-3-101-2014Automatic Building Detection based on Supervised Classification using High Resolution Google Earth ImagesS. Ghaffarian0S. Ghaffarian1Department of Geomatics Engineering, Hacettepe University, Ankara, TurkeyDepartment of Geomatics Engineering, Hacettepe University, Ankara, TurkeyThis paper presents a novel approach to detect the buildings by automization of the training area collecting stage for supervised classification. The method based on the fact that a 3d building structure should cast a shadow under suitable imaging conditions. Therefore, the methodology begins with the detection and masking out the shadow areas using luminance component of the LAB color space, which indicates the lightness of the image, and a novel double thresholding technique. Further, the training areas for supervised classification are selected by automatically determining a buffer zone on each building whose shadow is detected by using the shadow shape and the sun illumination direction. Thereafter, by calculating the statistic values of each buffer zone which is collected from the building areas the Improved Parallelepiped Supervised Classification is executed to detect the buildings. Standard deviation thresholding applied to the Parallelepiped classification method to improve its accuracy. Finally, simple morphological operations conducted for releasing the noises and increasing the accuracy of the results. The experiments were performed on set of high resolution Google Earth images. The performance of the proposed approach was assessed by comparing the results of the proposed approach with the reference data by using well-known quality measurements (Precision, Recall and F1-score) to evaluate the pixel-based and object-based performances of the proposed approach. Evaluation of the results illustrates that buildings detected from dense and suburban districts with divers characteristics and color combinations using our proposed method have 88.4 % and 853 % overall pixel-based and object-based precision performances, respectively.http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-3/101/2014/isprsarchives-XL-3-101-2014.pdf
collection DOAJ
language English
format Article
sources DOAJ
author S. Ghaffarian
S. Ghaffarian
spellingShingle S. Ghaffarian
S. Ghaffarian
Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet S. Ghaffarian
S. Ghaffarian
author_sort S. Ghaffarian
title Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images
title_short Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images
title_full Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images
title_fullStr Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images
title_full_unstemmed Automatic Building Detection based on Supervised Classification using High Resolution Google Earth Images
title_sort automatic building detection based on supervised classification using high resolution google earth images
publisher Copernicus Publications
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 1682-1750
2194-9034
publishDate 2014-08-01
description This paper presents a novel approach to detect the buildings by automization of the training area collecting stage for supervised classification. The method based on the fact that a 3d building structure should cast a shadow under suitable imaging conditions. Therefore, the methodology begins with the detection and masking out the shadow areas using luminance component of the LAB color space, which indicates the lightness of the image, and a novel double thresholding technique. Further, the training areas for supervised classification are selected by automatically determining a buffer zone on each building whose shadow is detected by using the shadow shape and the sun illumination direction. Thereafter, by calculating the statistic values of each buffer zone which is collected from the building areas the Improved Parallelepiped Supervised Classification is executed to detect the buildings. Standard deviation thresholding applied to the Parallelepiped classification method to improve its accuracy. Finally, simple morphological operations conducted for releasing the noises and increasing the accuracy of the results. The experiments were performed on set of high resolution Google Earth images. The performance of the proposed approach was assessed by comparing the results of the proposed approach with the reference data by using well-known quality measurements (Precision, Recall and F1-score) to evaluate the pixel-based and object-based performances of the proposed approach. Evaluation of the results illustrates that buildings detected from dense and suburban districts with divers characteristics and color combinations using our proposed method have 88.4 % and 853 % overall pixel-based and object-based precision performances, respectively.
url http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-3/101/2014/isprsarchives-XL-3-101-2014.pdf
work_keys_str_mv AT sghaffarian automaticbuildingdetectionbasedonsupervisedclassificationusinghighresolutiongoogleearthimages
AT sghaffarian automaticbuildingdetectionbasedonsupervisedclassificationusinghighresolutiongoogleearthimages
_version_ 1725290933627387904