Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance

D. Chaudhuri, N. K. Kushwaha, Ashok K Samal, R. C. Agarwal

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

Automatic building extraction remains an open research topic in digital photogrammetry and remote sensing. While many algorithms have been proposed for building extraction, none of them solve the problem completely. This is even a greater challenge in urban areas, due to high-object density and scene complexity. Standard approaches do not achieve satisfactory performance, especially with high-resolution satellite images. This paper presents a novel framework for reliable and accurate building extraction from high-resolution panchromatic images. Proposed framework exploits the domain knowledge (spatial and spectral properties) about the nature of objects in the scene, their optical interactions and their impact on the resulting image. The steps in the approach consist of 1) directional morphological enhancement; 2) multiseed-based clustering technique using internal gray variance (IGV); 3) shadow detection; 4) false alarm reduction using positional information of both building edge and shadow; and 5) adaptive threshold based segmentation technique. We have evaluated the algorithm using a variety of images from IKONOS and QuickBird satellites. The results demonstrate that the proposed algorithm is both accurate and efficient.

Original languageEnglish (US)
Article number7122242
Pages (from-to)1767-1779
Number of pages13
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume9
Issue number5
DOIs
StatePublished - May 1 2016

Fingerprint

Satellites
digital photogrammetry
panchromatic image
IKONOS
QuickBird
Photogrammetry
Image resolution
segmentation
Remote sensing
urban area
remote sensing
satellite image
detection
alarm

Keywords

  • Index Terms-Building detection
  • clustering
  • enhancement
  • feature extraction
  • high resolution
  • morphology
  • remote sensing
  • segmentation
  • thinning

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Atmospheric Science

Cite this

Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance. / Chaudhuri, D.; Kushwaha, N. K.; Samal, Ashok K; Agarwal, R. C.

In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 9, No. 5, 7122242, 01.05.2016, p. 1767-1779.

Research output: Contribution to journalArticle

@article{a200f2c77ff04d3ba8531da707a26923,
title = "Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance",
abstract = "Automatic building extraction remains an open research topic in digital photogrammetry and remote sensing. While many algorithms have been proposed for building extraction, none of them solve the problem completely. This is even a greater challenge in urban areas, due to high-object density and scene complexity. Standard approaches do not achieve satisfactory performance, especially with high-resolution satellite images. This paper presents a novel framework for reliable and accurate building extraction from high-resolution panchromatic images. Proposed framework exploits the domain knowledge (spatial and spectral properties) about the nature of objects in the scene, their optical interactions and their impact on the resulting image. The steps in the approach consist of 1) directional morphological enhancement; 2) multiseed-based clustering technique using internal gray variance (IGV); 3) shadow detection; 4) false alarm reduction using positional information of both building edge and shadow; and 5) adaptive threshold based segmentation technique. We have evaluated the algorithm using a variety of images from IKONOS and QuickBird satellites. The results demonstrate that the proposed algorithm is both accurate and efficient.",
keywords = "Index Terms-Building detection, clustering, enhancement, feature extraction, high resolution, morphology, remote sensing, segmentation, thinning",
author = "D. Chaudhuri and Kushwaha, {N. K.} and Samal, {Ashok K} and Agarwal, {R. C.}",
year = "2016",
month = "5",
day = "1",
doi = "10.1109/JSTARS.2015.2425655",
language = "English (US)",
volume = "9",
pages = "1767--1779",
journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
issn = "1939-1404",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance

AU - Chaudhuri, D.

AU - Kushwaha, N. K.

AU - Samal, Ashok K

AU - Agarwal, R. C.

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Automatic building extraction remains an open research topic in digital photogrammetry and remote sensing. While many algorithms have been proposed for building extraction, none of them solve the problem completely. This is even a greater challenge in urban areas, due to high-object density and scene complexity. Standard approaches do not achieve satisfactory performance, especially with high-resolution satellite images. This paper presents a novel framework for reliable and accurate building extraction from high-resolution panchromatic images. Proposed framework exploits the domain knowledge (spatial and spectral properties) about the nature of objects in the scene, their optical interactions and their impact on the resulting image. The steps in the approach consist of 1) directional morphological enhancement; 2) multiseed-based clustering technique using internal gray variance (IGV); 3) shadow detection; 4) false alarm reduction using positional information of both building edge and shadow; and 5) adaptive threshold based segmentation technique. We have evaluated the algorithm using a variety of images from IKONOS and QuickBird satellites. The results demonstrate that the proposed algorithm is both accurate and efficient.

AB - Automatic building extraction remains an open research topic in digital photogrammetry and remote sensing. While many algorithms have been proposed for building extraction, none of them solve the problem completely. This is even a greater challenge in urban areas, due to high-object density and scene complexity. Standard approaches do not achieve satisfactory performance, especially with high-resolution satellite images. This paper presents a novel framework for reliable and accurate building extraction from high-resolution panchromatic images. Proposed framework exploits the domain knowledge (spatial and spectral properties) about the nature of objects in the scene, their optical interactions and their impact on the resulting image. The steps in the approach consist of 1) directional morphological enhancement; 2) multiseed-based clustering technique using internal gray variance (IGV); 3) shadow detection; 4) false alarm reduction using positional information of both building edge and shadow; and 5) adaptive threshold based segmentation technique. We have evaluated the algorithm using a variety of images from IKONOS and QuickBird satellites. The results demonstrate that the proposed algorithm is both accurate and efficient.

KW - Index Terms-Building detection

KW - clustering

KW - enhancement

KW - feature extraction

KW - high resolution

KW - morphology

KW - remote sensing

KW - segmentation

KW - thinning

UR - http://www.scopus.com/inward/record.url?scp=84933558112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933558112&partnerID=8YFLogxK

U2 - 10.1109/JSTARS.2015.2425655

DO - 10.1109/JSTARS.2015.2425655

M3 - Article

VL - 9

SP - 1767

EP - 1779

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

IS - 5

M1 - 7122242

ER -