Automatic rooftop detection using a two-stage classification

Bikash Joshi, Hayk Baluyan, Amer Al Hinai, Wei Lee Woon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper presents a novel application of machine learning techniques to the automatic detection of building rooftops in satellite images. The image is first segmented into homogeneous regions using the k-means algorithm. These segments are then treated as candidate rooftop regions which are presented to a novel two-stage classification process; features are extracted from each segment and submitted to an ANN which serves as the first stage of the classification procedure. New features are then extracted from the outputs of the ANN and these are presented to an SVM which then performs the second classification pass. In this way, the first classification stage acts as a preprocessing step which, when processed by the SVM significantly reduces the number of false-positives. To establish the efficacy of the proposed method, its results are compared with those obtained using an alternative approach.

Original languageEnglish
Title of host publicationProceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages286-291
Number of pages6
ISBN (Electronic)9781479949236
DOIs
Publication statusPublished - 2014
Event16th UKSim-AMSS International Conference on Computer Modelling and Simulation, UKSim 2014 - Cambridge, United Kingdom
Duration: Mar 26 2014Mar 28 2014

Other

Other16th UKSim-AMSS International Conference on Computer Modelling and Simulation, UKSim 2014
CountryUnited Kingdom
CityCambridge
Period3/26/143/28/14

Fingerprint

K-means Algorithm
Satellite Images
False Positive
Preprocessing
Learning systems
Efficacy
Machine Learning
Satellites
Output
Alternatives

Keywords

  • Artificial neural network
  • Computer vision
  • Image segmentation
  • Machine learning
  • Rooftop detection
  • Support vector machine

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Applied Mathematics
  • Modelling and Simulation

Cite this

Joshi, B., Baluyan, H., Al Hinai, A., & Woon, W. L. (2014). Automatic rooftop detection using a two-stage classification. In Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014 (pp. 286-291). [7046079] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UKSim.2014.89

Automatic rooftop detection using a two-stage classification. / Joshi, Bikash; Baluyan, Hayk; Al Hinai, Amer; Woon, Wei Lee.

Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 286-291 7046079.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Joshi, B, Baluyan, H, Al Hinai, A & Woon, WL 2014, Automatic rooftop detection using a two-stage classification. in Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014., 7046079, Institute of Electrical and Electronics Engineers Inc., pp. 286-291, 16th UKSim-AMSS International Conference on Computer Modelling and Simulation, UKSim 2014, Cambridge, United Kingdom, 3/26/14. https://doi.org/10.1109/UKSim.2014.89
Joshi B, Baluyan H, Al Hinai A, Woon WL. Automatic rooftop detection using a two-stage classification. In Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 286-291. 7046079 https://doi.org/10.1109/UKSim.2014.89
Joshi, Bikash ; Baluyan, Hayk ; Al Hinai, Amer ; Woon, Wei Lee. / Automatic rooftop detection using a two-stage classification. Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 286-291
@inproceedings{7b464f11ff7f4371a2673c3f8a46d1ef,
title = "Automatic rooftop detection using a two-stage classification",
abstract = "This paper presents a novel application of machine learning techniques to the automatic detection of building rooftops in satellite images. The image is first segmented into homogeneous regions using the k-means algorithm. These segments are then treated as candidate rooftop regions which are presented to a novel two-stage classification process; features are extracted from each segment and submitted to an ANN which serves as the first stage of the classification procedure. New features are then extracted from the outputs of the ANN and these are presented to an SVM which then performs the second classification pass. In this way, the first classification stage acts as a preprocessing step which, when processed by the SVM significantly reduces the number of false-positives. To establish the efficacy of the proposed method, its results are compared with those obtained using an alternative approach.",
keywords = "Artificial neural network, Computer vision, Image segmentation, Machine learning, Rooftop detection, Support vector machine",
author = "Bikash Joshi and Hayk Baluyan and {Al Hinai}, Amer and Woon, {Wei Lee}",
year = "2014",
doi = "10.1109/UKSim.2014.89",
language = "English",
pages = "286--291",
booktitle = "Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Automatic rooftop detection using a two-stage classification

AU - Joshi, Bikash

AU - Baluyan, Hayk

AU - Al Hinai, Amer

AU - Woon, Wei Lee

PY - 2014

Y1 - 2014

N2 - This paper presents a novel application of machine learning techniques to the automatic detection of building rooftops in satellite images. The image is first segmented into homogeneous regions using the k-means algorithm. These segments are then treated as candidate rooftop regions which are presented to a novel two-stage classification process; features are extracted from each segment and submitted to an ANN which serves as the first stage of the classification procedure. New features are then extracted from the outputs of the ANN and these are presented to an SVM which then performs the second classification pass. In this way, the first classification stage acts as a preprocessing step which, when processed by the SVM significantly reduces the number of false-positives. To establish the efficacy of the proposed method, its results are compared with those obtained using an alternative approach.

AB - This paper presents a novel application of machine learning techniques to the automatic detection of building rooftops in satellite images. The image is first segmented into homogeneous regions using the k-means algorithm. These segments are then treated as candidate rooftop regions which are presented to a novel two-stage classification process; features are extracted from each segment and submitted to an ANN which serves as the first stage of the classification procedure. New features are then extracted from the outputs of the ANN and these are presented to an SVM which then performs the second classification pass. In this way, the first classification stage acts as a preprocessing step which, when processed by the SVM significantly reduces the number of false-positives. To establish the efficacy of the proposed method, its results are compared with those obtained using an alternative approach.

KW - Artificial neural network

KW - Computer vision

KW - Image segmentation

KW - Machine learning

KW - Rooftop detection

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84926681766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926681766&partnerID=8YFLogxK

U2 - 10.1109/UKSim.2014.89

DO - 10.1109/UKSim.2014.89

M3 - Conference contribution

SP - 286

EP - 291

BT - Proceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -