Curtin University Homepage
  • Library
  • Help
    • Admin

    espace - Curtin’s institutional repository

    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item
    • espace Home
    • espace
    • Curtin Research Publications
    • View Item

    Classification and representation of commonly used roofing material using multisensorial aerial data

    Access Status
    Fulltext not available
    Authors
    Ilehag, R.
    Bulatov, D.
    Helmholz, Petra
    Belton, David
    Date
    2018
    Type
    Conference Paper
    
    Metadata
    Show full item record
    Citation
    Ilehag, R. and Bulatov, D. and Helmholz, P. and Belton, D. 2018. Classification and representation of commonly used roofing material using multisensorial aerial data, pp. 217-224.
    Source Title
    International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
    DOI
    10.5194/isprs-archives-XLII-1-217-2018
    ISSN
    1682-1750
    School
    School of Earth and Planetary Sciences (EPS)
    URI
    http://hdl.handle.net/20.500.11937/71594
    Collection
    • Curtin Research Publications
    Abstract

    © Authors 2018. CC BY 4.0 License. As more cities are starting to experience the urban heat islands effect, knowledge about the energy emitted from building roofs is of primary importance. Since this energy depends both on roof orientations and materials, we tackled both issues by analysing sensor data from multispectral, thermal infrared, high-resolution RGB, and airborne laser datasets (each with different spatial resolutions) of a council in Perth, Australia. To localise the roofs, we acquired building outlines that had to be updated using the normalised digital surface model, the NDVI and the planarity. Then, we computed a semantic 3D model of the study area, with roof detail analysis being a particular focus. The main objective of this study, however, was to classify three commonly used roofing materials: Cement tiles, Colorbond and Zincalume by combining the multispectral and thermal infrared image bands while the high-resolution RGB dataset was used to provide additional information about the roof texture. Three types of image segmentation approaches were evaluated to assess any differences while performing the material classification; pixel-wise, superpixel-wise and building-wise image segmentation. Due to the limited amount of labelled data, we extended the dataset by labelling data ourselves and merged Colorbond and Zincalume into one separate class. The supervised classifier Random Forest was applied to all reasonable configurations of segmentation kinds, numbers of classes, and finally, keeping track of the added value of principal component analysis.

    Related items

    Showing items related by title, author, creator and subject.

    • Evaluation of monorail haulage systems in metalliferous underground mining
      Besa, Bunda (2010)
      The decline is a major excavation in metalliferous mining since it provides the main means of access to the underground and serves as a haulage route for underground trucks. However, conventional mining of the decline to ...
    • Research into stope roof control of compound roof by solid backfilling mining
      Gao, R.; Zhang, J.; Spearing, Sam; Li, M.; An, B.; Hao, D. (2015)
      Based on the analysis of the failure characteristics and backfilling effect of the compound roof at 1801 backfilling workface in Taiyuan coal mine, China, we propose a method of controlling the pre-subsidence of a compound ...
    • An insight into the commercial viability of green roofs in Australia
      Tassicker, N.; Rahnamayiezekavat, Payam; Sutrisna, Monty (2016)
      Construction industries around the world have, in recent history, become increasingly concerned with the sustainability of building practices. Inherently, the development of the built environment results in partial or ...
    Advanced search

    Browse

    Communities & CollectionsIssue DateAuthorTitleSubjectDocument TypeThis CollectionIssue DateAuthorTitleSubjectDocument Type

    My Account

    Admin

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Follow Curtin

    • 
    • 
    • 
    • 
    • 

    CRICOS Provider Code: 00301JABN: 99 143 842 569TEQSA: PRV12158

    Copyright | Disclaimer | Privacy statement | Accessibility

    Curtin University would like to pay our respect to the indigenous members of our community by acknowledging the traditional owners of the land on which the Perth Campus is located, the Wadjuk people of the Nyungar Nation; and on our Kalgoorlie Campus, the Wongutha people of the North-Eastern Goldfields.
    Watch our traditional Aboriginal welcome