Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Calgary

$19,500.00

Object-oriented classification for urban mapping

EF 2007-08

Résumé
Reliable and up-to-date information on the rapid and frequent changes of urban environment are critical to many GIS applications such as urban planning and management, urban transportation, environmental impacts of fast urban sprawl or risk evaluation for insurance companies. The advent of high spatial and spectral resolution remote sensing imagery has proved to very useful in urban areas for the creation and updating of different types of maps. However the application of the conventional classification algorithms that rely on pixel-based processing methods encounters many difficulties in the extraction of land-cover/land-use information from high resolution images. Indeed urban environment is a highly heterogeneous environment made of very different objects but constructed with similar material, which renders the classification of urban land-cover/land-use categories a very complex procedure. Furthermore, high spatial resolution adjacent pixels are likely to belong to the same land cover/use category despite their different spectral characteristics. A new approach of object-oriented classification will be sought out to discriminate urban land-cover/land-use categories more accurately and efficiently. Object-oriented image processing uses not only the spectral properties of objects but also their different scales, shape, texture and other features to better discriminate them. By combining multiresolution segmentation and fuzzy logic classification, urban mapping can be done according to the resolution and the scale of the expected objects. The development of mature methodologies for automated urban classification and change detection based on imagery may provide a hopeful solution to the very challenging problem of reliable and up-to-date maps, so that an image-based updating system becomes operational.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
249692-2007
Name nom
Couloigner, Isabelle
Department département
Geomatics Engineering
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2007
Competition year année de concours
2007
Award amount
19500
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
6
Committee name en
Civil Engineering
Committee name fr
Génie civil
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
1004
Research subject group en
Civil engineering
Research subject group fr
Génie civil
Research subject en
Survey engineering and remote sensing
Research subject fr
Génie de l'arpentage et télédétection
Partie
1
Nb partie
5
Application title
Object-oriented classification for urban mapping
Keyword
NA
Application summary
Reliable and up-to-date information on the rapid and frequent changes of urban environment are critical to many GIS applications such as urban planning and management, urban transportation, environmental impacts of fast urban sprawl or risk evaluation for insurance companies. The advent of high spatial and spectral resolution remote sensing imagery has proved to very useful in urban areas for the creation and updating of different types of maps. However the application of the conventional classification algorithms that rely on pixel-based processing methods encounters many difficulties in the extraction of land-cover/land-use information from high resolution images. Indeed urban environment is a highly heterogeneous environment made of very different objects but constructed with similar material, which renders the classification of urban land-cover/land-use categories a very complex procedure. Furthermore, high spatial resolution adjacent pixels are likely to belong to the same land cover/use category despite their different spectral characteristics. A new approach of object-oriented classification will be sought out to discriminate urban land-cover/land-use categories more accurately and efficiently. Object-oriented image processing uses not only the spectral properties of objects but also their different scales, shape, texture and other features to better discriminate them. By combining multiresolution segmentation and fuzzy logic classification, urban mapping can be done according to the resolution and the scale of the expected objects. The development of mature methodologies for automated urban classification and change detection based on imagery may provide a hopeful solution to the very challenging problem of reliable and up-to-date maps, so that an image-based updating system becomes operational.