A method for unsupervised change detection and automatic radiometric normalization in multispectral data

Allan Aasbjerg Nielsen, Morton John Canty

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    364 Downloads (Pure)

    Abstract

    Based on canonical correlation analysis the iteratively re-weighted multivariate alteration detection (MAD) method is used to successfully perform unsupervised change detection in bi-temporal Landsat ETM+ images covering an area with villages, woods, agricultural fields and open pit mines in North Rhine- Westphalia, Germany. A link to an example with ASTER data to detect change with the same method after the 2005 Kashmir earthquake is given. The method is also used to automatically normalize multitemporal, multispectral Landsat ETM+ data radiometrically. IDL/ENVI, Python and Matlab software to carry out the analyses is available from the authors' websites.
    Original languageEnglish
    Title of host publication34th International Symposium on Remote Sensing of Environment : The GEOSS Era: Towards Operational Environmental Monitoring
    Number of pages4
    PublisherInternational Society for Photogrammetry and Remote Sensing
    Publication date2011
    Publication statusPublished - 2011
    Event34th International Symposium on Remote Sensing of Environment (ISRSE2011) - Sydney Convention & Exhibition Centre , Sydney, Australia
    Duration: 10 Apr 201115 Apr 2011
    Conference number: 34

    Conference

    Conference34th International Symposium on Remote Sensing of Environment (ISRSE2011)
    Number34
    LocationSydney Convention & Exhibition Centre
    Country/TerritoryAustralia
    CitySydney
    Period10/04/201115/04/2011

    Keywords

    • Computer software
    • Environmental engineering
    • MATLAB
    • Remote sensing
    • Signal detection
    • Iterative methods

    Fingerprint

    Dive into the research topics of 'A method for unsupervised change detection and automatic radiometric normalization in multispectral data'. Together they form a unique fingerprint.

    Cite this