Model-Based Recognition and Parameter Estimation of Buildings from Multi-View Aerial Imagery Using Multi-Segmentation

Lieuwe Jan Spreeuwers, Klamer Schutte, K. Schutte, Z. Houkes

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    54 Downloads (Pure)

    Abstract

    This paper describes a system for analysis of aerial images of urban areas using multiple images from different viewpoints. In this paper the emphasis is on the discussion of the experimental evaluation using segmented images obtained by applying 3 different parameters in the segmentation-process. The proposed approach combines bottom-up and top-down processing. To evaluate statistically the performance of the system, a set of 50 realisations of 5 images from different viewpoints was used, which was generated by combining real and ray-traced images. The experiments show a significant improvement of reliability and accuracy if multi-segmentation is used in multi-view imagery, instead of single-segmentation.
    Original languageUndefined
    Title of host publicationProceedings of ISPRS
    Place of PublicationStuttgart
    PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
    Pages169-174
    Number of pages6
    ISBN (Print)not assigned
    Publication statusPublished - 1997
    EventProceedings of ISPRS : Commission III/IV Workshop 1997 - Stuttgart, Germany
    Duration: 17 Sept 199719 Sept 1997

    Publication series

    NameInternational Archives of Photogrammetry and Remote Sensing
    PublisherISPRS
    Volume32

    Conference

    ConferenceProceedings of ISPRS : Commission III/IV Workshop 1997
    Period17/09/9719/09/97
    Other17-19 Sep 1997

    Keywords

    • EWI-14172
    • METIS-113177
    • IR-65124
    • SCS-Safety

    Cite this