Title: Vehicles Detection from Very High Resolution Satellite Imagery
Citation: International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences vol. XXXVI, PART 3/W24 p. 83-88
Publisher: Institute of Photogrammetry and Cartography, Technische Universitaet Muenchen
Publication Year: 2005
JRC N°: JRC30914
URI: http://publications.jrc.ec.europa.eu/repository/handle/JRC30914
Type: Articles in periodicals and books
Abstract: This paper evaluates an inductive learning approach classification technique for vehicle detection and enumeration on very high resolution imagery. It tests pre-processing procedures applied to different images with different atmospheric conditions and automatic detection algorithms for detection and enumeration. This work contributes to the longer term objective that is beyond the scope of this paper to use vehicles counts to derive indicators of societal activity; this for a number of applications including situation assessments in conflict areas. The work uses Ikonos and Quickbird images collected over Baghdad in pre-war situation and during the Iraq conflict of 2003. Very high resolution imagery is an excellent information source to detect vehicles. The enumeration can be carried out using photo-interpretation techniques. However, this is impractical and relatively expensive. Automatic detection is possible. Image pre-processing is needed.
JRC Directorate:Space, Security and Migration

Files in This Item:
There are no files associated with this item.

Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.