In this paper the FOI temporal analysis method is presented and tested on images randomly chosen from a diurnal sequence. The method integrates data collection, both sensor images and weather, as well as modelling, with the signal processing detection methods. The detection methods presented show that mines can be detected using optical methods, even when the image sequence show very little contrast. Increasing the number of data collection times affects the detection rate and false alarm rate in a positive way. The result from the test with randomly chosen images show performance better than random for all of the tested cases, excellent for some cases. Using prior knowledge in the choice of time of data collection, the result from testing the method on real mine field data shows interesting result.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Temporal analysis for land mine detection


    Contributors:
    Linderhead, A. (author) / Sjokvist, S. (author) / Nyberg, S. (author) / Uppsall, M. (author) / Gronwall, C. (author) / Andersson, P. (author) / Letalick, D. (author)


    Publication date :

    2005


    Size :

    6 Seiten, 18 Quellen



    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Fuzzy clustering for land mine detection

    Frigui, H. / Gader, P. / Keller, J. | Tema Archive | 1998


    Multispectral image feature selection for land mine detection

    Clark, G.A. / Sengupta, S.K. / Aimonetti, W.D. et al. | Tema Archive | 2000



    Land mine detection measurements using acoustic-to-seismic coupling

    Ning Xiang / Sabatier, J.M. | Tema Archive | 2000


    Land mine detection with an ultra-wideband SAR system

    Andrieu, J. / Gallais, F. / Mallepeyre, V. et al. | Tema Archive | 2002