Machine learning techniques have shown considerable promise for visual inspection tasks such as locating human faces in cluttered scenes. In this paper, we examine the utility of such techniques for the scientifically-important problem of detecting and catloging impact craters in planetary images gathered by spacecraft. Various supervised learning algorithms, including ensemble methods (bagging and AdaBoost with feed-forward neural networks as base learners), support vector machines (SVM), and continuously-scalable template models (CSTM), are employed to derive crater detectors from ground-truthed images. The resulting detectors are evaluated on a challenging set of Viking Orbiter images of Mars containing roughly one thousand craters. The SVM approach with normalized image patches provides detection and localization performance closest to that of human labelers and is shown to be substantially superior to boundary-based approaches such as the Hough transform.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning to Detect Small Impact Craters


    Beteiligte:
    Wetzler, P. G. (Autor:in) / Honda, R. (Autor:in) / Enke, B. (Autor:in) / Merline, W. J. (Autor:in) / Chapman, C. R. (Autor:in) / Burl, M. C. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    497908 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Comet craters versus asteroid craters

    Bailey, M.E. | Elsevier | 1991


    Small Craters on the Meteoroid and Space Debris Impact Experiment

    Humes, D. H. / National Aeronautics and Space Administration / AIAA | British Library Conference Proceedings | 1995



    EXPERIMENTAL HYPERVELOCITY IMPACT CRATERS IN ROCK

    Gault, D. E. / Lung, R. V. / Moore, H. J. | NTRS | 1961


    Geology - Craters

    Morris, E. C. / Shoemaker, E. M. | NTRS | 1970