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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning to Detect Small Impact Craters


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


    Publication date :

    2005-01-01


    Size :

    497908 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Impact Craters

    Smith, Ronan / Eistrup, Christian | DataCite | 2021

    Free access

    Lunar Impact Craters

    P. D. Lowman | NTIS | 1964


    Lunar impact craters

    Lowman, P. D., Jr. | NTRS | 1964


    Impact Craters on Martian Volcanoes

    Mouginis-Mark, P. J. / Lunar and Planetary Institute| National Aeronautics and Space Administration| Universities Space Research Association | British Library Conference Proceedings | 1994


    Comet craters versus asteroid craters

    Bailey, M.E. | Elsevier | 1991