Computer vision for polar science

Students: Jerome Mitchell, Stefan Lee
Faculty: David J. Crandall, Geoffrey C. Fox, John D. Paden

Ground-penetrating radar systems are useful for a variety scientific studies, including monitoring changes to the polar ice sheets that may give clues to climate change. These systems produce vast amounts of radar image data that is typically processed by hand, because the echograms are noisy and difficult to interpret. We are investigating and developing computer vision techniques for analyzing this data, using probabilistic graphical models that can explicitly model the uncertainty and noise in the data. Our techniques are fast (typically milliseconds to seconds per image), and can incorporate a variety of diverse evidence including feedback from a human operator, or measurements from ice cores. We quantitatively evaluate our approaches on large-scale test data, typically including hundreds of echograms and comparing to human-labeled ground truth.




Papers and presentations

BibTeX entries:

    title = {Automatic estimation of ice bottom surfaces from radar imagery},
    year = {2017},
    booktitle = {IEEE International Conference on Image Processing (ICIP)},
    author = {Mingze Xu and David J. Crandall and Geoffrey C. Fox and John D. Paden}

    author = {Stefan Lee and Jerome Mitchell and David Crandall and Geoffrey C. Fox},
    title = {Estimating Bedrock and Surface Layer Boundaries and Confidence Intervals in Ice Sheet Radar Imagery using {MCMC}},
    booktitle = {IEEE International Conference on Image Processing (ICIP)},
    year = {2014}

    title = {Automatic Near Surface Estimation from Snow Radar Imagery},
    author = {Jerome E. Mitchell and David Crandall and Geoffrey Fox and John Paden},
    booktitle = {IEEE International Geoscience and Remote Sensing Symposium},
    year = {2013}

    author = {David Crandall and Geoffrey Fox and John Paden},
    title = {Layer-finding in radar echograms using probabilistic graphical models},
    booktitle = {IAPR International Conference on Pattern Recognition (ICPR)},
    year = {2012}


We gratefully acknowledge the support of the following:

National Science Foundation Lily Endowment
National Science
NASA IU Data to Insight Center IU Digital Science Center Lilly Endowment