Title :
Automated tracking of ice floes: a stochastic approach
Author_Institution :
Dept. of Math. Sci., Montana State Univ., Bozeman, MT, USA
fDate :
11/1/1991 12:00:00 AM
Abstract :
A method for tracking ice floes in sequential satellite imagery is presented. The approach, based on probability distributions, directly incorporates the spatial information about feature locations into the estimation procedure. Given an image taken at time t0, a probability model is used to determine how features in the image will appear at time t1, and the probability distribution is used to identify features common to both images. The use of a probability model provides a means to measure the goodness of fit of the resulting matches. The features used are the outlines of sea ice floes observed in SAR (synthetic aperture radar) images, although the method can be applied to any set of features. The floe outlines are found using an erosion-propagation algorithm which combines erosion from mathematical morphology with local propagation of information about floe edges
Keywords :
computerised pattern recognition; geophysics computing; oceanographic techniques; remote sensing by radar; sea ice; tracking; automated tracking; erosion-propagation algorithm; estimation procedure; feature locations; goodness of fit; ice floes; probability distributions; remote sensing; satellite imagery; sea ice; spatial information; stochastic approach; synthetic aperture radar; Data mining; Displacement measurement; Mechanical variables measurement; Morphology; Probability distribution; Radar tracking; Satellites; Sea ice; Sea measurements; Shape; Stochastic processes; Synthetic aperture radar;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on