Master's Research


Research Statement

Segmentation and Compression of SAR Imagery Via Hierarchical Modeling

There has recently been a growing interest in Synthetic Aperture Radar (SAR) imaging on account of its importance in a variety of applications. One reason for its gain in popularity is its ability to image terrain at extraordinary rates. Acquiring data at such rates, however, has drawbacks in the form of exorbitant costs in data storage and transmission over relatively slow channels. To alleviate these and related costs, we are developing a segmentation driven compression technique using hierarchical stochastic modeling within a multiscale framework. Our approach to SAR image compression is unique in that we exploit the multiscale stochastic structure inherent in SAR imagery. This structure is well captured by a set of scale auto-regressive (AR) models that accurately characterize the evolution in scale of homogeneous regions for different classes of terrain. We thus associate with each major classification of terrain, a predetermined AR model reflecting the terrain's evolution in scale. A segmentation of SAR imagery is then generated by using a statistical test to compare the local scale evolution behavior within an image to the predefined AR models. The segmentation is subsequently used in tandem with the corresponding models in a pyramid encoder to provide a robust spatially adaptive compression technique that hierarchically encodes both the segmentation and the image.


Related Publications:

A. J. Kim and "Hierarchical Stochastic Modeling of SAR Imagery for Segmentation/Compression" IEEE Transactions on Signal Processing, vol. 47, no. 2, Feb. 1999, pp. 458-468.

A. J. Kim, and "Segmentation and Compression of SAR Imagery via Hierarchical Stochastic Modeling" 1997 International Conference on Image Processing (ICIP '97), October 1997, Santa Barbara, Ca.

A. J. Kim, "Hierarchical Stochastic Modeling for Multiscale Segmentation and Compression of SAR Imagery" (ps) (pdf), M.I.T. Master's Thesis , June 1997.

A. J. Kim, and "Segmentation Directed SAR Image Compression via Hierarchical Stochastic Modeling", Proc. of the SPIE: Wavelet Applications IV , Aerosense, April 1997, Orlando, Fla.



Last modified: 1/27/99.

This page was meant to be to be viewed in a framed environment. If this is not the case (perhaps you accessed it via a search engine), click here to go to my main page.