Evaluation of Feature-Extraction Algorithms by Genetic Programming

This paper describes a validation of accuracy associated with a recent algorithm that has been designed to extract ridge and rubble features from multiyear ice. Results show that the algorithm performs well with low-resolution ERS SAR data products. 1. INTRODUCTION Roughness in the polar ice cover--...

Full description

Bibliographic Details
Main Authors: Procedure The Image, Jason M. Daida, Robert G. Onstott, Tommaso F. Bersano-begey, Steven J. Ross, John F. Vesecky
Other Authors: The Pennsylvania State University CiteSeerX Archives
Format: Text
Language:English
Subjects:
Online Access:http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.544
Description
Summary:This paper describes a validation of accuracy associated with a recent algorithm that has been designed to extract ridge and rubble features from multiyear ice. Results show that the algorithm performs well with low-resolution ERS SAR data products. 1. INTRODUCTION Roughness in the polar ice cover---like meso-scale features of pressure ridges and rubble fields---is of significant geophysical interest. Pressure ridges and rubble fields help to transfer kinetic energy from meteorological systems to the ice cover. Pressure ridges can significantly increase sea-ice drag coefficients, which subsequently affect sea-ice movement and deformation. Ridges and rubble fields are also of interest because they account for a large portion of the total ice mass. In ERS synthetic aperture radar (SAR) imagery, pressure ridges commonly appear as filamentary, curvilinear features of variable width. These features have radar backscatter signatures that differ only slightly from those of non-ridged multi.