Unsupervised Segmentation of 3D and 2D Seismic Reflection Data

K. Koester, M. Spann

Accepted for publication in Int. J. of Pattern Rec. and Artificial Int., Sept 1998

Abstract

This paper describes an unsupervised method to extract 2D and 3D inner earth structures from seismic reflection measurements. The
application is a typical texture segmentation problem, which can be split up into a feature extraction stage and a segmentation
stage. As a texture feature, the locally emergent frequency is estimated by a Gabor filter bank. The instantaneous frequency (IF)
has already been successfully used for seismic trace analysis and will be compared with the results of the filter bank.
The second stage of the algorithm involves a region-growing method to compute the final object structure. The extremely flexible segmentation
scheme is appropriate for application to 2D and 3D images of arbitrary vectorial dimension. The merging decision is based on the mutual inlier
ratio of two adjacent regions. This ratio is computed by robust regression techniques to avoid noise artifacts. A mutual inlier ratio
discrimination function to recognise identical Gaussian distributions, guaranteeing a 97.5\% certainty, is derived. This method is compared with
the Kolmogorov-Smirnov test and results of the application in a segmentation algorithm are shown. The segmentation stage is also tested
with different benchmark data sets from other computer vision problems to demonstrate its general flexibility.

Download gzipped Postscript (1613K)

Project achievements

Back to papers and internal reports