A novel approach for salt dome detection in seismic surveys using a Hidden Markov Model

In this paper, we present a novel salt dome detection method using a Hidden Markov Model (HMM). The proposed algorithm combines the HMM with the Higher Order Singular Value Decomposition (HOSVD) based features to accurately delineate the salt boundaries in seismic data. The optimal parameters for the HMM are estimated using the Expectation- Maximization (EM) algorithm. By using the HOSVD based features, we ensure that the proposed algorithm overcomes the limitations of existing texture attributes based methods that are heavily dependent upon the relevance of attributes and the size of window used for extracting these attributes. We tested the proposed algorithm on the Netherlands offshore F3 block. Our algorithm, using a small feature set, produces excellent results as compared to the existing edge-based, texture-based, and the hybrid edge-texture based methods.