| Title: |
A Novel Approach for Salt Dome Detection and Tracking using a Hybrid Hidden Markov Model with an Active Contour Model. |
| Authors: |
Deriche, M.; absa, Ahmed Abo; Amin, A.; Liu, B. |
| Source: |
Journal of Electrical Systems; Sep2020, Vol. 16 Issue 3, p276-294, 19p |
| Subject Terms: |
Salt domes; Singular value decomposition; Hidden Markov models; Algorithms; Tracking algorithms; Change-point problems; Imaging systems in seismology |
| Geographic Terms: |
Netherlands |
| Abstract: |
One of the most important tasks in seismic data interpretation is the detection of salt bodies since most of the important reservoirs are trapped around such bodies. However, the accurate interpretation and analysis of such data depends heavily upon the robustness of the attributes/features used and the efficiency of the classification/segmentation stage. In this paper, we present a novel salt dome detection and tracking algorithm which combines the Hidden Markov Model (HMM) with the Active Contour Model (ACM). The HMM is used with a set of new features based on the Higher Order Singular Value Decomposition (HOSVD) of 3D seismic volumes to accurately delineate the boundaries of salt domes. The model parameters of the HMM are estimated using the Expectation-Maximization (EM) algorithm. The new HOSVD based features ensure that the proposed workflow overcomes the limitations of edge-based and texturebased methods. Furthermore, in order to alleviate the computational burden of the HMM, an ACM is applied on consecutive seismic images to track the changes of the salt dome boundary across the 3D seismic volume. We tested the proposed algorithm on real seismic data from the Netherlands offshore F3 block. Our algorithm, with only a small set of features, produces excellent results as compared to existing edge-based, texture-based, and fusion-based methods. [ABSTRACT FROM AUTHOR] |
| : |
Copyright of Journal of Electrical Systems is the property of Journal of Electrical Systems and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Complementary Index |