Image processing of seismic attributes for automatic fault extraction

Qi, Jie; Lyu, Bin; Alali, Abdulmohsen; Machado, Gabriel; Hu, Ying; Marfurt, Kurt J.

doi:10.1190/geo2018-0369.1

Cited by 57 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Historically, seismic interpretation analysis are performed on post-stack seismic data and based on a long list of attributes. 219,220 These attributes include amplitude, 221 curvature, 222 gradient, coherence, 223 as well as texture information. A comprehensive review of these attribute-based works is provided by Chopra and Marfurt.…”

Section: A Image Classification For Seismic Interpretationmentioning

confidence: 99%

Machine learning in acoustics: Theory and applications

Bianco

Gerstoft

Traer

et al. 2019

The Journal of the Acoustical Society of America

424

126

View full text Add to dashboard Cite

Acoustic data provide scientific and engineering insights in fields ranging from biology and communications to ocean and Earth science. We survey the recent advances and transformative potential of machine learning (ML), including deep learning, in the field of acoustics. ML is a broad family of statistical techniques for automatically detecting and utilizing patterns in data. Relative to conventional acoustics and signal processing, ML is data-driven. Given sufficient training data, ML can discover complex relationships between features and desired labels or actions, or between features themselves. With large volumes of training data, ML can discover models describing complex acoustic phenomena such as human speech and reverberation. ML in acoustics is rapidly developing with compelling results and significant future promise. We first introduce ML, then highlight ML developments in five acoustics research areas: source localization in speech processing, source localization in ocean acoustics, bioacoustics, seismic exploration, and environmental sounds in everyday scenes.

show abstract

Section: A Image Classification For Seismic Interpretationmentioning

confidence: 99%

Machine learning in acoustics: Theory and applications

Bianco

Gerstoft

Traer

et al. 2019

The Journal of the Acoustical Society of America

424

126

View full text Add to dashboard Cite

show abstract

“…To further suppress other structural discontinuities and sharpen faults, we apply a Laplacian of a Gaussian filter (Machado et al, 2016;Qi et al, 2019) on the multispectral coherence volume. We then compute a directional skeletonization (Qi et al, 2016) along with the fault plane on the filtered multispectral coherence, providing enhanced fault images.…”

Section: Workflowmentioning

confidence: 99%

Seismic fault enhancement using spectral decomposition assisted attributes

Lyu

Machado

et al. 2019

SEG Technical Program Expanded Abstracts 2019

Self Cite

View full text Add to dashboard Cite

Seismic attributes provide an efficient tool for fault identification and delineation in seismic data. Coherence followed by smoothing, sharpening, and skeletonization have significantly improved fault images. Traditionally, we apply coherence and fault enhancement processes to the full-bandwidth seismic data. These resulting images may still be disappointing in the presence of strong seismic noise, or juxtaposition of relatively similar reflectors across a fault. We develop a seismic fault enhancement method based on spectral decomposition assisted attributes. Certain spectral components often exhibit higher signal-to-noise (S/N) ratio over other components, sometimes because of the seismic data quality and sometimes due to the underlying geologic features including tuning and reflector alignment. Because the phase is different for different spectral components, alignment effects occur for only a few spectral components not all components, which helps to fill the coherence gap due to the similar reflectors across faults. In the proposed seismic fault enhancement method, we first perform a structure-oriented filtering (SOF) on the original seismic amplitude volume, to improve the data quality. Next, we compute the multispectral coherence, to further reduce the noise and fill the coherence gap, thus improving the continuity of the faults. Finally, we provide the enhanced fault images by computing a directional skeletonization on the multispectral coherence volume, which further suppress other structural discontinuities and improve the resolution of faults. We evaluate this seismic fault enhancement method with the Opunake 3D seismic survey acquired in the offshore Taranaki Basin, New Zealand.

show abstract

“…Digital image processing algorithms and face recognition management systems based on artificial intelligence are widely used in social life [7]. With the continuous development of artificial intelligence, the Internet of Things, and other cutting-edge technologies, the design of the smart campus, smart city, smart health care, and other fields are becoming more and more sophisticated, especially since 2020, driven by the rigid demand for epidemic prevention and control, the application of face recognition technology in the whole society is constantly strengthened [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Research on the design of automatic image processing function for intelligent face management system

Cai

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Around the background of rapid development of intelligent technology, an efficient image processing system oriented to the smart management of human faces is focused on. The system is mainly developed towards high speed, high definition, high integration and reliability. The article investigates a novel automatic image processing algorithm, covering three key modules: automatic exposure control, color interpolation and chromaticity space conversion. The algorithm can process the output image of CMOS sensor in Bayer format in real time and adjust the image parameters to obtain a high-quality image. In terms of face recognition performance, the algorithm has a significant advantage in recognition speed compared with other algorithms, and the average recognition accuracy reaches 94.258%. In the practical application of ID card portrait processing, the image shows a more uniform grayscale distribution in the range of 5 to 255 after automatic color adjustment, and the color quality is significantly improved. Meanwhile, in the portrait enhancement experiments, the images obtained with this image automatic processing algorithm outperform the traditional ID card image processing methods regarding information entropy, mutual information, standard deviation and peak signal-to-noise ratio (PSNR).

show abstract

Image processing of seismic attributes for automatic fault extraction

Cited by 57 publications

References 42 publications

Machine learning in acoustics: Theory and applications

Machine learning in acoustics: Theory and applications

Seismic fault enhancement using spectral decomposition assisted attributes

Research on the design of automatic image processing function for intelligent face management system

Contact Info

Product

Resources

About