Digital panoramic borehole camera technology has been widely employed in actual projects, and a large number of high-accuracy borehole camera images have been obtained. The borehole camera images accurately record the geological information, especially the feature parameters of discontinuities. However, since the acquisition of these features is usually done by hand, the workload is large and the results can be affected by human factors. To solve this problem, this paper presents an automatic interpretation method of discontinuities in borehole camera image. In this method, image gray, gradient values and projection method are employed to distinguish the occurrence region of structural planes. Then, standard sine function matching method is employed to search the discontinuities in the region. Lastly, the optimal sine curve is screened out and adopted as the feature curve of discontinuities. And the related parameters of feature curve are analyzed and converted into the parameters of discontinuities, such as the central position, orientation, dip angle and fracture width of discontinuity, which are required in engineering projects. This method can automatically identify the discontinuity in the borehole camera image continuously and quickly, and obtain the corresponding structural parameters. The method is stable and reliable, and greatly improves the working efficiency. It can realize the automatic interpretation of the discontinuities and the extraction of geometric parameters, and provide an effective and reliable solution for drilling information acquisition and borehole camera image signal processing.
Knowledge of a rock body's structural stability is often necessary in geotechnical, geological, oil extraction, and also geological disaster control projects. The reliability of a project can heavily depend on the discontinuities found in rock bodies, such as joints, faults, weak planes, and bedding planes (Assous et al. 2013, Bae et al. 2011, Cunningham et al. 2004). A digital panoramic borehole camera system can obtain the high-definition images of boreholes that offer an accurate representation of their discontinuities characteristics. Therefore, the accurate recognition of discontinuities and rapid extraction of their parameters are highly valuable for actual drilling engineering (Deltombe &Schepers 2004).
Present identification methods of discontinuities in borehole camera images mostly rely heavily on human reading. Generally, the structures identification and parameter extraction process may involve computer-aided pre-processing or characteristic curve fitting. Through using human-assigned control points on the discontinuities or other necessary parameters, the methods can obtain the sine curve's parameters of discontinuities in borehole camera images (Lofi et al. 2012, Schepers et al. 2001), which is a laborious and slow process that requires human intervention. And the obtained discontinuities are often varying depending on individual readers (Han et al. 2013, Hurich &Deemer 2013, Malone et al. 2013). This kind of manual identification process can become a drain on time and human effort in engineering practice, particularly when the boreholes are deep or numerous. Thus, the full-automatic recognition of discontinuities in borehole camera images for actual drilling engineering becomes urgent and very valuable.
