high performance computing on graphics processing units: hgpu.org

An important part of today’s search for hydrocarbon reservoirs such as oil and gas is the use of seismic methods which measure changes in acoustic impedance to explore the interior of the earth. Similar to medical imaging techniques such as MRI or CT, seismic methods generate image slices (survey lines) through the subsurface geology. By placing many of these 2D survey lines within close distance to each other, a more detailed three-dimensional picture can be build. This technique is called a 3D survey [Ric05, p. 123]. The visualization and interpretation of the resulting information is a challenging task due to the huge amount of generated data, which can easily reach sizes of multiple gigabytes [Mur02]. Moreover, seismic data contains a high presence of noise, which makes it even more difficult to visualize. Interpretation often includes time-consuming manual tasks by so-called seismic interpreters to identify subsurface structures that may hint at potential hydrocarbon deposits. An often used method to support the interpretation of volumetric seismic data is volume rendering. This thesis mainly focuses on techniques to improve the classification and visualization of volumetric seismic data by means of volume rendering. More specifically it will be investigated if the so-called occlusion spectrum, which is a classification technique from the medical domain, can be used in the context of seismic volume rendering.