Seismic image segmentation and its application to geologic interpretation

Image segmentation is a standard low-level task in computer vision. We demo nstrate how the segmentation of two-dimensional (2-D) seismic images can as sist in geologic interpretation. An image segmentation technique is applied to 2-D images of the acoustic impedance. A salient feature of the resultin g segments is that the hydrocarbon bearing regions are characterized by a f iner segmentation than the other regions. A modified apparent polarity attr ibute is introduced and images of this attribute are segmented. The boundar ies of the resulting segments pass through the minima and the maxima of the acoustic impedance in a manner which allows us to segment the acoustic imp edance image into layers of high and low acoustic impedance. Our methods ca n assist in segmentation of acoustic impedance images according to litholog y or geologic facies.