Seismic Time Section Analysis Using Machine Vision

In this paper we introduce a three stage approach for extracting events from a seismic time section. The approach incorporates recent, techniques from computer vision such as deformable templates and multiple hypothesis tracking, and also takes advantage of constraints arising from the physics of seismic reflectors. First, a 2D local matched fdtering scheme is used to reduce the time section to a collection of event tokens suitable for tracking with a Kalman filter. Second, a multiple tracking system is used to analyse regions with crossing events. By using a dynamic model of event shape parameters, Kalman filters are able to track events that deviate from an ideal form. Finally, based on events found through Kalman filtering, flexible templates are used to exploit similarity between events. Due to the global nature of the flexible template search process, even events with sections of poor visibility can be identified. Based on this research, a semi-automatic system for extracting seismic events has been developed.