3-DIMENSIONAL SURFACE RECONSTRUCTION USING OPTICAL-FLOW FOR MEDICAL IMAGING

The recovery of a three-dimensional (3-D) model from a sequence of two -dimensional (2-D) images is very useful in medical image analysis, Im age sequences obtained from the relative motion between the object and the camera or the scanner contain more 3-D information than a single image. Methods to visualize the computed tomograms can be divided into two approaches: the surface rendering approach and the volume renderi ng approach, In this paper, a new surface rendering method using optic al how is proposed, Optical flow is the apparent motion in the image p lane produced by the projection of the real 3-D motion onto 2-D image. The 3-D motion of an object can be recovered from the optical-flow he ld using additional constraints. By extracting the surface information from 3-D motion, it is possible to get an accurate 3-D model of the o bject, Both synthetic and real image sequences have been used to illus trate the feasibility of the proposed method, The experimental results suggest that the proposed method is suitable for the reconstruction o f 3-D models from ultrasound medical images as well as other computed tomograms.