Combined 3D Object Motion Estimation in Medical Sequences (TA-P3)
Author(s) :
Delhay Bertrand (CREATIS, France)
Clarysse Patrick (CREATIS, France)
Grangeat Pierre (CEA-LETI, France)
Magnin Isabelle (CREATIS, France)
Bonnet Stephane (CEA-LATI, France)
Abstract : In this paper, a method for the combined estimation of object's motion and boundaries in 3D image sequences is proposed. Based on the object concept of MPEG-4 standard and on a preliminary segmentation, it partitions the images in 3 types of 3D blocks. Motion is accurately determined on boundary blocs and initialize the estimation in the object interior. This initialization is refined with an BBGDS algorithm to detect some disparities in the motion field. Synthetic experiments show that the accuracy is equivalent to classical block matching algorithm with exhaustive search but in the third of the time. Moreover, the description of objects in terms of motion and shape is readily available.

Menu