PROJECTIVE RECOVERY OF STRUCTURE FROM NONRIGID MOTION USING TEMPORAL FUSION

Although most naturally occurring objects move in a nonrigid manner, t he vast majority of the motion research in computer vision has focused on rigid objects due to mathematical elegance and legacy. Driven rece ntly by new applications in telecommunications, medicine, and industry , a new body of research is beginning to emerge that is focused on the recovery of structure and motion for nonrigid objects. Most of these methods, however, have abandoned the large body of work in feature-bas ed rigid body motion recovery in favor of model-based techniques, whic h unfortunately limits their abilities in completely unknown environme nts. Four token-based, rigid body structure from motion (SFM) algorith ms are modified for the recovery of structure from nonrigid motion by replacing the rigidity constraint with the temporal fusion of an image sequence. The results of numerous experiments using simulated imagery are also presented to demonstrate and characterize the performance of the four modified techniques. (C) 1997 Society or Photo-Optical Instr umentation Engineers.