Presents a method to determine the 3D motion of multiple objects from two perspective views. In our method, segmentation is determined based on a 3D rigidity constraint. We divide the input image into overlapping patches, and for each sample of the translation parameter space, we compute the rotation parameters of patches using a least-squares fit. Every patch votes for a sample in the translation and rotation parameter space. For a patch containing multiple motions, we use an M-estimator to compute rotation parameters of a dominant motion. We use the adaptive Hough transform to refine the relevant parameter space in a "coarse-to-fine" fashion. Applications of the proposed method to both synthetic and real images are demonstrated with promising results.<>
Recovering 3D motion of multiple objects using adaptive Hough transform
01.01.1995
602201 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Recovering 3D Motion of Multiple Objects Using Adaptive Hough Transform
British Library Conference Proceedings | 1995
|British Library Online Contents | 1993
|British Library Online Contents | 1993
|Adaptive dual-point Hough transform for object recognition
British Library Online Contents | 2004
|