Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Motion boundary detection in image sequences by local stochastic tests

: Nagel, H.-H.; Socher, G.; Kollnig, H.; Otte, M.


Eklundh, J.-O.:
Computer Vision. ECCV '94. Proceedings. Vol.2
Berlin: Springer, 1994 (Lecture Notes in Computer Science 801)
ISBN: 3-540-57957-5
ISSN: 0302-9743
pp.305-315 : Abb.,Lit.
European Conference on Computer Vision (ECCV) <3, 1994, Stockholm>
Conference Paper
Fraunhofer IITB ( IOSB) ()
motion boundary; optical flow estimation; optical flow field; segmentation; stochastic approach; stochastic test

While estimating both components of opticalflow based on the postulated validity of the Optical Flow Constraint Equation (OFCE), it has been tacitly assumed so far that the partial derivatives of the gray value distribution - which are required for this approach at the pixel positions involved - are independent from each other. (Nagel 94) has shown in a theoretical investigation how dropping this assumption affects the estimation procedure. The advantage of such a more rigorous approach consists in the possibility to replace heuristic tests for the local detection of discontinuities in optical flow fields by well known stochastic tests. First results from various experiments with this new approach are presented and discussed.