Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Spatiotemporally adaptive estimation and segmentation of OF-fields

: Nagel, H.-H.; Gehrke, A.


Burkhardt, H.; Neumann, B.:
Computer Vision. ECCV '98. Proceedings. Vol. 2
Berlin: Springer, 1998 (Lecture Notes in Computer Science 1407)
ISBN: 3-540-64613-2
ISSN: 0302-9743
European Conference on Computer Vision (ECCV) <5, 1998, Freiburg/Brsg.>
Conference Paper
Fraunhofer IITB ( IOSB) ()
adaptive filtering; adaptive Filterung; Bewegung; image motion; optical flow; optischer Fluß; segmentation; Segmentierung

A grayvalue structure tensor provides knowledge about a local grayvalue variation. This knowledge can be used to devise a spatiotemporally adaptive optic flow estimation process. Such an adaptive estimation lowers the level at which the resulting optic flow (OF) field is disturbed by noise and estimation artefacts. This in turn substantially simplifies the analysis of remaining - often subtle - effects which easily jeopardize a 'naive' segmentation approach. Appropriate treatment of such effects eventually results in a basically simple, but nevertheless surprisingly robust segmentation approach. Various stages of this approach are illustrated by examples for the extraction of moving vehicle images from a digitized road intersection video-sequence.