A comparative evaluation of algorithms for fast computation of level set PDEs with applications to motion segmentation
- 13 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 636-639
- https://doi.org/10.1109/icip.2001.958199
Abstract
We address the problem of fast computation of level set partial dif- ferential equations (PDEs) in the context of motion segmentation. Although several fast level set computation algorithms are known, some of them, such as the fast marching method, are not applica- ble to the video segmentation problem since the front being com- puted does not advance monotonically. We study narrow-banding, pyramidal and a pyramidal/narrow-banding schemes that leads to a 70-fold time gain over the single-resolution scheme.Keywords
This publication has 5 references indexed in Scilit:
- Morphing active contours: a geometric approach to topology-independent image segmentation and trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Detection and tracking of moving objects using a new level set based methodPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Topology-independent region tracking with level setsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Geodesic active contours and level sets for the detection and tracking of moving objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- Motion segmentation with level setsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999