DocumentCode :
2515438
Title :
Stochastic Filtering of Level Sets for Curve Tracking
Author :
Avenel, Christophe ; Mémin, Etienne ; Pérez, Patrick
Author_Institution :
Univ. Rennes 1, Rennes, France
fYear :
2010
fDate :
23-26 Aug. 2010
Firstpage :
3553
Lastpage :
3556
Abstract :
This paper focuses on the tracking of free curves using non-linear stochastic filtering techniques. It relies on a particle filter which includes color measurements. The curve and its velocity are defined through two coupled implicit level set representations. The stochastic dynamics of the curve is expressed directly on the level set function associated to the curve representation and combines a velocity field captured from the additional second level set attached to the past curve´s points location. The curve´s dynamics combines a low-dimensional noise model and a data-driven local force. We demonstrate how this approach allows the tracking of highly and rapidly deforming objects, such as convective cells in infra-red satellite images, while providing a location-dependent assessment of the estimation confidence.
Keywords :
curve fitting; image colour analysis; image representation; nonlinear filters; particle filtering (numerical methods); set theory; stochastic processes; color measurement; curve representation; data-driven local force; deforming object tracking; free curve tracking; implicit level set representation; level set function; low-dimensional noise model; nonlinear stochastic filtering; particle filter; stochastic dynamics; velocity field; Atmospheric measurements; Dynamics; Level set; Particle measurements; Stochastic processes; Tracking; Trajectory; Curve tracking; level set; stochastic filtering;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
ISSN :
1051-4651
Print_ISBN :
978-1-4244-7542-1
Type :
conf
DOI :
10.1109/ICPR.2010.867
Filename :
5597833
Link To Document :
بازگشت