Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/30403
Share/Impact:
Título : Integration of conditionally dependent object features for robust figure-background segmentation
Autor : Moreno Noguer, Francesc, Sanfeliu Cortés, Alberto, Samaras, Dimitris
Palabras clave : Bayesian methods
Object detection
Pattern recognition: Computer vision
Pattern recognition: Object detection
Computer vision
Pattern recognition systems
Fecha de publicación : 2005
Editor: Institute of Electrical and Electronics Engineers
Resumen: We propose a new technique for focusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by tile integration of appearance and geometric object features and by their description using particle filters. Previous approaches assume independence of the object cues or apply the particle filter formulation to only one of the features, and assume a smooth change in the rest, which can prove is very limiting, especially when the state of some features needs to be updated using other cues or when their dynamics follow non-linear and unpredictable paths. Our technique offers a general framework to model the probabilistic relationship between features. The proposed method is analytically justified and applied to develop a robust tracking system that adapts online and simultaneously the color space where the image points are represented, the color distributions, and the contour of the object. Results with synthetic data and real video sequences demonstrate the robustness and versatility of our method.
Descripción : IEEE International Conference on Computer Vision (ICCV) 2005, Beijing (China)
URI : http://hdl.handle.net/10261/30403
ISBN : 076952334X
DOI: http://dx.doi.org/10.1109/ICCV.2005.126
Citación : 10th IEEE International Conference on Computer Vision: pp. 1713-1720 (2005)
Appears in Collections:(IRII) Comunicaciones congresos

Files in This Item:
File Description SizeFormat 
doc1.pdf901,08 kBAdobe PDFView/Open
Show full item record
 
CSIC SFX LinksSFX Query

Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.