English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/30403
Title: Integration of conditionally dependent object features for robust figure-background segmentation
Authors: Moreno-Noguer, Francesc; Sanfeliu, Alberto; Samaras, Dimitris
Keywords: Bayesian methods
Object detection
Pattern recognition: Computer vision
Pattern recognition: Object detection
Computer vision
Pattern recognition systems
Issue Date: 2005
Publisher: Institute of Electrical and Electronics Engineers
Citation: 10th IEEE International Conference on Computer Vision: pp. 1713-1720 (2005)
Abstract: 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.
Description: IEEE International Conference on Computer Vision (ICCV) 2005, Beijing (China)
URI: http://hdl.handle.net/10261/30403
DOI: http://dx.doi.org/10.1109/ICCV.2005.126
ISBN: 076952334X
Appears in Collections:(IRII) Comunicaciones congresos
Files in This Item:
File Description SizeFormat 
doc1.pdf901,08 kBAdobe PDFThumbnail
Show full item record

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