DocumentCode :
2503054
Title :
Segmenting Video Foreground Using a Multi-Class MRF
Author :
Dickinson, Patrick ; Hunter, Andrew ; Appiah, Kofi
Author_Institution :
Univ. of Lincoln, Lincoln, UK
fYear :
2010
fDate :
23-26 Aug. 2010
Firstpage :
1848
Lastpage :
1851
Abstract :
Methods of segmenting objects of interest from video data typically use a background model to represent an empty, static scene. However, dynamic processes in the background, such as moving foliage and water, can act to undermine the robustness of such methods and result in false positive object detections. Techniques for reducing errors have been proposed, including Markov Random Field (MRF) based pixel classification schemes, and also the use of region-based models. The work we present here combines these two approaches, using a region-based background model to provide robust likelihoods for multi-class MRF pixel labelling. Our initial results show the effectiveness of our method, by comparing performance with an analogous per-pixel likelihood model.
Keywords :
image classification; image representation; image segmentation; object detection; video signal processing; Markov random field; analogous per-pixel likelihood model; multi-class MRF; object detections; object segmention; pixel classification; region-based background model; video data; video foreground segmention; Adaptation model; Conferences; Image color analysis; Image segmentation; Labeling; Mathematical model; Pixel; MRF; Video segementation;
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.2010.456
Filename :
5597201
Link To Document :
بازگشت