DocumentCode :
1843309
Title :
Graph cut video object segmentation using histogram of oriented gradients
Author :
Wang, Chun Hao ; Guan, Ling
Author_Institution :
Ryerson Univ., Toronto, ON
fYear :
2008
fDate :
18-21 May 2008
Firstpage :
2590
Lastpage :
2593
Abstract :
This paper introduces a novel way to implement graph cut for video object segmentation with shape information. Graph Cut is a very efficient algorithm for image segmentation and histogram of oriented gradients (HOG) is useful in detecting humans. We combine the HOG feature to incorporate a shape prior into graph cut algorithm as a new way to enhance video object segmentation accuracy. In previous work, we used a fully connected 3-D that is slow and is subject to weak edges, inconsistent luminance. The new method is compared with old methods to show that it helps by introducing a shape prior for segmentation of pre-trained objects such as humans.
Keywords :
graph theory; image segmentation; video signal processing; graph cut video object segmentation; histogram of oriented gradients; image segmentation; shape information; Costs; Histograms; Humans; Image segmentation; MPEG 4 Standard; Object segmentation; Shape; Topology; Tracking; Video compression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 2008. ISCAS 2008. IEEE International Symposium on
Conference_Location :
Seattle, WA
Print_ISBN :
978-1-4244-1683-7
Electronic_ISBN :
978-1-4244-1684-4
Type :
conf
DOI :
10.1109/ISCAS.2008.4541986
Filename :
4541986
Link To Document :
بازگشت