DocumentCode :
3343227
Title :
Fast semantic scene segmentation with conditional random field
Author :
Yang, Wen ; Dai, Dengxin ; Triggs, Bill ; Xia, Guisong ; He, Chu
Author_Institution :
Sch. of Electron. Inf., Wuhan Univ., Wuhan, China
fYear :
2010
fDate :
26-29 Sept. 2010
Firstpage :
229
Lastpage :
232
Abstract :
In this paper, we present a fast approach to obtain semantic scene segmentation with high precision. We employ a two-stage classifier to label all image pixels. First, we use the regularized logistic regression to combine different appearance-based features and the improved spatial layout of labeling information. In the second stage, we incorporate the local, regional and global cues into a conditional random field model to provide a final segmentation, and a fast max-margin training method is employed to learn the parameters of the model quickly. The comparison experiments on four multi-class image segmentation databases show that our approach can achieve comparable semantic segmentation results and work faster than that of the state-of-the-art approaches.
Keywords :
image segmentation; pattern classification; appearance based feature; classifier; image pixels; image segmentation database; logistic regression; semantic scene segmentation; Accuracy; Context; Image segmentation; Labeling; Pixel; Semantics; Training; Scene segmentation; conditional random field; image labeling; logistic regression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
ISSN :
1522-4880
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2010.5652023
Filename :
5652023
Link To Document :
بازگشت