DocumentCode :
2917689
Title :
A hierarchical conditional random field model for labeling and segmenting images of street scenes
Author :
Huang, Qixing ; Han, Mei ; Wu, Bo ; Ioffe, Sergey
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
1953
Lastpage :
1960
Abstract :
Simultaneously segmenting and labeling images is a fundamental problem in Computer Vision. In this paper, we introduce a hierarchical CRF model to deal with the problem of labeling images of street scenes by several distinctive object classes. In addition to learning a CRF model from all the labeled images, we group images into clusters of similar images and learn a CRF model from each cluster separately. When labeling a new image, we pick the closest cluster and use the associated CRF model to label this image. Experimental results show that this hierarchical image labeling method is comparable to, and in many cases superior to, previous methods on benchmark data sets. In addition to segmentation and labeling results, we also showed how to apply the image labeling result to rerank Google similar images.
Keywords :
computer vision; image segmentation; learning (artificial intelligence); pattern clustering; random processes; Google similar image reranking; computer vision; distinctive object class; hierarchical conditional random field model; image clusters; image labeling; image segmentation; learning; street scene; Computational modeling; Google; Image color analysis; Labeling; Layout; Semantics; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
ISSN :
1063-6919
Print_ISBN :
978-1-4577-0394-2
Type :
conf
DOI :
10.1109/CVPR.2011.5995571
Filename :
5995571
Link To Document :
بازگشت