DocumentCode
254443
Title
T-Linkage: A Continuous Relaxation of J-Linkage for Multi-model Fitting
Author
Magri, L. ; Fusiello, A.
Author_Institution
Dept. of Math., Univ. of Milan, Milan, Italy
fYear
2014
fDate
23-28 June 2014
Firstpage
3954
Lastpage
3961
Abstract
This paper presents an improvement of the J-linkage algorithm for fitting multiple instances of a model to noisy data corrupted by outliers. The binary preference analysis implemented by J-linkage is replaced by a continuous (soft, or fuzzy) generalization that proves to perform better than J-linkage on simulated data, and compares favorably with state of the art methods on public domain real datasets.
Keywords
image motion analysis; image segmentation; image sequences; video signal processing; J-linkage algorithm; T-linkage; binary preference analysis; continuous generalization; continuous relaxation; fuzzy generalization; motion segmentation; multimodel fitting; outlier rejection; soft generalization; video sequence; Clustering algorithms; Computational modeling; Computer vision; Data models; Estimation; Motion segmentation; Robustness;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location
Columbus, OH
Type
conf
DOI
10.1109/CVPR.2014.505
Filename
6909900
Link To Document