DocumentCode :
69924
Title :
Geodesic Propagation for Semantic Labeling
Author :
Li, Qifeng ; Chen, Xia ; Song, Yuning ; Zhang, Ye ; Jin, Xinzhe ; Zhao, Qiming
Author_Institution :
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China
Volume :
23
Issue :
11
fYear :
2014
fDate :
Nov. 2014
Firstpage :
4812
Lastpage :
4825
Abstract :
This paper presents a semantic labeling framework with geodesic propagation (GP). Under the same framework, three algorithms are proposed, including GP, supervised GP (SGP) for image, and hybrid GP (HGP) for video. In these algorithms, we resort to the recognition proposal map and select confident pixels with maximum probability as the initial propagation seeds. From these seeds, the GP algorithm iteratively updates the weights of geodesic distances until the semantic labels are propagated to all pixels. On the contrary, the SGP algorithm further exploits the contextual information to guide the direction of propagation, leading to better performance but higher computational complexity than the GP. For video labeling, we further propose the HGP algorithm, in which the geodesic metric is used in both spatial and temporal spaces. Experiments on four public data sets show that our algorithms outperform several state-of-the-art methods. With the GP framework, convincing results for both image and video semantic labeling can be obtained.
Keywords :
Algorithm design and analysis; Image color analysis; Image edge detection; Image segmentation; Labeling; Semantics; Semantic labeling; geodesic propagation; indicator; label transfer; video labeling;
fLanguage :
English
Journal_Title :
Image Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1057-7149
Type :
jour
DOI :
10.1109/TIP.2014.2358193
Filename :
6898820
Link To Document :
بازگشت