Accurate semantic image labeling by fast geodesic propagation

Authors:
Xiaowu Chen;Dongyue Zhao;Yibiao Zhao;Liang Lin
Affiliations:
State Key Laboratory of Virtual Reality Technology and Systems, SCSE, Beihang University, Beijing, P.R. China;State Key Laboratory of Virtual Reality Technology and Systems;School of Computer and Information Technology, Beijing Jiaotong University, Beijing, P.R. China;Department of Statistic, University of California, Los Angeles
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 6
Cited 2

Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Graph Partition by Swendsen-Wang Cuts

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues

IEEE Transactions on Pattern Analysis and Machine Intelligence
Short note: O(N) implementation of the fast marching algorithm

Journal of Computational Physics
Multi-Class Segmentation with Relative Location Prior

International Journal of Computer Vision
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

International Journal of Computer Vision

Occlusion cues for image scene layering

Computer Vision and Image Understanding
Supervised geodesic propagation for semantic label transfer

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motivated by recently raised image semantic labeling problem, this paper studies a fast Geodesic Propagation (GP) algorithm that integrates recognition proposal and image compatibility into a graphical representation. Given the recognition proposal map of the image, the initial seeds are selected as confident pixels standing on local proposal peaks by Mean-shift algorithm. The geodesic distance is then defined on a hybrid manifold, combining the color and boundary features with the recognition proposal map. Based on the geodesic distance, the semantic labeling is simultaneously propagated from the initial seeds of all classes to the rest of image pixels. This inference algorithm is capable of multi-labeling an image of 2-mega pixels in one second (with a common PC). In the experiment, we test on 21 generic semantic categories (sky, road, grass ...) on MSRC dataset, and 17 categories on LHI dataset to evaluate the performance.