Sciweavers

Share
ECCV
2010
Springer

Supervised Label Transfer for Semantic Segmentation of Street Scenes

10 years 9 months ago
Supervised Label Transfer for Semantic Segmentation of Street Scenes
In this paper, we propose a robust supervised label transfer method for the semantic segmentation of street scenes. Given an input image of street scene, we first find multiple image sets from the training database consisting of images with annotation, each of which can cover all semantic categories in the input image. Then, we establish dense correspondence between the input image and each found image sets with a proposed KNN-MRF matching scheme. It is followed by a matching correspondences classification that tries to reduce the number of semantically incorrect correspondences with trained matching correspondences classification models for different categories. With those matching correspondences classified as semantically correct correspondences, we infer the confidence values of each super pixel belonging to different semantic categories, and integrate them and spatial smoothness constraint in a markov random field to segment the input image. Experiments on three datasets show our ...
Honghui Zhang, Jianxiong Xiao, Long Quan
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ECCV
Authors Honghui Zhang, Jianxiong Xiao, Long Quan
Comments (0)
books