Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 633-640, 2016
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/633/2016/
doi:10.5194/isprs-archives-XLI-B3-633-2016
 
10 Jun 2016
EFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD
Weihao Li1 and Michael Ying Yang1,2 1TU Dresden, Computer Vision Lab Dresden, Dresden, Germany
2University of Twente, ITC Faculty, EOS department, Enschede, The Netherlands
Keywords: Man-made Scene, Semantic Segmentation, Fully Connected CRFs, Mean Field Inference Abstract. In this paper we explore semantic segmentation of man-made scenes using fully connected conditional random field (CRF). Images of man-made scenes display strong contextual dependencies in the spatial structures. Fully connected CRFs can model long-range connections within the image of man-made scenes and make use of contextual information of scene structures. The pairwise edge potentials of fully connected CRF models are defined by a linear combination of Gaussian kernels. Using filter-based mean field algorithm, the inference is very efficient. Our experimental results demonstrate that fully connected CRF performs better than previous state-of-the-art approaches on both eTRIMS dataset and LabelMeFacade dataset.
Conference paper (PDF, 2981 KB)


Citation: Li, W. and Yang, M. Y.: EFFICIENT SEMANTIC SEGMENTATION OF MAN-MADE SCENES USING FULLY-CONNECTED CONDITIONAL RANDOM FIELD, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 633-640, doi:10.5194/isprs-archives-XLI-B3-633-2016, 2016.

BibTeX EndNote Reference Manager XML