PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Scene Segmentation with Low-dimensional Semantic Representations and Conditional Random Fields
Wen Yang, William Triggs, Dengxin Dai and Gui-Song Xia
EURASIP Journal on Advances in Signal Processing 2010.


Partitioning visual scenes into regions corresponding to the semantic-level object classes that they contain is an important problem in visual recognition. Recently, significant progress has been made by combining local appearance cues with contextual information via random field models. We present a fast, precise and highly scalable semantic segmentation algorithm that incorporates several kinds of local appearance features, example-based spatial layout priors, and neighborhood-level and global contextual information. The method works at the level of image patches. In the first stage, codebook based local appearance features are regularized and reduced in dimension using latent topic models, combined with spatial pyramid matching based spatial layout features, and fed into logistic regression classifiers to produce an initial patch level labeling. In the second stage, these labels are combined with patch-neighborhood and global aggregate features using either a second layer of Logistic Regression or a Conditional Random Field. Finally, the patch-level results are refined to pixel-level using MRF or over-segmentation based methods. The CRF is trained using a fast Maximum Margin approach. Comparative experiments on four multi-class segmentation datasets show that each of the above elements improves the results, leading to a scalable algorithm that is both faster and more accurate than existing patch-level approaches.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
Multimodal Integration
ID Code:7173
Deposited By:William Triggs
Deposited On:07 March 2011