PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Structured Class-labels in Random Forests for Semantic Image Labeling
Peter P. Kontschieder, Samuel Rota Bulò, Horst Bischof and Marcello Pelillo
In: ICCV 2011 -- 13th International Conference on Computer Visione, 6 - 13 November 2011, Barcelona, Spain.

Abstract

In this paper we propose a simple and effective way to integrate structural information in random forests for semantic image labelling. By structural information we refer to the inherently available, topological distribution of object classes in a given image. Different object class labels will not be randomly distributed over an image but usually form coherently labelled regions. In this work we provide a way to incorporate this topological information in the popular random forest framework for performing low-level, unary classification. Our paper has several contributions: First, we show how random forests can be augmented with structured label information. In the second part, we introduce a novel data splitting function that exploits the joint distributions observed in the structured label space for learning typical label transitions between object classes. Finally, we provide two possibilities for integrating the structured output predictions into concise, semantic labellings. In our experiments on the challenging MSRC and CamVid databases, we compare our method to standard random forest and conditional random field classification results.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Theory & Algorithms
ID Code:9200
Deposited By:Marcello Pelillo
Deposited On:21 February 2012