Directional Associative Markov Network for 3-D Point Cloud Classification - Robotics Institute Carnegie Mellon University

Directional Associative Markov Network for 3-D Point Cloud Classification

Daniel Munoz, Nicolas Vandapel, and Martial Hebert
Conference Paper, Proceedings of 4th International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT '08), June, 2008

Abstract

In this paper we address the problem of automated three dimensional point cloud interpretation. This problem is important for various tasks from environment modeling to obstacle avoidance for autonomous robot navigation. In addition to locally extracted features, classifiers need to utilize contextual information in order to perform well. A popular approach to account for context is to utilize the Markov Random Field framework. One recent variant that has successfully been used for the problem considered is the Associative Markov Network (AMN). We extend the AMN model to learn directionality in the clique potentials, resulting in a new anisotropic model that can be efficiently learned using the subgradient method. We validate the proposed approach using data collected from different range sensors and show better performance against standard AMN and Support Vector Machine algorithms.

BibTeX

@conference{Munoz-2008-10003,
author = {Daniel Munoz and Nicolas Vandapel and Martial Hebert},
title = {Directional Associative Markov Network for 3-D Point Cloud Classification},
booktitle = {Proceedings of 4th International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT '08)},
year = {2008},
month = {June},
keywords = {structured learning, markov random field, terrain classification, urban environment},
}