Publication detail

Adapting Polynomial Mahalanobis Distance for Self-Supervised Learning in an Outdoor Environment

RICHTER, M. PETYOVSKÝ, P. MIKŠÍK, O.

Original Title

Adapting Polynomial Mahalanobis Distance for Self-Supervised Learning in an Outdoor Environment

Type

conference paper

Language

English

Original Abstract

This paper addresses the problem of autonomous navigation of UGV in an unstructured environment. Generally, state-of-the-art approaches use color based segmentation of road/non-road regions in particular. There arises an important question, how is the distance between an input pixel and a color model measured. Many algorithms employ Mahalanobis distance, since Mahalanobis distance better follows the data distribution, however it is assumed, that the data points have a normal distribution. Recently proposed Polynomial Mahalanobis Distance (PMD) represents more discriminative metric, which provides superior results in an unstructured terrain, especially, if the road is barely visible even for humans. In this paper, we discuss properties of the Polynomial Mahalanobis Distance, and propose a novel framework - A Three Stage Algorithm (TSA), which deals with both, picking of suitable data points from the training area as well as self-supervised learning algorithm for long-term road representation.

Keywords

Polynomial Mahalanobis Distance, A Three Stage Algorithm, Self-supervised Learning, Robotics

Authors

RICHTER, M.; PETYOVSKÝ, P.; MIKŠÍK, O.

RIV year

2012

Released

3. 1. 2012

Publisher

The Institute of Electrical and Electronics Engineers, Inc.

ISBN

978-1-4577-2134-2

Book

Proceedings, The 10th International Conference on Machine Learning and Applications, ICMLA 2011, Volume 1: Main Conference (ISBN 978-1-4577-2134-2 , 978-0-7695-4607-0)

Pages from

448

Pages to

453

Pages count

6

BibTex

@inproceedings{BUT89729,
  author="Miloslav {Richter} and Petr {Petyovský} and Ondřej {Mikšík}",
  title="Adapting Polynomial Mahalanobis Distance for Self-Supervised Learning in an Outdoor Environment",
  booktitle="Proceedings, The 10th International Conference on Machine Learning and Applications, ICMLA 2011, Volume 1: Main Conference (ISBN 978-1-4577-2134-2 , 978-0-7695-4607-0)",
  year="2012",
  pages="448--453",
  publisher="The Institute of Electrical and Electronics Engineers, Inc.",
  isbn="978-1-4577-2134-2"
}