Adaptive Road Detection through Continuous Environment Learning

Published

October 15, 2004

Author(s)

M Foedissch, A Takeuchi

Abstract

The Intelligent Systems Division of the National Institute of Standards and Technology has been engaged for several years in developing real-time systems for autonomous driving. A road detection program is an essential part of the project. Previously we developed an adaptive road detection system based on color histograms using a neural network. This, however, still required human involvement during the initialization step. As a continuation of the project, we have expanded the system so that it can adapt to the new environment without any human intervention. This system updates the neural network continuously based on the road image structure. In order to reduce the possibility of misclassifying road and non-road, we have implemented an adaptive road feature acquisition method.

Proceedings Title

Proceedings of the AIPR Conference

Conference Dates

October 13-15, 2004

Conference Location

Washington, D.C, MD, USA

Conference Title

AIPR Conference

Pub Type

Conferences

Download Paper

Local Download

Keywords

automated vehicles, Brain Models & Neural Nets, Neural Networks, road detection, Robotics & Intelligent Systems, vehicle environment perception, Vision

Citation

Foedissch, M. and Takeuchi, A. (2004), Adaptive Road Detection through Continuous Environment Learning, Proceedings of the AIPR Conference, Washington, D.C, MD, USA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=822555 (Accessed July 27, 2024)