Road Tracking in Aerial Images Based on Human-Computer Interaction and Bayesian Filtering

Prof. Terry Caelli (ASSET, NICTA. / RSISE, ANU.)

DATE: 2005-11-04
TIME: 11:00:00 - 12:00:00
LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU

ABSTRACT:
A typical way to update map road layers is to compare recent aerial images with existing map data, detect new roads and add them as cartographic entities to the road layer and such processes vary in the degree to which humans and computers are involved. Semi-automatic methods are preferable in real applications because computer vision algorithm are still not sufficiently robust and reliable and, more importantly, maps require final checking by a human due to the legal implications of errors. In this paper we introduce a road tracking system based on human-computer interactions (HCI) and Bayesian filtering. Bayesian filters, specifically, extended Kalman filters and particle filters, are used in conjunction with human inputs to estimate road axis points and update the tracking algorithms. Experimental results show that this approach is efficient and reliable and that it produces substantial savings over the traditional manual map revision approach.

This is work by Terry Caelli, Jun Zhou and Walter F. Bischof

BIO:
Professor Caelli was awarded his Bachelor of Arts (Hons) in Mathematics and Psychology in 1972 and his PhD in 1975 from the University of Newcastle, Australia.

Prior to joining NICTA and over the past twenty five years, Professor Caelli has been Killam Professor of Science and Professor of Computing Science at the University of Alberta, Canada; Acting Director of the NASA Center for Mapping at Ohio State University, USA; Professor of Computer Science at the University of Melbourne and Curtin University, Australia. Professor Caelli’s interests lie in: 1. Imaging spectroscopy and thermal imaging involving the 3D mapping of materials or sources of heat emitted from objects; 2. Intelligent cartography, in particular, the advancement of computer-aided map revision; 3. The improvement of current SQL for GIS for the development of query technologies that can probe more deeply into spatial databases and support complex domain-specific queries and spatio-temporal data matching.

These topics involve Computer Vision, Machine Learning and Structural Pattern Recognition.

Professor Caelli is leading the SISM: Spectral Imaging and Source Mapping project. This project focuses on the development of new methods for 3D mapping of materials from stereo hyperspectral cameras or sources of heat emitted from objects as detected by quantitative thermography. Applications vary from process control to environmental monitoring as well as uses in health.

MEDIA:
051104_caelli.pdf
051104_caelli_video_redirect.html

	Skip Navigation CECS Home \| ANU Home \| Search ANU \| HORUS \| Staff Home
	Seminars @ CECS ANU College of Engineering and Computer Science