Automated Linear Feature Identification and Extraction (ALFIE)
October 1999 - March 2002

Participants
Gary Priestnall (School of Geography, University of Nottingham)
Matt Hatcher, Steve Wallace & Richard Ley (QinetiQ)
Dan Morton, Bill Savage (Laser-Scan Ltd)

Funding
QinetiQ

Project Overview
The demand for efficient techniques for creating and updating digital maps is high and for many applications the extraction of structured vector road networks at medium to large scales is important. Current methods of ground survey and aerial photographic survey can be expensive and time consuming. Remotely sensed imagery offers a range of geographical information from the regional contextual knowledge provided by low resolution multi-spectral imagery, to the large scale detail offered by digital orthophotography and very high resolution satellite sensors. Tools to automate stages of the process of linear feature extraction from imagery are required. An approach to feature extraction was developed through the ALFIE project which uses an object-oriented data model as the framework to store contextual knowledge and to use this in the control of feature extraction routines. One of the main study areas was around Worcester, UK (below).

Research Outcomes

Priestnall, G., Hatcher, M. J., Morton, R. D., Wallace, S. J., Ley R. G. (2004) A framework for automated extraction and classification of linear networks Photogrammetric Engineering and Remote Sensing 70, 12, 1373-1382

Wallace, S.J., Hatcher, M.J., Ley, R.G., Priestnall, G., Morton, R. D. (2002) Automatic differentiation of linear features extracted from remotely sensed imagery Österreichische Zeitschrift für Vermessung und Geoinformation, Heft 3+4, 17 – 29

Wallace,S.J, Hatcher,M.J, Priestnall,G., and Morton, R.D (2001) Research into a framework for automatic linear feature identification and extraction" in Baltsavias,E.P, Gruen,A. and Van Gool. L [eds] Automatic Extraction of Man-made objects from aerial and space images (III) 381-390. Lisse:Swets & Zeitlinger

Priestnall G. and Wallace S. (2000) Semi-automated linear extraction using a knowledge rich object data model IAPRS, Vol. XXXIII, Amsterdam, 2000

Priestnall, G., and Wallace, S. (2000) Semi-automated linear feature extraction using a knowledge rich object data model International Archives of Photogrammetry and Remote Sensing (IAPRS), Vol. XXXIII, Part 3B:740-747, ISPRS Congress 2000, Amsterdam, 17-13 July 2000

Related Links
www.qinetiq.com