13 July 1994 Experimental results in autonomous landing approaches by dynamic machine vision
Author Affiliations +
Abstract
The 4-D approach to dynamic machine vision, exploiting full spatio-temporal models of the process to be controlled, has been applied to on board autonomous landing approaches of aircraft. Aside from image sequence processing, for which it was developed initially, it is also used for data fusion from a range of sensors. By prediction error feedback an internal representation of the aircraft state relative to the runway in 3-D space and time is servo- maintained in the interpretation process, from which the control applications required are being derived. The validity and efficiency of the approach have been proven both in hardware- in-the-loop simulations and in flight experiments with a twin turboprop aircraft Do128 under perturbations from cross winds and wind gusts. The software package has been ported to `C' and onto a new transputer image processing platform; the system has been expanded for bifocal vision with two cameras of different focal length mounted fixed relative to each other on a two-axes platform for viewing direction control.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ernst Dieter Dickmanns, Stefan Werner, S. Kraus, and R. Schell "Experimental results in autonomous landing approaches by dynamic machine vision", Proc. SPIE 2220, Sensing, Imaging, and Vision for Control and Guidance of Aerospace Vehicles, (13 July 1994); doi: 10.1117/12.179615; https://doi.org/10.1117/12.179615
PROCEEDINGS
10 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Scanpath-based model for visual tracking of telerobots
Proceedings of SPIE (June 01 2000)
Mosaics from video with burned-in metadata
Proceedings of SPIE (May 09 2005)
Computer vision system for three-dimensional inspection
Proceedings of SPIE (November 08 1994)
Approximation-based video tracking system
Proceedings of SPIE (June 30 1991)

Back to Top