Machine vision-based night landing aids for aircraft.

摘要

The development of machine vision based pilot aids to help reduce night approach and landing accidents is explored in this thesis. The techniques developed in this thesis are motivated by the desire to use the available information sources for navigation such as the airport lighting layout, attitude sensors and Global Positioning System to derive more precise aircraft position and orientation information. The fact that airport lighting geometry is known and that images of airport lighting can be acquired by the camera, has lead to the synthesis of machine vision based algorithms for runway relative aircraft position and orientation estimation.; The main contribution of this research is the synthesis of seven navigation algorithms based on two broad families of solutions. The first family of solution methods consists of techniques that reconstruct the airport lighting layout from the camera image and then estimate the aircraft position components by comparing the reconstructed lighting layout geometry with the known model of the airport lighting layout geometry. The second family of methods is comprised of techniques that synthesize the image of the airport lighting layout using a camera model and estimate the aircraft position and orientation by comparing this image with the actual image of the airport lighting acquired by the camera. Algorithms I through IV belong to the first family of solutions while Algorithms V through VII belong to the second family of solutions. Algorithms I and II are parameter optimization methods, Algorithms III and IV are feature correspondence methods and Algorithms V through VII are Kalman filter centered algorithms. In order to take advantage of the aircraft dynamics and the multiple images available along the glide path, the position estimates provided by Algorithms I through IV are used for driving a six-state Kalman filter for providing improved estimates of the aircraft position and inertial velocity components. Algorithms V through VII are Kalman filter centered algorithms and are designed to implicitly utilize the aircraft dynamics and the multiple images available along the glide path. Additionally, Algorithm VI integrates the position information derived from a Global Positioning System receiver.; Results of computer simulations are presented to demonstrate the performance of all the seven algorithms developed in this thesis. It is shown that all the algorithms meet some or all of the Federal Aviation Administration specified navigation accuracy requirements for various landing categories. These results show that it is feasible to design an accurate machine vision based night landing aid with the currently available technology.