Detection of obstacles on runways using ego-motion compensation and tracking of significant features

This paper describes a method for obstacle detection on a runway for autono mous navigation and landing of an aircraft, in presence of extraneous featu res, such as tire-marks. An obstacle is defined as an object, which has a s ignificant motion or height relative to the runway. Suitable features are e xtracted from the image and warping is performed, using approximately known camera and plane parameters, to compensate the ego-motion as far as possib le. Residual disparity after warping is estimated using an optical flow alg orithm. Features are tracked from frame to frame to obtain more reliable es timates of their motion. The residual disparities are used to comet the mot ion parameters with a robust method, where features having large residual d isparities are signaled as obstacles. Nelson's optical flow constraint is p roposed to separate moving obstacles from stationary ones. A Bayesian frame work is used at every stage so that the confidence in the estimates can be determined. (C) 2000 Elsevier Science B.V. All rights reserved.