Vision-based range estimation using helicopter flight data

Abstract

Computer-vision-based methods provide one general approach for obstacle detection and range estimation for pilot assistance during low-altitude flight. Results obtained using helicopter flight data with a feature-based range estimation algorithm are presented. A method for recursively estimating range using a Kalman filter with a monocular sequence of images and knowledge of the camera's motion is described. The helicopter flight experiment and one of four resulting datasets are briefly discussed. The performance of the range estimation algorithm is examined by comparing the range estimates with true range measurements collected during the flight experiment.<>