Inference of flight angles associating the flight images movement with camera parameters

Abstract

Flight Critical Parameters of an aerial vehicle — Angles of Pitch, Yaw and Roll — are those that describe the movement of a vehicle in any three-dimensional space. This paper presents a visual estimation of Flight Critical Parameters, through an association between two camera parameters — Focal Length and Optical Center — with the information about the movement of flight image. This movement information is an integration of two informations: Horizon Line position and orientation; and Image Optical Flow. The need of integration of movement estimation techniques is the following: the angles estimation using Horizon information is used with efficiency in several related works, but this approach does not enable yaw angle estimation. Optical Flow approach enables the estimation of all of the angles and can be used without the presence of Horizon on the vision field, but can fail in some scenarios. Preliminary experiments made with flight video and IMU data of a fixed-wing aircraft proved the efficiency of the presented method.