Abstract
We present a vision system based on a monocular camera to track the 3D position and orientation of an Unmanned Aerial Vehicle (UAV) during the landing process aboard a ship. The proposed method uses a 3D model-based approach based on a Particle Filter (PF) with proposal distributions given by an Unscented Kalman Filter (UKF) for the translational motion and filters based on directional statistics for the rotational motion. Our main contributions are (i) the development of a novel 3D model-based tracking architecture based on directional statistics that can be easily adapted to other tracking problems, and (ii) the development of the Unscented Bingham-Gauss Filter (UBiGaF) for rotation estimation. We show the advantages of using directional statistics based filters on 3D model-based tracking in a series of quantitative tests in a challenging simulation scenario with real video data. The obtained position and angular error are compatible with the automatic landing system requirements when using directional statistics. We obtain lower error when using the UBiGaF scheme for the vast majority of the tested combinations.
Highlights
The vast majority of the accidents and incidents with Unmanned Aerial Vehicles (UAVs) occur during take-off or landing [1], [2], since these are the most challenging maneuvres where, typically, an external pilot takes control
We propose one approach to automate the landing maneuver by tracking the pose of the UAV with a monocular Red, Green and Blue (RGB) camera located on the Fast Patrol Boat (FPB) with a processing station to perform the needed Computer Vision (CV) processing tasks
EXPERIMENTAL RESULTS we show results of UAV tracking in a simulated environment using real video footage
Summary
The vast majority of the accidents and incidents with Unmanned Aerial Vehicles (UAVs) occur during take-off or landing [1], [2], since these are the most challenging maneuvres where, typically, an external pilot takes control. In previous work [3] we have proposed a pose tracking framework using a 3D model-based vision system employing the UAV Computer-Aided Design (CAD) model and an Unscented Particle Filter (UPF) based approach using Gaussian noise in the translational component of motion and. The main contributions of this article are (i) the inclusion of directional statistics and correlation between attitude and angular velocity in the UAV tracking field, (ii) the development and analysis of a novel UBiGaF for the state estimation of rotating objects, (iii) the use of directional statistics in 3D model-based tracking and (iv) the comparison of performance between the UPF, the UBiF and the UBiGaF in a simulation environment using real data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
