In this paper, we developed and validated a three-dimensional (3D) feature-based algorithm for tracking stochastic ship-deck motion at high sea states, specifically Sea-State 6 using data from the Navy SCONE data set. The new vision algorithm was developed from the structure-from-motion technique, which recovers the 3D structure of an object from a series of two-dimensional (2D) images, and was validated using a simulated 3D ship deck attached to a moving Stewart platform. Algorithm performance with different feature detectors and image resolutions was compared. In hand-held tests, the vision algorithm was demonstrated to accurately estimate the pose of a moving ship deck using a quadrotor. Visually degraded conditions were also evaluated; the algorithm was found robust to occlusion and low illumination, but performance reduced somewhat in severe glare. The vision algorithm was then validated in a simple free-flight test. All results were compared with Vicon ground-truth data. Additionally, as the 3D algorithm is computationally demanding, we developed and validated a method to improve the computational speed of the vision algorithm.
Development of Three-Dimensional Feature-Based Vision Algorithm for Ship-Deck Landing
Journal of Aircraft ; 1-13
01.05.2025
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
VISION-BASED DECK STATE ESTIMATION FOR AUTONOMOUS SHIP-BOARD LANDING
British Library Conference Proceedings | 2013
|British Library Conference Proceedings | 2023
|Computer vision scheme for autonomous landing of unmanned helicopter on ship deck
British Library Online Contents | 2007
|Robust Autonomous Ship Deck Landing for Rotorcraft
British Library Conference Proceedings | 2016
|