Abstract

In this paper we present an on-board Computer Vision System for the pose estimation of an Unmanned Aerial Vehicle (UAV)with respect to a human-made landing target. The proposed methodology is based on a coarse-to-fine approach to searchthe target marks starting from the recognition of the characteristics visible from long distances, up to the inner details whenshort distances require high precisions for the final landing phase. A sequence of steps, based on a Point-to-Line Distancemethod, analyzes the contour information and allows the recognition of the target also in cluttered scenarios. The proposedapproach enables to fully assist the UAV during its take-off and landing on the target, as it is able to detect anomaloussituations, such as the loss of the target from the image field of view, and the precise evaluation of the drone attitude whenonly a part of the target remains visible in the image plane. Several indoor and outdoor experiments have been carriedout to demonstrate the effectiveness, robustness and accuracy of developed algorithm. The outcomes have proven that ourmethodology outperforms the current state of art, providing high accuracies in estimating the position and the orientation oflanding target with respect to the UAV.

Autore Pugliese

• Petitti Antonio , D'orazio Tiziana Rita

Tutti gli autori

• C. Patruno; M. Nitti; A. Petitti; E. Stella; T. D'Orazio

Titolo volume/Rivista

Journal of intelligent & robotic systems

Anno di pubblicazione

2018

ISSN

1573-0409

ISBN

Non Disponibile

Numero di citazioni Wos

Nessuna citazione

Ultimo Aggiornamento Citazioni

Non Disponibile

Numero di citazioni Scopus

Non Disponibile

Ultimo Aggiornamento Citazioni

Non Disponibile

Settori ERC

Non Disponibile

Codici ASJC

Non Disponibile