Landscape analysis system using 3D stereoscopic for drone

Abstract

Autonomous drone is the Unmanned Aerial Vehicle (UAV) that did not have human control when operated. But if the drone encounter problem and cannot continue the mission, it has to land and wait for recover. It need to analyze the safety of landing area. This paper proposes the method to analyze the landing area of the drone using cross-correlation of the 3D stereoscopic image. The output of cross-correlation will be taken by polynomial equation. The polynomial coefficient is considered as the parameters for analyzing the landing Landscape. 120 images are used to train and set the parameters. To evaluate the system performance, 40 images from real environments are tested. The experimental result shows that the proposed system can correctly analyze the landing landscape as 92.5%.