2D monocular visual odometry using mobile-phone sensors

Abstract

Smartphone equipped with a high-resolution camera and a variety of motion sensors is a lightweight, inexpensive, and flexible choice for micro-unmanned aerial vehicles (micro-UAVs) payloads. In this study, a Samsung Galaxy S3 smartphone is selected as an on-board sensor platform for UAV localization in an environment that does not have the option of Global Positioning System (GPS)-based navigation. A multi-sensor UAV localization scheme is proposed and developed by using the phone built-in camera, pressure sensor, and orientation sensor. The proposed method does not have to reconstruct an environment map. Furthermore, both indoor and outdoor experiments are carried out based on a robot arm and an eight-rotor UAV, respectively. Experimental results validate the effectiveness of the implemented scheme and corresponding algorithms. A video of this work is available at pan.baidu.com/s/10IwQM.