Mobile Localization and Mapping using Visual Features

Master Thesis

About This Topic

To enable autonomous flight of a unmanned aerial vehicle (UAV), the UAV must be aware of its position and orientation in space. This remains a challenge when performing autonomous flight in GPS denied environments, such as buildings. This topic is integrated into the Smartcopter research project (https://www.ims.tuwien.ac.at/projects/smartcopter) with its major goal to equip a simple quadcopter with a state of the art handheld device (ie. smartphone or tablet) to perform all operations for autonomous flight on-board.

The main task of this topic is to integrate existing state of the art visual localization and mapping algorithms on a mobile device. The camera of the mobile device is used for natural feature tracking and mapping. The entire system is tested for performance, latency and volume coverage. A solid background in programming is necessary, background in mobile computing and computer vision is an asset. The topic is ideal to gain a deeper understanding in visual feature tracking, SLAM, mobile computing and robotics.

Programming: C/C++, Java

SDKs/Platforms: Android, ROS, ..

Note: this topic can also be started as a practicum and extended to be completed as master thesis.