Visual odometry for unmanned aerial vehicle localization and image mosaicking | |
| Author | Kunwar, Saket |
| Call Number | AIT Thesis no.CS-13-03 |
| Subject(s) | Multisensor data fusion Mobile robots Real-time data processing |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | This thesis presents an approach to solving Simultaneous Localization And Mapping (SLAM) in real-time for an Unmanned Aerial Vehicle (UAV) . Pose Graph based sensor fusion from the sensors available in Parrot Ardrone—a cheap and popular UAV— along with Visual Odometery from the downward facing camera forms the basis for UAV localization. Evalua tion and selection of feature detector and descriptor suitable for an online solution also forms a major theme. Simultaneously the downward facing camera creates a mosaic of the terrain environment. This solution paves the way for further robotic application, specifically those that finds a mosaic valuable. This thesis demonstrates an implementation within the Robot Operating System (ROS) framework; using incremental smoothing and mapping to provide an effective online solution for application such as search and rescue. |
| Year | 2013 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Manukid Parnichkun;Nagai, Masahiko; |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2013 |