Detail of the student project

Topic:Visual odometry (SLAM) from omnidirectional camera
Department:Katedra kybernetiky
Supervisor:Doc. Ing. Tomáš Svoboda Ph.D.
Announce as:DP,BP,PMI,SOP,PRO
Description: Center for Machine Perception, Department of Cybernetics, contributes to the EU project NIFTi by developing visual algorithms for object/victim detection and robot localization. Among many other sensors, The robot carries an omnidirectional camera on board.

On of the important taks is the robot localization in an unknown terrain. The goal of this work is to develop and implement a real-time robut method for visual based localization of the robot. The method will complement and robustifies the laser based mapping and robot odometry filtering
Instruction:Contact: Tomáš Svoboda
Recommended courses: Computer Vision Methods, Three-Dimensional Computer Vision
Bibliography:F. Fraundorfer and D. Scaramuzza. Visual odometry : Part ii: Matching, robustness, optimization, and applications. Robotics Automation Magazine, IEEE, 19(2):78?90, June 2012.

Y. Ma, S. Soatto, J. Kosecka, and S.S. Sastry. An Invitation to 3-D Vision: From Images to Geometric Models, volume 26 of Interdisciplinary Applied Mathematics Series. Springer, New York, 2010
Realization form:code C/C++; Python
Responsible person: Petr Pošík