Thesis (Selection of subject)Thesis (Selection of subject)(version: 390)
Thesis details
   Login via CAS
Visual odometry from omnidirectional camera
Thesis title in Czech: Visual odometry from omnidirectional camera
Thesis title in English: Visual odometry from omnidirectional camera
Key words: vizuální odometrie, spherická aproximace, odhad pohybu kamery.
English key words: visual odometry, spherical approximation, camera motion estimation.
Academic year of topic announcement: 2012/2013
Thesis type: diploma thesis
Thesis language: angličtina
Department: Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
Supervisor: Tomáš Svoboda
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 24.04.2012
Date of assignment: 02.05.2012
Confirmed by Study dept. on: 02.04.2013
Date and time of defence: 15.05.2013 09:00
Date of electronic submission:14.04.2013
Date of submission of printed version:12.04.2013
Date of proceeded defence: 15.05.2013
Opponents: RNDr. David Obdržálek, Ph.D.
 
 
 
Guidelines
A mobile robot that is being developed for urban search and rescue
(USAR) is equipped with various sensors including an omnidirectional
camera. Propose an algorithm for visual odometry - estimation of
camera (robot) motion from omnidirectional images. Take advantage of
omnidirectional data. Convenient geometrical properties of the
omnidirectional camera can possibly stabilize the usually
ill-conditioned problem. Implement the algorithm within Robot
Operating System (ROS) middleware on the robot and evaluate on real
data.
References
[1] Ma, Y. and Soatto, S. and Košecká, J. and Sastry,
S.S. An Invitation to 3-D Vision: From Images to Geometric Models,
Springer 2010

[2] Scaramuzza, D. and Fraundorfer, F., Visual Odometry,
Robotics & Automation Magazine, IEEE, vol. 18, No 4

[3] Fraundorfer, F., Scaramuzza, D., Visual Odometry: Part II - Matching,
Robustness, and Applications, IEEE Robotics and Automation Magazine, 2012
(early access article http://dx.doi.org/10.1109/MRA.2012.2182810)

[4] Tardif, J.P. and Pavlidis, Y. and Daniilidis, K. Monocular visual
odometry in urban environments using an omnidirectional camera,
Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ
International Conference on.

[5] Nister, D. and Naroditsky, O. and Bergen, J. Visual odometry for
ground vehicle applications, Journal of Field Robotics, vol 23, No 1

Preliminary scope of work
Vizuální odometrie ze všesměrové kamery
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html