© The Institution of Engineering and Technology
An effective technique for applying visual tracking algorithms to omnidirectional image sequences is presented. The method is based on a spherical image representation which allows taking into account the distortions and nonlinear resolution of omnidirectional images. Experimental results show that both deterministic and probabilistic tracking methods can effectively be adapted in order to robustly track an object with an omnidirectional camera.
References
-
-
1)
-
Mei, C., Benhimane, S., Malis, E., Rives, P.: `Homography-based tracking for central catadioptric cameras', Proc. Int. Conf. on Intelligent Robots and Systems, 2006, Beijing, China, p. 669–674.
-
2)
-
Marchand, E., Chaumette, F.: `Fitting 3d models on central catadioptric images', Proc IEEE Int. Conf. on Robotics and Automation, 2007, Rome, Italy, p. 52–58.
-
3)
-
Demonceaux, C., Vasseur, P.: `Omnidirectional image processing using geodesic metric', Proc. Int. Conf. on Image Processing, 2009, p. 221–224.
-
4)
-
Comaniciu, D., Ramesh, V., Meer, P.: `Real-time tracking of non-rigid objects using mean shift', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2000, Hilton Head Kland, SC, USA, p. 142–149.
-
5)
-
M. Isard ,
A. Blake
.
Condensation-conditional density propagation for visual tracking.
Int. J. Comput. Vis.
,
1 ,
5 -
28
-
6)
-
Wallhoff, F., Zobl, M., Rigoll, G., Potucek, I.: `Face tracking in meeting room scenarios using omnidirectional views', Proc. IEEE Conf. on Pattern Recognition, 2004, Washington, DC, USA, p. 933–936, Vol. 4.
-
7)
-
Lucas, B.D., Kanade, T.: `An iterative image registration technique with an application to stereo vision', Proc. Int. Joint Conf. on Artificial Intelligence, 1981, Vancouver, Canada, p. 674–859.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2011.2838
Related content
content/journals/10.1049/el.2011.2838
pub_keyword,iet_inspecKeyword,pub_concept
6
6