| Y. Ye and J.K. Tsotsos. Sensor planning for 3d object search. CVIU, 73(2):145--168, February 1999. |
....appearance based methods, which avoid segmentation, lead to more robust recognition modules than methods which are restricted to geometric primitives, like point or line features. This result has also motivated the approach proposed in this paper. The selection of viewpoints depends on two facts [25, 23]: on the one hand the view can be selected which is the most probable and stable view of an object, and on the other hand the viewpoint shows the 2 D projection which allows the best distinction of considered objects with respect to the model database. The mathematical fundamentals for likelihood ....
J. K. Tsotsos and Y. Ye. Sensor planning in 3d object search. In Proceedings of the 4th International Symposium on Intelligent Robotic Systems, pages 131--136. IEEE Computer Society Press, July 1996.
No context found.
Y. Ye and J.K. Tsotsos. Sensor planning for 3d object search. CVIU, 73(2):145--168, February 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC