Estimation of Camera 3D-Position to Minimize Occlusions
P. Gil, F. Torres, O. Reinoso
Fourth International Conference on Informatics in Control, Automation and Robotics ICINCO  (Angers (France), 9-12 May)
Ed. Instincc Press  ISBN:978-972-8865-83-2  - 2, 311-317

Abstract:

ESTIMATION OF CAMERA 3D-POSITION TO MINIMIZE OCCLUSIONS

Pablo Gil, Fernando Torres
Department of Physics, Systems Engineering and Signal Theory, University of Alicante, Crta. San Vicente s/n
Alicante, Spain, Pablo.Gil@ua.es, ftorres@dfists.ua.es

Oscar Reinoso
Department of Industrial Systems Engineering, Miguel Hernandez University
Elche, Spain o.reinoso@umh.es

Keywords: Occlusions, Camera viewpoint, Camera pose, Segmentation.

Abstract: Occlusions are almost always seen as undesirable singularities that pose difficult challenges to recognition processes of objects which have to be manipulated by a robot. Often, the occlusions are perceived because the viewpoint with which a scene is observed is not adapted. In this paper, a strategy to determine the location, orientation and position, more suitable so that a camera has the best viewpoint to capture a scene composed by several objects is presented. The estimation for the best location of the camera is based on minimizing the zones of occlusion by the analysis of a virtual image sequence in which is represented the virtual projection of the objects. These virtual projections represent the images as if they were captured by a camera with different viewpoints without moving it.