Title :
Occlusion Processing Method Using Improved Object Contour Extraction Algorithm by Neighboring Edge Search and MER in Simulation
Author :
Cha, JeongHee ; Shin, HyunCheul
Author_Institution :
Div. of Inf. & Comput., BaekSeok Coll. of Cultural Studies, Cheonan
Abstract :
For realistic simulation, it is essential to determine the occlusion areas of the virtual object produces after registering real image and virtual object exactly. In this paper, we proposed the new method to solve occlusions using improved object contour extraction by neighboring edge search and MER (minimum enclosing rectangle). We acquire the detailed contour of complex objects by proposed algorithms and extract the three dimensional information of the position using picking algorithm. We use MER to determine the occlusion area for performance improvement. In the experiment, we compared proposed algorithms with existed method and proved the effectiveness in the environment which partial occlusions happen.
Keywords :
feature extraction; hidden feature removal; image registration; stereo image processing; 3D information extraction; image registration; minimum enclosing rectangle; neighboring edge search; object contour extraction; occlusion processing method; partial occlusions; picking algorithm; realistic simulation; virtual object; Data mining; Gradient Vector Flow; MER; Neighboring Edge Search; Object Contour Extraction Algorithm; Occlusion; Simulation;
Conference_Titel :
Convergence and Hybrid Information Technology, 2008. ICHIT '08. International Conference on
Conference_Location :
Daejeon
Print_ISBN :
978-0-7695-3328-5
DOI :
10.1109/ICHIT.2008.298