Title :
Improving environment modelling by edge occlusion surface completion
Author :
Castellani, Umberto ; Livatino, Salvatore ; Fisher, Robert B.
Author_Institution :
Dept. of Informatics, Univ. of Verona, Italy
Abstract :
Reconstruction of 3D models from range images usually focuses on complex objects completely contained in the field of view. Using range images to reconstruct a whole environment is challenging because of many occlusions. The focus of this paper is the reconstruction of the corners and edges of partially occluded simple-shape objects like furniture pieces in a indoor scene. Little research has been done on reconstructing obscured surface parts. We introduce a new approach to detect and complete occlusions. The proposed approach is based on good boundary and surface continuation and explores architectural constraints as well. Results on real images confirmed the improvement of environment modelling and the perception of the scene objects.
Keywords :
distance measurement; edge detection; image reconstruction; image segmentation; 3D model reconstruction; architectural constraints; boundary continuation; complex objects; edge occlusion; edge reconstruction; environment modelling; furniture pieces; image segmentation; indoor scene; occlusion detection; partially occluded objects; range images; simple-shape objects; surface completion; surface continuation; Computer vision; Focusing; Image edge detection; Image reconstruction; Informatics; Layout; Object recognition; Phase detection; Reverse engineering; Surface reconstruction;
Conference_Titel :
3D Data Processing Visualization and Transmission, 2002. Proceedings. First International Symposium on
Print_ISBN :
0-7695-1521-4
DOI :
10.1109/TDPVT.2002.1024138