ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Effectively Exploiting Distortion of Structured Light Pattern for Capturing Depth Discontinuities
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Ji Young Park, Cheol Hwon Kim, Jae Keun Na, June Ho Yi
Issue Date
2007-01
Citation
Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2007, pp.29-34
Language
English
Type
Conference Paper
Abstract
Depth discontinuities (aka depth edges) play a very important role in many appearance based approaches to computer vision problems because they represent object contours. This research shows that structured light imaging can efficiently be used to capture depth edges without 3D reconstruction. We strategically project structured light and exploit distortion of light pattern in the structured light image along depth discontinuities to reliably detect depth edges. However, in reality, distortion along depth discontinuities may not occur or be large enough to detect depending on the distance from the camera or projector. We have presented the method that guarantee the occurrence of the distortion along depth discontinuities for a continuous range of object location. Experimental results show that the proposed methods accurately detect depth edges of shapes of human hand and body as well as general objects.
KSP Keywords
3D Reconstruction, Computer Vision(CV), Depth edges, Human hand, Light pattern, Object location, Structured light, appearance-based, object contours