ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper 적응적인 패치 기반의 3차원 복원 알고리즘
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
유정재, 박창준
Issue Date
2017-11
Citation
대한전자공학회 종합 학술 대회 (추계) 2017, pp.585-588
Publisher
대한전자공학회
Language
Korean
Type
Conference Paper
Abstract
In this paper, we propose an improved method to generate a dense point cloud for generating a 3D scene model from images captured by UAV. Based on the PMVS approach, the proposed method improves the uniformity of the patch cloud by adaptively changing the size of the image region used for photometric discrepancy computation according to the texture characteristics. Adaptive patch also solves hole problems in textureless region while it does not lead to a large increase in computation time. Experimental results show that the proposed method can improve the performance of 3D dense point generation compared to the previous method.
KSP Keywords
3D scene, Dense point cloud, Improved method, Texture characteristics, adaptive patch, computation time, textureless region