ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Real-Time Video Photomosaics with Optimized Image Set and GPU
Cited 6 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
최윤석, 정순철, 김재우, 구본기
발행일
201409
출처
Journal of Real-Time Image Processing, v.9 no.3, pp.569-578
ISSN
1861-8200
출판사
Springer
DOI
https://dx.doi.org/10.1007/s11554-013-0384-8
협약과제
13VT1700, 방통융합형 Full 3D 복원 기술 개발(표준화연계), 구본기
초록
We propose a real-time approach to automatically generate photomosaic videos from a set of optimized images by taking advantage of CUDA GPU acceleration. Our approach divides an input image into smaller cells-usually rectangular cells-and replaces each cell with a small image of an appropriate color pattern. Photomosaics require a large set of tile images with a variety of patterns to create high-quality digital mosaic images. Because a large database of images requires longer processing time and larger storage space for searching patterns from the database, this requirement causes problems in developing a real-time system or mobile applications that have limited resources. This paper deals with a real-time video photomosaics using genetic feature selection method for building an optimized image set and taking advantage of CUDA to accelerate pattern searching that minimizes computation cost. © 2013 Springer-Verlag Berlin Heidelberg.
키워드
CUDA, Genetic feature selection, Non-photorealistic rendering, Photomosaics, Real-time
KSP 제안 키워드
CUDA GPU, Computation cost, Feature selection(FS), GPU Acceleration, Genetic feature selection, High-quality, Limited resources, Mobile Application(APP), Pattern searching, Real-time video, Rectangular cells