상세 보기
Near real-time local stereo matching algorithm based on fast guided image filtering
- Hong Gwang-Soo;
- Park Jong-Kweon;
- Kim Byung-Gyu
Citations
WEB OF SCIENCE
0Citations
SCOPUS
10초록
Accuracy and computational complexity are challenges of stereo matching algorithm. Much research has been devoted to stereo matching based on cost volume filtering of matching costs. Local stereo matching based guided image filtering (GIF) has a computational complexity of O(N). A proposed algorithm focuses on reduction of computational complexity using the concept of fast guided image filter, which increase the speed up to O(N=s2) with a sub-sampling ratio s. Experi- mental results using the Middlebury benchmark indicated the proposed algorithm achieved effective local stereo matching with a fast execution time.
키워드
Cost Volume Filtering; Fast Guided Image Filtering; Guided Image Filtering; Local Stereo Matching; Computational complexity; Costs; Fast execution time; Guided images; Local stereo matching; Near-real time; Speed up; Stereo matching; Stereo matching algorithm; Sub-sampling; Stereo image processing
- 제목
- Near real-time local stereo matching algorithm based on fast guided image filtering
- 저자
- Hong Gwang-Soo; Park Jong-Kweon; Kim Byung-Gyu
- 발행일
- 2016-12
- 유형
- Conference Paper
- 저널명
- Proceedings of the 2016 6th European Workshop on Visual Information Processing, EUVIP 2016