期刊
COMPUTER VISION AND IMAGE UNDERSTANDING
卷 145, 期 -, 页码 95-110出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.cviu.2015.12.003
关键词
Optical flow; Neighborhood descriptors; Bilateral filtering; Image registration; Endoscopic image mosaicing
资金
- Agence nationale de la recherche (ANR)
- Conseil Regional de Lorraine (CRL) [ANR-11-TECS-001]
Total variational (TV) methods using l(1)-norm are efficient approaches for optical flow determination. This contribution presents a multi-resolution TV-l(1) approach using a data-term based on neighborhood descriptors and a weighted non-local regularizer. The proposed algorithm is robust to illumination changes. The benchmarking of the proposed algorithm is done with three reference databases (Middlebury, KITTI and MPI Sintel). On these databases, the proposed approach exhibits an optimal compromise between robustness, accuracy and computation speed. Numerous tests performed both on complicated data of the reference databases and on challenging endoscopic images acquired under three different modalities demonstrate the robustness and accuracy of the method against the presence of large or small displacements, weak texture information, varying illumination conditions and modality changes. (C) 2015 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据