期刊
INTERNATIONAL JOURNAL OF COMPUTER VISION
卷 106, 期 1, 页码 31-56出版社
SPRINGER
DOI: 10.1007/s11263-013-0640-1
关键词
Junction detection; Scale characterization; a-contrario method; Scale-invariant keypoints; Contrast invariance
资金
- ANR project Callisto
- FUI project CEDCA
Accurate junction detection and characterization are of primary importance for several aspects of scene analysis, including depth recovery and motion analysis. In this work, we introduce a generic junction analysis scheme. The first asset of the proposed procedure is an automatic criterion for the detection of junctions, permitting to deal with textured parts in which no detection is expected. Second, the method yields a characterization of L-, Y- and X- junctions, including a precise computation of their type, localization and scale. Contrary to classical approaches, scale characterization does not rely on the linear scale-space. First, an a contrario approach is used to compute the meaningfulness of a junction. This approach relies on a statistical modeling of suitably normalized gray level gradients. Then, exclusion principles between junctions permit their precise characterization. We give implementation details for this procedure and evaluate its efficiency through various experiments.
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