Recovering Occlusion Boundaries from an Image
Recovering Occlusion Boundaries from an Image
复制标题
DOI：
10.1007/s11263-010-0400-4
复制
发表时间：
2011-02
影响因子：
19.5
通讯作者：
Derek Hoiem;Alexei A. Efros;M. Hebert
中科院分区：
文献类型：
--
作者：
Derek Hoiem;Alexei A. Efros;M. Hebert
遮挡推理是计算机视觉中的一个基本问题。在本文中，我们提出了一种算法来恢复场景中独立结构的遮挡边界和深度排序。我们的方法不是将问题视为纯粹的图像处理问题，而是使用来自估计表面布局的线索，并使用条件随机场(CRF)模型应用格式塔分组原则。我们提出了一种基于凝聚合并的分层分割过程，该过程随着分割的进行而重新估计边界强度。我们在几何背景数据集上的实验验证了我们对特征的选择、我们对分类器的迭代求精以及我们的CRF模型。在Berkeley分割数据集、Pascal VOC 2008和LabelMe上的实验也表明，训练后的算法可以推广到其他数据集，并可以作为带有图形/背景标签的对象边界预测器。
Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose an algorithm to recover the occlusion boundaries and depth ordering of free-standing structures in the scene. Rather than viewing the problem as one of pure image processing, our approach employs cues from an estimated surface layout and appliesGestaltgrouping principles using a conditional random field (CRF) model. We propose a hierarchical segmentation process, based on agglomerative merging, that re-estimates boundary strength as the segmentation progresses. Our experiments on the Geometric Context dataset validate our choices for features, our iterative refinement of classifiers, and our CRF model. In experiments on the Berkeley Segmentation Dataset, PASCAL VOC 2008, and LabelMe, we also show that the trained algorithm generalizes to other datasets and can be used as an object boundary predictor with figure/ground labels.