Geometric Image Parsing in Man-Made Environments
Geometric Image Parsing in Man-Made Environments
复制标题
DOI：
10.1007/s11263-011-0488-1
复制
发表时间：
2010-09
影响因子：
19.5
通讯作者：
E. Tretyak;O. Barinova;Pushmeet Kohli;V. Lempitsky
中科院分区：
文献类型：
--
作者：
E. Tretyak;O. Barinova;Pushmeet Kohli;V. Lempitsky
我们提出了一个新的基于优化的解析框架，用于对来自人造环境的单个图像进行几何分析。该框架将场景建模为从低层（边缘）到中层（线段、线和消失点）再到高层（天顶和地平线）跨越不同层的几何图元的组合。因此，这种模型中的推理联合且同时估计（a）将边缘分组为线段，（b）将线段分组为直线，（c）将线分组为平行族，以及（d）图像中地平线和天顶的定位。B。这样的统一处理意味着不确定性信息在模型的层之间传播。这与大多数以前解决同一问题的方法相反，这些方法要么忽略中间层（线段或线），要么使用自底向上的逐步流水线。为了评估，我们考虑了公开可用的约克城市“曼哈顿”场景数据集，并引入了一个新的，更难的103个城市户外图像数据集，其中包含许多非曼哈顿场景。地平线估计任务的比较评估表明，我们的方法相比，目前最先进的方法达到更高的精度和鲁棒性。
We present a new optimization based parsing framework for the geometric analysis of a single image coming from a man-made environment. This framework models the scene as a composition of geometric primitives spanning different layers from low level (edges) through mid-level (lines segments, lines and vanishing points) to high level (the zenith and the horizon). The inference in such a model thus jointly and simultaneously estimates (a) the grouping of edges into the line segments, (b) the grouping of line segments into the straight lines, (c) the grouping of lines into parallel families, and (d) the positioning of the horizon and the zenith in the image. Such a unified treatment means that the uncertainty information propagates between the layers of the model. This is in contrast to most previous approaches to the same problem, which either ignore the middle levels (line segments or lines) all together, or use the bottom-up step-by-step pipeline.For the evaluation, we consider a publicly available York Urban dataset of “Manhattan” scenes, and also introduce a new, harder dataset of 103 urban outdoor images containing many non-Manhattan scenes. The comparative evaluation for the horizon estimation task demonstrate higher accuracy and robustness attained by our method when compared to the current state-of-the-art approaches.