Efficient 3D Scene Labeling Using Fields of Trees
Efficient 3D Scene Labeling Using Fields of Trees
复制标题
DOI：
10.1109/iccv.2013.380
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
O. Kähler;I. Reid
中科院分区：
文献类型：
--
作者：
O. Kähler;I. Reid
我们解决的问题，三维场景标记的结构化学习框架。与以前使用结构化支持向量机的工作不同，我们采用了最近描述的决策树字段和回归树字段框架，从训练数据中学习条件随机场的一元和二元项。我们表明，这在推理速度方面具有显着的优势，同时保持类似的准确性。我们还证明了经验的重要性，利用先验知识的粗糙场景布局，如地平面的位置的功能，整体标签的准确性。我们展示了如何通过我们的框架自动估计这种粗略的布局，并且这些信息可以用于引导改进的详细标签的准确性。
We address the problem of 3D scene labeling in a structured learning framework. Unlike previous work which uses structured Support Vector Machines, we employ the recently described Decision Tree Field and Regression Tree Field frameworks, which learn the unary and binary terms of a Conditional Random Field from training data. We show this has significant advantages in terms of inference speed, while maintaining similar accuracy. We also demonstrate empirically the importance for overall labeling accuracy of features that make use of prior knowledge about the coarse scene layout such as the location of the ground plane. We show how this coarse layout can be estimated by our framework automatically, and that this information can be used to bootstrap improved accuracy in the detailed labeling.