论文标题
深霍夫转变线先验
Deep Hough-Transform Line Priors
论文作者
论文摘要
在线段检测上的经典工作是基于知识的；它使用精心设计的几何先验，使用图像梯度，像素分组或霍夫变换变体。取而代之的是，当前的深度学习方法消除了所有先前的知识，并通过在大型手动注释数据集上训练深层网络来代替先验。在这里，我们通过使用深层网络来学习功能的同时构建基于经典知识的先验，从而减少对标记数据的依赖。我们通过可训练的霍夫变换块将线路添加到一个深层网络中。 Hough Transform提供了有关全局线参数化的先验知识，而卷积层可以学习局部梯度样线。在线框（Shanghaitech）和York Urban数据集上，我们表明，增加先验知识可以提高数据效率，因为不再需要从数据中学到线路先验。关键字：霍夫变换；全局线先验，线段检测。
Classical work on line segment detection is knowledge-based; it uses carefully designed geometric priors using either image gradients, pixel groupings, or Hough transform variants. Instead, current deep learning methods do away with all prior knowledge and replace priors by training deep networks on large manually annotated datasets. Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features. We add line priors through a trainable Hough transform block into a deep network. Hough transform provides the prior knowledge about global line parameterizations, while the convolutional layers can learn the local gradient-like line features. On the Wireframe (ShanghaiTech) and York Urban datasets we show that adding prior knowledge improves data efficiency as line priors no longer need to be learned from data. Keywords: Hough transform; global line prior, line segment detection.
