论文标题
通过带有霍夫层的轻质CNN进行线路检测
Line detection via a lightweight CNN with a Hough Layer
论文作者
论文摘要
线路检测是传统上通过Hough Transform解决的重要计算机视觉任务。但是，随着深度学习的发展，可训练的线路检测方法变得流行。在本文中，我们提出了一个轻巧的CNN，用于使用嵌入式无参数的霍夫层进行线路检测，该层允许网络神经元具有全局带状的接收场。我们认为，传统的卷积网络应用于线路检测任务时有两个固有的问题，并显示了霍夫层如何在网络中插入的问题。此外，我们指出了用于行检测的当前数据集中的一些主要不一致之处。
Line detection is an important computer vision task traditionally solved by Hough Transform. With the advance of deep learning, however, trainable approaches to line detection became popular. In this paper we propose a lightweight CNN for line detection with an embedded parameter-free Hough layer, which allows the network neurons to have global strip-like receptive fields. We argue that traditional convolutional networks have two inherent problems when applied to the task of line detection and show how insertion of a Hough layer into the network solves them. Additionally, we point out some major inconsistencies in the current datasets used for line detection.
