Line detection via a lightweight CNN with a Hough Layer
This work addresses line detection for computer vision applications, but appears incremental as it builds on existing deep learning and Hough Transform methods.
The authors tackled line detection in computer vision by proposing a lightweight CNN with an embedded Hough layer to address inherent problems in traditional convolutional networks, achieving results that demonstrate improved performance, though no concrete numbers are provided in the abstract.
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.