CVMar 10, 2020

Deep Hough Transform for Semantic Line Detection

arXiv:2003.04676v4233 citations
AI Analysis

This addresses the problem of detecting meaningful line structures for computer vision applications, offering a novel approach that is incremental in combining existing techniques.

The paper tackles semantic line detection in natural scenes by integrating the classical Hough transform into deep learning, proposing a one-shot end-to-end framework that transforms line detection into spotting points in a parametric domain, leading to improved efficiency and performance over state-of-the-art methods on a new large-scale dataset and a public dataset.

We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e. non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features eg features along lines close to a specific line, that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes