Deep Hough-Transform Line Priors

Conference Paper (2020)
Author(s)

Y. Lin (TU Delft - Pattern Recognition and Bioinformatics)

S. Pintea (TU Delft - Pattern Recognition and Bioinformatics)

Jan C. Gemert (TU Delft - Pattern Recognition and Bioinformatics)

Research Group
Pattern Recognition and Bioinformatics
DOI related publication
https://doi.org/10.1007/978-3-030-58542-6_20
More Info
expand_more
Publication Year
2020
Language
English
Research Group
Pattern Recognition and Bioinformatics
Volume number
12367
Pages (from-to)
323-340
ISBN (print)
978-3-030-58541-9
ISBN (electronic)
978-3-030-58542-6

Abstract

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.

No files available

Metadata only record. There are no files for this record.