ELSM: Evidence-Based Line Segment Merging
Authors:
- 23 March 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 67 (7) , 2498-2514
Abstract
Existing line segment detectors break perceptually contiguous linear structures into multiple line segments. This can be offset by re-merging the segments, but existing merging algorithms over-merge and produce globally incorrect segments. Geometric cues are necessary but not sufficient for deciding whether to merge two segments or not. By restricting the result of any merging decision to have underlying image support, we reduce over-merging and globally incorrect segments. We propose a novel measure for evaluating merged segments based on line segment Hausdorff distance. On images from YorkUrbanDB, we show that our algorithm improves both qualitative and quantitative results obtained from four existing line segment detection methods and is better than two existing line segment merging methods. Our method does not suffer from inconsistent results produced by four recent deep learning-based models. The method is easily customisable to work for line drawings such as hand-drawn maps to obtain vectorized representations.Keywords
Funding Information
- Higher Education Commission National Research Program for Universities (8329)
This publication has 35 references indexed in Scilit:
- Background grid extraction from historical hand-drawn cadastral mapsInternational Journal on Document Analysis and Recognition (IJDAR), 2023
- Hierarchical line segment matching for wide-baseline images via exploiting viewpoint robust local structure and geometric constraintsISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Line-based visual odometry using local gradient fittingJournal of Visual Communication and Image Representation, 2021
- Fast vision‐based autonomous detection of moving cooperative target for unmanned aerial vehicle landingJournal of Field Robotics, 2018
- Structure from Motion with Line Segments Under Relaxed Endpoint ConstraintsInternational Journal of Computer Vision, 2016
- Structure and motion from line correspondences: Representation, projection, initialization and sparse bundle adjustmentJournal of Visual Communication and Image Representation, 2014
- Accurate segmentation of land regions in historical cadastral mapsJournal of Visual Communication and Image Representation, 2014
- Shape from Angle Regularity2012
- Uniqueness of Solutions to Structure and Motion from Combinations of Point and Line CorrespondencesJournal of Visual Communication and Image Representation, 1996
- Morphological Extraction of Line Networks from Noisy Low-Contrast ImagesJournal of Visual Communication and Image Representation, 1995