WLD: A Wavelet and Learning based Line Descriptor for Line Feature Matching

Thumbnail Image
Date
2020
Authors
Lange, Manuel
Raisch, Claudio
Schilling, Andreas
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present a machine learning based and wavelet enhanced line feature descriptor for line feature matching. Therefor we trained a neural network to compute a descriptor for a line, given preprocessed information from the image area around the line. In the preprocessing step we utilize wavelets to extract meaningful information from the image for the descriptor. This process is inspired by the human vision system. We used the Unreal Engine 4 and multiple different freely available scenes to create our training data. We conducted the evaluation on ground truth labeled images of our own and from the Middlebury Stereo Dataset. To show the advancement of our method in terms of matching quality, we compare it to the Line Band Descriptor (LBD), to the Deep Learning Based Line Descriptor (DLD), which we used as a starting point for this work, and to the Learnable Line Segment Descriptor for Visual SLAM (LLD). We publish the project on github to support the community: https://github.com/manuellange/WLD
Description

        
@inproceedings{
10.2312:vmv.20201186
,
booktitle = {
Vision, Modeling, and Visualization
},
editor = {
Krüger, Jens and Niessner, Matthias and Stückler, Jörg
},
title = {{
WLD: A Wavelet and Learning based Line Descriptor for Line Feature Matching
}},
author = {
Lange, Manuel
 and 
Raisch, Claudio
 and 
Schilling, Andreas
},
year = {
2020
},
publisher = {
The Eurographics Association
},
ISBN = {
978-3-03868-123-6
},
DOI = {
10.2312/vmv.20201186
}
}
Citation
URI
https://doi.org/10.2312/vmv.20201186
 https://diglib.eg.org:443/handle/10.2312/vmv20201186
Collections
VMV2020