A Siamese neural network for learning the similarity metrics of linear features

Abstract

Measuring similarity is essential for classifying, clustering, retrieving, and matching linear features in geospatial data. However, the complexity of linear features challenges the formalization of characteristics and determination of the weight of each characteristic in similarity measurements. Additionally, traditional methods have limited adaptability to the variety of linear features. To address these challenges, this study proposes a metric learning model that learns similarity metrics directly from linear features. The model’s ability to learn allows no pre-determined characteristics and supports adaptability to different levels of complex linear features. LineStringNet functions as a feature encoder that maps vector lines to embeddings without format conversion or feature engineering. With a Siamese architecture, the learning process minimizes the contrastive loss, which brings similar pairs closer and pushes dissimilar pairs away in the embedding space. Finally, the proposed model calculates the Euclidean distance to measure the similarity between learned embeddings. Experiments on common linear features and building shapes indicated that the learned similarity metrics effectively supported retrieving, matching, and classifying lines and polygons, with higher precision and accuracy than traditional measures. Furthermore, the model ensures desired metric properties, including rotation and starting point invariances, by adjusting labeling strategies or preprocessing input data.

Keywords:

• Linear feature
• similarity
• metric learning
• Siamese network
• LineStringNet

Acknowledgments

We sincerely thank the editors and the anonymous reviewers for their valuable comments and suggestions.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

The data and codes that support the findings of this study are available at https://doi.org/10.6084/m9.figshare.14885214

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [41930101, 42161066], LZJTU EP [201806], and 2021 Central-Guided Local Science and Technology Development Fund of Gansu Province: Making and Applications of We-maps Oriented to Public Participation Mapping.

Notes on contributors

Pengbo Li

Pengbo Li is a Ph.D. candidate at the Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, China. His research interests include map generalization, spatial relations and machine learning. He contributed to the idea, methodology, codes, datasets, manuscript writing and revision of the paper.

Haowen Yan

Haowen Yan is a Professor at the Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, China. His research interests include automated map generalization, spatial relations, geovisualization, we-maps and spatial data security. He contributed to the idea, methodology, and revision of the paper.

Xiaomin Lu

Xiaomin Lu is an Associate Professor at the Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, China. Her research interests include map generalization and spatial relations. She contributed to dataset preparation and reviewed the manuscript.