MultiLineStringNet: a deep neural network for linear feature set recognition

ABSTRACT

Pattern recognition of linear feature sets, such as river networks, road networks, and contour clusters, is essential in cartography and geographic information science. Previous studies have investigated many methods to identify the patterns of linear feature sets; the key to each of these studies is to generate a reasonable and computable representation for each set. However, most existing methods are only designed for a specific task or data type and cannot provide a general solution for formalizing linear feature sets owing to their complex geometric characteristics, spatial relations and distributions. In addition, some methods require human involvement to specify characteristics, choose parameters, and determine the weights of different measures. To reduce human intervention and improve adaptability to various feature types, this paper proposes a novel deep learning architecture for learning the representations of linear feature sets. The presented model accepts vector data directly without extra data conversion and feature extraction. After generating local, neighborhood, and global representations of inputs, the representations are aggregated accordingly to perform pattern recognition tasks, including classification and segmentation. In the experiments, building groups classification and road interchanges segmentation achieved accuracies of 98% and 89%, respectively, indicating the model’s effectiveness and adaptability.

KEYWORDS:

• Linear feature set
• pattern recognition
• deep learning
• building group classification
• road interchange detection

Acknowledgments

The authors sincerely thank the editors and the anonymous reviewers for their valuable feedback and insightful comments.

Disclosure statement

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

Data availability statement

The data and code that support the findings of this study are available with the identifier at the public link (https://doi.org/10.6084/m9.figshare.21789881).

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [41930101, 42161066], Gansu Provincial Department of Education: The “Innovation Star” Project of Excellent Postgraduates [2023CXZX-506] and the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, No. [KF-2022-07-015].