标題: MCTN-Net: A Multiclass Transportation Network Extraction Method Combining Orientation and Semantic Features

作者: Shao, CL (Shao, Chenglin); Li, HF (Li, Huifang); Shen, HF (Shen, Huanfeng)

來源出版物: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 卷: 21 文獻号: 6005205 DOI: 10.1109/LGRS.2024.3372194 Published Date: 2024

摘要: Transportation network extraction based on deep learning has become a hotspot. However, the existing models all aim to distinguish between background and transportation networks, while ignoring the class attributes within the transportation networks. In this letter, we propose a multiclass transportation network extraction network (MCTN-Net) to simultaneously extract railways, roadways, trails, and bridges. Inspired by multitask learning, the network first extracts the orientation and semantic information together by the use of a dense feature shared encoder (DFSE). The orientation and semantic features are then fused in the orientation-guided stacking module (OGSM) to enhance the connection between transportation network pixels. Furthermore, a semantic refinement branch (SRB) is designed to improve the ability to classify different transportation network types through deep supervised fusion and class attention. A multiclass transportation network dataset (MCTN dataset) was constructed and used in the experiments. The experiential results indicate that the proposed method achieves a mean intersection over union (MIoU) of 64.29% and a frequency-weighted intersection over union (FWIoU) of 71.20% without the background, which is significantly better than the other road extraction models and semantic segmentation methods. The code and dataset are available at https://github.com/fzzfRS/MCTN-Net.

作者關鍵詞: Transportation; Semantics; Feature extraction; Bridges; Roads; Rail transportation; Data mining; Multiclass transportation network (MCTN) extraction; orientation learning; semantic feature refinement

地址: [Shao, Chenglin; Li, Huifang; Shen, Huanfeng] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Li, Huifang; Shen, Huanfeng] Wuhan Univ, Collaborat Innovat Ctr Geospatial Technol, Wuhan 430079, Peoples R China.

通訊作者地址: Li, HF (通訊作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

電子郵件地址: chenglinshao@whu.edu.cn; huifangli@whu.edu.cn; shenhf@whu.edu.cn

影響因子：4.8