BMDCNet: A Satellite Imagery Road Extraction Algorithm Based on Multilevel Road Feature

• Published in: IEEE geoscience and remote sensing letters Vol. 21; pp. 1 - 5
• Main Authors: Wang, Chenggong, Lu, Junyu, Chen, Zehua
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Attention mechanism; Computational modeling; Context; contextual information; Convolution; Data mining; Datasets; Decoding; dynamic convolution; Feature extraction; Information processing; Kernel; Modules; Multilevel; multiscale feature; Remote sensing; road extraction; Roads; Roads & highways; Satellite imagery; Semantics; Source code; Strips; Urban planning; Vehicle dynamics; United States > US; Massachusetts
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2024.3485680

Multilevel road feature extraction from remote sensing image plays an important role in numerous applications such as autonomous driving and urban planning. However, interference from background, occlusions, and road-like information makes it difficult to distinguish different levels of roads. To address these issues, this study proposes a deep network named BMDCNet, which adopts LinkNet as the baseline model. The bidirectional multilevel road feature dynamic fusion (BMDF) module is designed to replace the simple skip connections, which greatly reduce the semantic gap between the encoder and the decoder. Furthermore, the dual context dynamic extraction (DCDE) module is designed to dynamically extract and integrate global and local multiscale context information. Finally, experiments are conducted on the DeepGlobe road extraction dataset and the Massachusetts roads dataset. The results demonstrate that compared with LinkNet, F1 and IoU of BMDCNet increased by 1.79% and 2.68% on DeepGlobe, and by 0.35% and 0.47% on Massachusetts, respectively. Our source code is available at https://github.com/ZehuaChenLab/BMDCNet .