OARENet

open code for "Occlusion-aware road extraction network for high-resolution remote sensing imagery" Here is the coder for SwinTransformer+OADecoder., network code is in networks dir

1. Checking the setting.py
2. python train.py
3. python test_metric.py(check the pixel metric)
4. python large_test.py (infer large remote sensing imagery)

resources of weighted

https://drive.google.com/drive/folders/10re9hvyYdo8H9FR-rvXomlQVl-EnBzqX?usp=drive_link

Citation

Lu X, Zhong Y, Zheng Z, et al. GAMSNet: Globally aware road detection network with multi-scale residual learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 175: 340-352.

版权所有

本方法版权归智能化遥感数据提取分析与应用研究组（RSIDEA：http://rsidea.whu.edu.cn/ ）所有，该研究组隶属于武汉大学测绘遥感信息工程国家重点实验室（LIESMARS）。OARENet仅限于学术目的使用，并需引用以下论文，任何商业用途均被禁止。

R. Yang, Y. Zhong, Y. Liu, X. Lu and L. Zhang, "Occlusion-Aware Road Extraction Network for High-Resolution Remote Sensing Imagery," in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-16, 2024, Art no. 5619316, doi: 10.1109/TGRS.2024.3387945.