MAD-UNet: A Multi-Region UAV Remote Sensing Network for Rural Building Extraction
Sensors · 09.04.2024 · 24 (8) · 2393
DOI: 10.3390/s24082393 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.04.2024. Verfasst von Hang Xue und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ke Liu, North China Institute of Aerospace Engineering Doctoral Fund: Research on Spatio-Temporal Data Fusion Analysis of Beijing-Tianjin-Hebei City Cluster.
Abstract (Originalsprache)
For the development of an idyllic rural landscape, an accurate survey of rural buildings is essential. The extraction of rural structures from unmanned aerial vehicle (UAV) remote sensing imagery is prone to errors such as misclassifications, omissions, and subpar edge detailing. This study introduces a multi-scale fusion and detail enhancement network for rural building extraction, termed the Multi-Attention-Detail U-shaped Network (MAD-UNet). Initially, an atrous convolutional pyramid pooling module is integrated between the encoder and decoder to enhance the main network’s ability to identify buildings of varying sizes, thereby reducing omissions. Additionally, a Multi-scale Feature Fusion Module (MFFM) is constructed within the decoder, utilizing superficial detail features to refine the layered detail information, which improves the extraction of small-sized structures and their edges. A coordination attention mechanism and deep supervision modules are simultaneously incorporated to minimize misclassifications. MAD-UNet has been tested on a private UAV building dataset and the publicly available Wuhan University (WHU) Building Dataset and benchmarked against models such as U-Net, PSPNet, DeepLabV3+, HRNet, ISANet, and AGSCNet, achieving Intersection over Union (IoU) scores of 77.43% and 91.02%, respectively. The results demonstrate its effectiveness in extracting rural buildings from UAV remote sensing images across different regions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Remote Sensing and Information Engineering, North China Institute of Aerospace Engineering, Langfang 065000, China.
- Hebei Collaborative Innovation Center of Space Remote Sensing Information Processing and Application, Langfang 065000, China.
ORCID-Profile: Yumeng Wang
Förderung
- Ke Liu
- North China Institute of Aerospace Engineering Doctoral Fund: Research on Spatio-Temporal Data Fusion Analysis of Beijing-Tianjin-Hebei City Cluster
Zitieren
APA
Xue, H., Liu, K., Wang, Y., Chen, Y., Huang, C., Wang, P., & Li, L. (2024). MAD-UNet: A Multi-Region UAV Remote Sensing Network for Rural Building Extraction. Sensors, 24(8), 2393. https://doi.org/10.3390/s24082393
Vancouver
Xue H, Liu K, Wang Y, Chen Y, Huang C, Wang P, et al. MAD-UNet: A Multi-Region UAV Remote Sensing Network for Rural Building Extraction. Sensors. 2024;24(8):2393. doi:10.3390/s24082393
BibTeX
@article{Xue2024,
author = {Xue, Hang and Liu, Ke and Wang, Yumeng and Chen, Yuxin and Huang, Caiyi and Wang, Pengfei and Li, Lin},
title = {MAD-UNet: A Multi-Region UAV Remote Sensing Network for Rural Building Extraction},
journal = {Sensors},
year = {2024},
volume = {24},
number = {8},
pages = {2393},
doi = {10.3390/s24082393}
}
EUVIMED