» Articles » PMID: 38676009

MAD-UNet: A Multi-Region UAV Remote Sensing Network for Rural Building Extraction

Overview
Journal Sensors (Basel)
Publisher MDPI
Specialty Biotechnology
Date 2024 Apr 27
PMID 38676009
Authors
Affiliations
Soon will be listed here.
Abstract

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.

Citing Articles

RCEAU-Net: Cascade Multi-Scale Convolution and Attention-Mechanism-Based Network for Laser Beam Target Image Segmentation with Complex Background in Coal Mine.

Yang W, Wang Y, Zhang X, Zhu L, Ren Z, Ji Y Sensors (Basel). 2024; 24(8).

PMID: 38676169 PMC: 11054103. DOI: 10.3390/s24082552.

References
1.
Song J, Zhu A, Zhu Y . Transformer-Based Semantic Segmentation for Extraction of Building Footprints from Very-High-Resolution Images. Sensors (Basel). 2023; 23(11). PMC: 10255903. DOI: 10.3390/s23115166. View

2.
Zhang L, Wu J, Fan Y, Gao H, Shao Y . An Efficient Building Extraction Method from High Spatial Resolution Remote Sensing Images Based on Improved Mask R-CNN. Sensors (Basel). 2020; 20(5). PMC: 7085500. DOI: 10.3390/s20051465. View

3.
Wei R, Fan B, Wang Y, Yang R . A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images. Sensors (Basel). 2023; 23(7). PMC: 10099251. DOI: 10.3390/s23073643. View

4.
El Merabet Y, Meurie C, Ruichek Y, Sbihi A, Touahni R . Building roof segmentation from aerial images using a lineand region-based watershed segmentation technique. Sensors (Basel). 2015; 15(2):3172-203. PMC: 4367354. DOI: 10.3390/s150203172. View

5.
Yu M, Chen X, Zhang W, Liu Y . AGs-Unet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network. Sensors (Basel). 2022; 22(8). PMC: 9031445. DOI: 10.3390/s22082932. View