UAV image segmentation in complex mining areas by integrating spatially adaptive feature modulation and multi-scale context fusion modules
- 1School of Emergency Technology and Management, University of Emergency Management
Abstract
To address the misclassification of visually similar ground objects and inaccurate boundary localization caused by background interference, as well as small-object omission, fragmented regions, and incomplete boundaries resulting from scale variations, this study proposes MASwin-Unet for semantic segmentation of complex mining areas. The model incorporates a Spatially Adaptive Feature Modulation Module (SAFM) to suppress background noise and similar-texture interference while enhancing key regions and boundary details. It also introduces a Multi-Scale Context Fusion Module (MSCF) to integrate contextual information across different receptive fields and improve multi-scale feature modeling. An experimental dataset was constructed from UAV imagery of the Dongshan Xiuqing Mining Area, and experiments were also conducted on AeroScapes and LoveDA. MASwin-Unet achieved an OA of 97.18%, a Kappa coefficient of 95.79%, an mIoU of 85.14%, and an mF1 of 90.73%, outperforming BEDSN, FADC, DeepLabV3 + , PSPNet, HRNet, SegFormer, TransUNet, U-Net, and Swin-Unet. The results demonstrate good generalization on public datasets and show that the model effectively reduces similar-object misclassification, small-object omission, and incomplete boundary segmentation in complex UAV scenes.
Related
- Spatially-adaptive dynamic dictionary learning for fine-grained remote sensing image segmentation
- AMF-U-Net: an adaptive multimodal fusion residual attention 3D U-Net for boundary-aware brain tumour segmentation
- Boundary-interior ratio: a spatially decomposed evaluation framework for CNN and mamba-based breast ultrasound segmentation
- Multiparametric MRI-based habitat and peritumoral radiomics integrating semi-automated segmentation for preoperative prediction of high-grade prostate cancer: a dual-center study
- Time Series Segmentation in Adaptive Optics Ophthalmoscopy With Application to Flicker-Induced Vasodilation.
BibTeX
@article{li2026image,
title = {{UAV image segmentation in complex mining areas by integrating spatially adaptive feature modulation and multi-scale context fusion modules}},
author = {Qing Li and Mingxing Lu and Yan Li},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-69579-z},
url = {https://doi.org/10.1038/s41598-026-69579-z},
note = {CC BY},
}
RIS
TY - JOUR
TI - UAV image segmentation in complex mining areas by integrating spatially adaptive feature modulation and multi-scale context fusion modules
AU - Qing Li
AU - Mingxing Lu
AU - Yan Li
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-69579-z
UR - https://doi.org/10.1038/s41598-026-69579-z
AB - To address the misclassification of visually similar ground objects and inaccurate boundary localization caused by background interference, as well as small-object omission, fragmented regions, and incomplete boundaries resulting from scale variations, this study proposes MASwin-Unet for semantic segmentation of complex mining areas. The model incorporates a Spatially Adaptive Feature Modulation Module (SAFM) to suppress background noise and similar-texture interference while enhancing key regions and boundary details. It also introduces a Multi-Scale Context Fusion Module (MSCF) to integrate contextual information across different receptive fields and improve multi-scale feature modeling. An experimental dataset was constructed from UAV imagery of the Dongshan Xiuqing Mining Area, and experiments were also conducted on AeroScapes and LoveDA. MASwin-Unet achieved an OA of 97.18%, a Kappa coefficient of 95.79%, an mIoU of 85.14%, and an mF1 of 90.73%, outperforming BEDSN, FADC, DeepLabV3 + , PSPNet, HRNet, SegFormer, TransUNet, U-Net, and Swin-Unet. The results demonstrate good generalization on public datasets and show that the model effectively reduces similar-object misclassification, small-object omission, and incomplete boundary segmentation in complex UAV scenes.
SN - 2045-2322
ER -