LMDE-UNet: local multi-directional state space modeling with dynamic edge enhancement for building extraction from remote sensing images
Abstract
Accurate building extraction from remote sensing imagery requires both contextual information and local structural detail. This paper presents LMDE-UNet , an encoder–decoder network that combines window-based local multi-directional scanning (WLMS), a bottleneck feature aggregation module (BFAM), and an edge enhancement module (DEEM) in the skip connections. Each local visual selective scan block models global context before applying local scanning within non-overlapping windows. Experiments on three building-extraction datasets show that LMDE-UNet achieves higher intersection over union (IoU) and F1-scores than the evaluated baselines, with competitive precision and recall. On the Typical Chinese Urban Building Dataset, LMDE-UNet achieves an IoU of 73.47% and an F1-score of 85.16%, exceeding the corresponding SwinUNet scores by 0.99 and 0.63 percentage points, respectively. Its precision reaches 86.73%. The ablation results suggest that WLMS provides larger IoU gains when combined with BFAM and DEEM than when added alone.
Related
- Quad-directional frequency-aware state space modeling for low-light image enhancement
- Dynamic modeling, simulation, and analysis of solar/wind-based hybrid renewable energy system for rural residential building: a case study
- Model Predictive Control for Dynamic Hydraulic Balancing in Building Radiator Heating Systems: Modeling, Design, and Experimental Validation
- Energy landscape and dynamic state modeling for schizophrenia biomarker extraction in task-based fMRI
- Diffusion Enhancement and Directional Suppression Induced by Reciprocal Flows
BibTeX
@article{huang2026lmdeunet,
title = {{LMDE-UNet: local multi-directional state space modeling with dynamic edge enhancement for building extraction from remote sensing images}},
author = {Huada Huang and Zhenzhong Huang and Chao Ren and Wei Zhang and Guowei Zhao and Yintao Liu},
journal = {Scientific Reports},
year = {2026},
month = nov,
doi = {10.1038/s41598-026-77120-5},
url = {https://www.nature.com/articles/s41598-026-77120-5},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - LMDE-UNet: local multi-directional state space modeling with dynamic edge enhancement for building extraction from remote sensing images
AU - Huada Huang
AU - Zhenzhong Huang
AU - Chao Ren
AU - Wei Zhang
AU - Guowei Zhao
AU - Yintao Liu
PY - 2026
DA - 2026/11/04
JO - Scientific Reports
DO - 10.1038/s41598-026-77120-5
UR - https://www.nature.com/articles/s41598-026-77120-5
AB - Accurate building extraction from remote sensing imagery requires both contextual information and local structural detail. This paper presents LMDE-UNet , an encoder–decoder network that combines window-based local multi-directional scanning (WLMS), a bottleneck feature aggregation module (BFAM), and an edge enhancement module (DEEM) in the skip connections. Each local visual selective scan block models global context before applying local scanning within non-overlapping windows. Experiments on three building-extraction datasets show that LMDE-UNet achieves higher intersection over union (IoU) and F1-scores than the evaluated baselines, with competitive precision and recall. On the Typical Chinese Urban Building Dataset, LMDE-UNet achieves an IoU of 73.47% and an F1-score of 85.16%, exceeding the corresponding SwinUNet scores by 0.99 and 0.63 percentage points, respectively. Its precision reaches 86.73%. The ablation results suggest that WLMS provides larger IoU gains when combined with BFAM and DEEM than when added alone.
SN - 2045-2322
ER -