Jingyi Xiong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jingyi Xiong has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Buyu Su
National Key Laboratory of Uranium Resource Exploration-Mining and Nuclear Remote Sensing, Beijing Research Institute of Uranium Geology, Beijing 100029, China
1 shared publication - Defei Yin
Science and Technology on Near-Surface Detection Laboratory, The Fifth Research Institute of Wuxi, Wuxi 214035, China
1 shared publication - Fan Yang
Institute of Desert Meteorology, China Meteorological Administration/National Observation and Research Station of Desert Meteorology, Taklimakan Desert of Xinjiang/Taklimakan Desert Meteorology Field Experiment Station of China Meteorological Administration/Xinjiang Key Laboratory of Desert Meteorology and Sandstorm/Key Laboratory of Tree-ring Physical and Chemical Research, China Meteorological Administration, Urumqi 830002, China
1 shared publication - Haowei Mu
School of Geography and Ocean Science, Nanjing University, Nanjing 210023, China
1 shared publication - Junjian Liu
Institute of Desert Meteorology, China Meteorological Administration, Urumqi 830002, China
1 shared publication - Piyuan Yi
National Key Laboratory of Uranium Resource Exploration-Mining and Nuclear Remote Sensing, Beijing Research Institute of Uranium Geology, Beijing 100029, China
1 shared publication
Latest Publications
- Open Access
HR-Mamba: Building Footprint Segmentation with Geometry-Driven Boundary Regularization
Building extraction underpins land-use assessment, urban planning, and disaster mitigation, yet dense urban scenes still cause missed small objects, target adhesion, and ragged contours. We present High-Resolution-Mamba (HR-Mamba), a high-resolution semantic segmentation network that augments a High-Resolution Network (HRNet) parallel backbone with edge-aware and sequence-state modeling. A Canny-enhanced, median-filtered stem stabilizes boundaries under noise; Involution-based residual blocks capture position-specific local geometry; and a Mamba-based State Space Models (Mamba-SSM) global branch captures cross-scale long-range dependencies with linear complexity. Training uses a composite loss of binary cross entropy (BCE), Dice loss, and Boundary loss, with weights selected by joint grid search. We further design a feature-driven adaptive post-processing pipeline that includes geometric feature analysis, multi-strategy simplification, multi-directional regularization, and topological consistency verification to produce regular, smooth, engineering-ready building outlines. On dense urban imagery, HR-Mamba improves F1-score from 80.95% to 83.93%, an absolute increase of 2.98% relative to HRNet. We conclude that HR-Mamba jointly enhances detail fidelity and global consistency and offers a generalizable route for high-resolution building extraction in remote sensing.
Open AccessHR-Mamba: Building Footprint Segmentation with Geometry-Driven Boundary Regularization
Building extraction underpins land-use assessment, urban planning, and disaster mitigation, yet dense urban scenes still cause missed small objects, target adhesion, and ragged contours. We present High-Resolution-Mamba (HR-Mamba), a high-resolution semantic segmentation network that augments a High-Resolution Network (HRNet) parallel backbone with edge-aware and sequence-state modeling. A Canny-enhanced, median-filtered stem stabilizes boundaries under noise; Involution-based residual blocks capture position-specific local geometry; and a Mamba-based State Space Models (Mamba-SSM) global branch captures cross-scale long-range dependencies with linear complexity. Training uses a composite loss of binary cross entropy (BCE), Dice loss, and Boundary loss, with weights selected by joint grid search. We further design a feature-driven adaptive post-processing pipeline that includes geometric feature analysis, multi-strategy simplification, multi-directional regularization, and topological consistency verification to produce regular, smooth, engineering-ready building outlines. On dense urban imagery, HR-Mamba improves F1-score from 80.95% to 83.93%, an absolute increase of 2.98% relative to HRNet. We conclude that HR-Mamba jointly enhances detail fidelity and global consistency and offers a generalizable route for high-resolution building extraction in remote sensing.