Ke Li

Understanding remote sensing imagery is vital for object observation and planning. However, the acquisition of optical images is inevitably affected by shadows and occlusions, resulting in local discrepancies in object representation. To address these challenges, this paper proposes AFNE-Net, a general network architecture for remote sensing image segmentation. First, the model introduces an attention-based feature fusion module. Through the use of weighted fusion of multi-resolution features, this effectively expands the receptive field and enhances semantic associations between categories. Subsequently, a feature enhancement module based on the consistency of neighborhood semantic representation is introduced. This aims to improve the feature representation and reduce segmentation errors caused by local perturbations. Finally, evaluations are conducted on the ISPRS Potsdam, UAVid, and LoveDA datasets to verify the effectiveness of the proposed model.

The spatial layout of residential communities has a significant impact on the local microclimate. These microclimate changes subtly affect the daily feelings and health status of residents. This study takes hypertension as a case to simulate the outdoor microclimate characteristics of different types of communities, and to analyze the potential correlation between spatial design and the health of residents, providing a scientific basis for the design of health-oriented communities. Initially, the microclimate characteristics of communities are obtained through computational fluid dynamics (CFD) simulation. Subsequently, the correlation between the outdoor microclimate and the incidence of hypertension in communities is discussed. The study area covers communities within a 4 km radius of Zhongnan hospital. The results indicate that microclimatic factors, such as temperature, Predicted Mean Vote (PMV), and Universal Thermal Climate Index (UTCI), are significantly negatively correlated with the incidence of hypertension in communities of different building heights. For temperature, the absolute value of the correlation coefficient for multi-story communities is 0.431, slightly lower for mid-rise communities at 0.323, and further drops to 0.296 for high-rise communities. Correspondingly, the values for PMV are 0.434, 0.336, and 0.306, respectively. The values for UTCI are 0.442, 0.310, and 0.303, respectively. This effect gradually weakens as building heights increase. Fluctuations in wind speed appear to weakly influence the incidence of hypertension. These results provide a scientific basis for health-oriented urban planning.