High-precision building information extraction is essential in surveying and mapping. Deep learning methods have proven effective in extracting buildings from satellite optical images. This paper introduces a Boundary-Enhanced Semantic Segmentation Model (BE-SegModel) to address the issue of unclear building boundary segmentation in high-resolution satellite images. The model simultaneously extracts building masks and boundary information, ultimately enhancing extraction accuracy. Deep-level heatmaps and feature maps are visualized to analyze the knowledge acquired by the proposed model. The model's performance is evaluated using the xBD, WHU Global, and WHU East Asia Building datasets. Experimental results indicate that, with the inclusion of semantic boundaries, the proposed BE-SegModel outperforms seven mainstream models, including ResNet34, HRNet, Deeplabv3+, CBRNet, FCN, FCN-UNet, and ResNeXt50. In summary, BE-SegModel significantly improves segmentation accuracy, achieving over 6.9% improvement relative to the baseline model.

Very high resolution (VHR) remote sensing change detection (CD) is crucial for monitoring Earth’s dynamics but faces challenges in capturing fine-grained changes and distinguishing them from pseudo-changes due to varying acquisition conditions. Existing deep learning methods often suffer from information loss via downsampling, obscuring details, and lack filter adaptability to spatial heterogeneity. To address these issues, we introduce Information-Preserving Adaptive Convolutional Network (IPACN). IPACN features a novel Information-Preserving Backbone (IPB), leveraging principles adapted from reversible networks to minimize feature degradation during hierarchical bi-temporal feature extraction, enhancing the preservation of fine spatial details, essential for accurate change delineation. Crucially, IPACN incorporates a Frequency-Adaptive Difference Enhancement Module (FADEM) that applies adaptive filtering, informed by frequency analysis concepts, directly to the bi-temporal difference features. The FADEM dynamically refines change signals based on local spectral characteristics, improving discrimination. This synergistic approach, combining high-fidelity feature preservation (IPB) with adaptive difference refinement (FADEM), yields robust change representations. Comprehensive experiments on benchmark datasets demonstrate that IPACN achieves state-of-the-art performance, showing significant improvements in F1 score and IoU, enhanced boundary delineation, and improved robustness against pseudo-changes, offering an effective solution for very high resolution remote sensing CD.