Due to the high automaticity and efficiency of image-based residential area extraction, it has become one of the research hotspots in surveying, mapping, and computer vision, etc. For the application of mapping residential area, the extracted contour is required to be regular. However, the contour results of existing deep-learning-based residential area extraction methods are assigned accurately according to the actual range of residential areas in imagery, which are difficult to directly apply to mapping due to the extractions being messy and irregular. Most of the existing ground object extraction datasets based on optical satellite images mainly promote the research of semantic segmentation, thereby ignoring the requirements of mapping applications. In this paper, we introduce an optical satellite images dataset named RERB (Residential area Extraction with Regularized Boundary) to support and advance end-to-end learning of residential area mapping. The characteristic of RERB is that it embeds the prior knowledge of regularized contour in the dataset. In detail, the RERB dataset contains 13,892 high-quality satellite images with a spatial resolution of 2 m acquired from different cities in China, and the size of each image is approximately 256 × 256 pixels, which covers an area of more than 3640 square kilometers. The novel published RERB dataset encompasses four superiorities: (1) Large-scale and high-resolution; (2) well annotated and regular label contour; (3) rich background; and (4) class imbalance. Therefore, the RERB dataset is suitable for both semantic segmentation and mapping application tasks. Furthermore, to validate the effectiveness of the RERB, a novel end-to-end regularization extraction algorithm of residential areas based on contour cross-entropy constraints is designed and implemented, which can significantly improve the regularization degree of extraction for the mapping of residential areas. The comparative experimental results demonstrate the preponderance and practicability of our public dataset and can further facilitate future research.

Satellite-derived bathymetry (SDB) provides an efficient approach for shallow-water mapping because of its wide spatial coverage and repeated observation capability. However, multi-temporal bathymetric results derived from optical imagery often exhibit substantial inconsistencies due to variations in atmospheric conditions, water optical properties, bottom reflectance, and imaging geometry. Moreover, different bathymetric intervals usually exhibit distinct uncertainty characteristics, while conventional global fusion methods generally apply a single statistical strategy to the entire depth range. To address this limitation, this study proposes an ICESat-2-constrained adaptive segment-wise rank-statistic fusion framework for multi-temporal SDB. The bathymetric range is adaptively divided into multiple depth intervals using ICESat-2 bathymetric control points, and the optimal rank-statistic fusion strategy is independently selected for each interval according to local RMSE evaluation. In this way, shallow-water outliers can be effectively suppressed, while deep-water systematic underestimation can be alleviated simultaneously. Experiments conducted in Ganquan Island, Dong Island, and Key Biscayne demonstrate that the proposed framework consistently outperforms individual single-scene results as well as conventional mean and median fusion methods. Compared with conventional mean and median fusion methods, the RMSE was reduced by up to 27.5%, while the coefficient of determination (R²) reached 0.95. Significant improvements were particularly observed in deeper bathymetric intervals and complex benthic environments. The results indicate that adaptive segmented rank-statistic fusion can effectively characterize bathymetric-dependent error variations and achieve unified optimization for shallow-water outlier suppression and deep-water bias correction.

Accurate image classification under extreme label scarcity remains a critical challenge in remote sensing, where hyperspectral imagery offers rich spectral signatures but suffers from coarse spatial resolution limitations. Although integrating complementary panchromatic and multispectral data can alleviate this spatial bottleneck, existing methods struggle to fully exploit their deep spatial–spectral features without dense annotations. We propose GeCoM, a joint generative and interactive contrastive self-supervised learning framework for few-shot multi-source image classification. GeCoM employs modality-specific Transformer encoders with a multi-scale masking strategy to reconstruct fine spatial–spectral patterns. Simultaneously, an interactive contrastive optimization module is introduced to align heterogeneous multi-source features within a unified latent space. Experiments on the Houston 2018 benchmark and two regional scenes from Gaofen-14 satellite demonstrate that GeCoM achieves superior Overall Accuracies of 74.66%, 92.36%, and 94.02% with only 15 labeled samples per class, outperforming state-of-the-art baselines. This study provides a robust, label-efficient spatial–spectral representation solution for multi-sensor earth observation.