The urban functional areas (UFA) are the basic spatial units of a city, identifying their category information and spatial distribution is of great significance for studying urban spatial structure and formulating scientific and reasonable urban planning policies. However, traditional classification systems are still limited due to the data processing costs and time consuming. With the development of high-resolution satellite, the two-dimensional image has been able to identify more ground object information on a fine scale, but it lacks the application of three-dimensional characteristics and social attributes. At the same time, machine learning and deep learning have shown great utility in extracting features, and they should be applied more to the classification of urban functional areas to improve efficiency. To solve these problems, we propose an efficient and accurate framework for mapping UFA using multi-source geospatial data. It can grasp the dynamic changes in the city more accurately, and provide reference for the study of urban functional areas. An improved frequency density (IFD) model was proposed to improve the overall classification accuracy by 4.4%. Besides, the nighttime light (NTL) data from SDGSAT-1 satellite glimmer imagers are also used to classify UFA. By combining NTL and urban building height data, a sky view enhanced nightlight index (SVENI) was proposed, which can improve the overall classification accuracy of UFA by 5.8%. This study systematically clarifies the role of data sources, methods, and automatically integration models in the classification framework for UFA, which is of great significance for urban planning and sustainable development.

Reliable state estimation in railway environments presents significant challenges due to geometric degeneracy resulting from repetitive structural layouts and point cloud sparsity caused by high-speed motion. Conventional LiDAR-based SLAM systems frequently suffer from longitudinal drift and mapping artifacts when operating in such feature-scarce and dynamically complex scenarios. To address these limitations, this paper proposes SERail-SLAM, a robust semantic-enhanced multi-sensor fusion framework that tightly couples LiDAR odometry, inertial pre-integration, and GNSS constraints. Unlike traditional approaches that rely on rigid voxel grids or binary semantic masking, we introduce a Semantic-Enhanced Adaptive Voxel Map. By leveraging eigen-decomposition of local point distributions, this mapping strategy dynamically preserves fine-grained stable structures while compressing redundant planar surfaces, thereby enhancing spatial descriptiveness. Furthermore, to mitigate the impact of environmental noise and segmentation uncertainty, a confidence-aware filtering mechanism is developed. This method utilizes raw segmentation probabilities to adaptively weight input measurements, effectively distinguishing reliable landmarks from clutter. Finally, a category-weighted joint optimization scheme is implemented, where feature associations are constrained by semantic stability priors, ensuring globally consistent localization. Extensive experiments in real-world railway datasets demonstrate that the proposed system achieves superior accuracy and robustness compared to state-of-the-art geometric and semantic SLAM methods.

Dense partial-view LiDAR observations are attractive for outdoor perception, but limited overlap and viewpoint sensitivity make odometry and mapping less reliable than with spinning LiDARs. Many recent algorithms for this sensing regime are built as LiDAR-inertial odometry frameworks, whose localization and mapping performance can degrade or fail when the IMU state estimation becomes unstable. This paper presents a LiDAR-only framework for complex outdoor scenes using a factor-graph back-end. After denoising and motion compensation, the point cloud is projected onto a range image for ground, planar, edge, and line extraction. Pose estimation is strengthened by degeneracy-aware feature selection, while loop closing combines scan-based and path-based cues to handle partial-view revisits. Experiments in tunnels, urban roads, residential areas, and other challenging scenes show reduced drift and improved mapping consistency for dense limited-FoV LiDAR data.