ISPRS International Journal of Geo-Information

Developing a more equitable, efficient, and sustainable system of community sports and fitness facilities, while improving the accessibility and popularity of national fitness activities, is crucial to advancing the Healthy China Initiative. However, existing studies have limitations: insufficiently granular classification of community-level facilities, failure to account for how differences in facility types affect service equity, absence of integrated validation that combines objective quantification and subjective perception, and inattention to group differences. These gaps provide the motivation for this study. This study uses Shijingshan District, Beijing, as a case study, categorizing community sports and fitness facilities into two categories: for-profit commercial facilities and non-profit community sports parks. Employing GIS technology, Z-score standardization, and questionnaire surveys, an evaluation was conducted from three aspects: accessibility, supply–demand dynamics, and group perception. The results show that: (1) Facility accessibility exhibits significant spatial heterogeneity. Commercial facilities are densely clustered in core subdistricts, whereas community sports parks exhibit higher accessibility in the southern and eastern areas than in the northern and western areas, with inadequate coverage in peripheral areas; (2) most facilities are in short supply shortage, and the supply–demand imbalance is particularly pronounced in peripheral areas; and (3) regarding group equity, gender equity is outperforms age equity, and the supply–demand structure aligns closely with gender-specific preferences. This study argues that the spatial mismatch between facility distribution and resident demand, as well as imbalances in the supply of facility types, are the key factors undermining equity. It proposes optimization strategies, including augmenting facility supply in peripheral areas and coordinating the provision of commercial facilities and community sports parks.

Unauthorized farmland excavation is a prominent manifestation of farmland non-agriculturalization, and its effective monitoring depends on structured representations of objects and their spatial interactions in complex scenes. However, the existing computer vision research mainly focuses on object-level recognition or scene-level classification, while lacking datasets that explicitly model topological relationships in farmland excavation scenarios. To address this limitation, this paper presents TopoFarm, a topology-annotated panoptic dataset for unauthorized farmland excavation scenes. TopoFarm provides fine-grained panoptic segmentation annotations together with pairwise object contact relationship labels, enabling joint object–relation modeling and topology-aware scene representation. To improve annotation reliability under complex conditions, a human-in-the-loop hybrid intelligence framework, termed HITPA, is introduced to integrate automatic panoptic segmentation, depth-aware topological reasoning, and expert-guided refinement, achieving high annotation quality with controlled manual effort. Based on TopoFarm, systematic benchmark experiments are conducted for panoptic segmentation and topological relationship reasoning, along with a hierarchical evaluation protocol to analyze the impact of object-level representation quality on relational inference. The results demonstrate that TopoFarm poses substantial challenges for both tasks and highlight the strong dependence of topological reasoning on object accuracy and global scene context. Overall, TopoFarm provides a new data foundation and evaluation benchmark for topology-aware perception in farmland monitoring applications.

This paper proposes a building reconstruction framework for airborne LiDAR data to address the challenge of automated modeling under conditions of uneven point cloud density and missing vertical walls, generating high-precision and structurally compact 3D building models. The method first combines adaptive resolution hypervoxels with a global graph cut optimization strategy to extract precise roof plane primitives from sparse point clouds of buildings. Subsequently, it infers building facades and internal vertical walls based on point cloud projection contours and height change detection, thereby completing the wall structures commonly missing in airborne LiDAR data. Finally, a feature line constraint term is introduced into the hypothesis-and-selection-based reconstruction framework to guide the structural optimization of candidate planes, ensuring the reconstructed model closely matches the actual building geometry. The proposed method was evaluated on multiple public airborne LiDAR datasets, demonstrating its effectiveness through qualitative and quantitative comparisons with various state-of-the-art approaches.