The roof is one of the most iconic elements of Chinese vernacular architecture. Accurate and efficient recognition of roof types is essential for the digital documentation, dynamic monitoring, and restoration planning for vernacular architectural heritage. This study proposes a novel object detection technique by integrating the DCNv2, the DyHead and the SIoU to address challenges such as complex morphology, diverse materials, and feature occlusion in roof images. Experiments indicate that YOLOv10-DDS achieves 80.8% and 62.4% on mAP50 and mAP50-95, improving by 2.1% and 1.5% over the baseline model and outperforming other advanced methods. Validation across diverse scenarios confirms that the model maintains high accuracy and adaptability. A three-tier classification system comprising 16 subclasses of Chinese vernacular architectural roofs and a dual-perspective dataset were developed. This study establishes a technical foundation for the preservation and restoration of vernacular architectural heritage, expanding the application scope of object detection in cultural heritage research.
The role of administrative power in the enduring culture-regime debate is examined through a cultural diffusion case in China using digital archeology. 5698 Weilongwu (WLWs, traditional Hakka houses) objects were detected through remote sensing imagery, and the origin point was estimated. Then conceptual framework of “cultural primacy” and “cultural attenuation” combined with historical administrative features was established to quantitatively analyze the diffusion pattern of these ancient houses. Spatial statistics, incorporating convex hull algorithms and 24-axis directional analysis, quantified and mapped the cultural diffusion trends under the administrative influence. Results indicated that cultural diffusion correlated strongly with historical administrative regions, thriving at the prefecture level but constrained beyond. Findings above suggest administrative power mediated diffusion not through coercion, but by balancing local and imperial governance, ultimate shaping China’s multicultural landscape. The scalable methodology offers broader insights into cultural diffusion, human activity, and natural environments, with applicability to diverse cultural regions.
Green performance assessment is crucial for the conservation of built heritage. However, protected buildings often prohibit contact measurements and interior sensors, making traditional methods difficult to apply. To address this issue, we propose a method based on 3D laser scanning point clouds that relies entirely on facade scanning and aims to establish a green information model for monitoring sustainability performance. We selected Chuncao Mansion, an overseas Chinese villa on the World Heritage island of Kulangsu, as a case study; the building features typical passive design strategies. Using terrestrial laser scanning, high-precision point cloud data of the facade were obtained, registered, and denoised to build a complete 3D geometric base. We then extracted key geometric parameters from the point cloud, including veranda depth, clear height between columns, and geometric opening area ratio. These parameters were integrated into a simplified BIM model as green geometric information. Finally, we performed solar simulations based on this model, selecting the winter and summer solstices to quantify the self-shading performance of the “Chugui” curved veranda and the adjacent standard straight verandas. The results show that the mean absolute cloud-to-cloud deviation in overlapping areas is 9 mm, providing a consistent geometric basis for component-level measurement; absolute accuracy requires independent verification. For the southeast-facing veranda, local direct sunlight exposure across the analyzed surface is limited to 0–2 h on the summer solstice, while local exposure in the same area reaches 6–10 h on the winter solstice. A depth-controlled counterfactual simulation confirms that this seasonal regulation is attributed to the combined geometric configuration: the increased depth (4.44 m) secures beneficial winter solar access, while the curvature acts as a more effective lateral shading mask to reduce summer exposure compared to an equal-depth straight veranda. This study proposes a complete non-contact technical workflow covering facade scanning, green parameter extraction, BIM integration, and simulation-based solar performance assessment. The workflow is suitable for protected built heritage and can be extended to similar heritage buildings in hot–humid climate zones, providing a basis for future green assessment and potential low-carbon intervention.