Objective This research addresses critical challenges in the documentation and research of classical Chinese gardens. As exemplary representatives of the World Cultural Heritage, Suzhou classical gardens are renowned for their intricate spatial compositions and profound cultural significance. However, current teaching and research predominantly rely on manual surveying and mapping data from the last century, such as the maps included in Liu Dunzhen’s publication, which no longer accurately reflect the current conditions. This resrarch takes the Master-of-Nets Garden as an example, whose spatial layout has undergone multiple modifications, including the restoration of the Peony Courtyard in 2003, making it significantly different from what it is in existing maps. Traditional manual surveying methods are typiclly inefficient and subjective, particularly when documenting complex morphological features such as rockery textures and architectural curves. Therefore, this research innovatively integrates modern digital surveying technologies including 3D laser scanning and photogrammetry with intelligent image processing algorithms, such as the Canny edge detection and gradient analysis, to develop a comprehensive methodology for automated feature recognition and 2D drawing generation. Based on the case study of the Peony Courtyard, this research establishes a high-precision 3D point cloud model, aiming to provide reliable technical support and scientific basis for garden heritage conservation, academic research, and professional education, while addressing the critical limitation of historical maps in dynamically reflecting garden evolution.
Methods This research adopts a multi-source data fusion approach, systematically integrating three advanced surveying techniques. During the data acquisition stage, terrestrial photogrammetry is first employed using a GPS-equipped Nikon Z5 camera to capture 1,675 high-quality images under controlled conditions at fixed daily time slots, with the overlapping area between consecutive images exceeding 70%, comprehensively covering traditionally difficult-to-document concealed areas including interior spaces, eaves, and rockery caves. Secondly, oblique aerial photography is conducted using a DJI Mavic 2 Pro drone along five designed flight paths (one nadir and four oblique routes) capturing 188 georeferenced aerial images. Thirdly, the FARO Focus S350 3D laser scanner is deployed at 26 locations to capture high-precision data of complex morphological features such as building facades and rockeries. During the data processing stage, RealityCapture is used to integrate multi-source data, constructing a 3D point cloud model with millimeter-level precision. It is verified through 38 on-site measurements using steel tape that the model’s overall error rate at 0.71% ± 0.13% (mean ± SD), with particularly reliable accuracy in architectural and courtyard areas. During the intelligent mapping stage, this study employs the Canny edge detection algorithm, with its optimal high and low thresholds of 4 and 2 determined through repeated trials, to extract feature lines of objects. Subsequently, this research utilizes gradient threshold masks to categorize the feature lines into three hierarchical levels: outer contours, secondary contours, and texture lines, corresponding to thick, medium, and thin lines, respectively, ultimately generating professional-level 2D plans and sections. Lastly, special elements like vegetation are optimized through manual assistance to ensure the completeness and accuracy of drawings.
Results The experimental outcomes have significant advantages in multiple aspects. In terms of precision, the algorithm-generated 2D drawings maintain a stable error rate below 1%, substantially outperforming traditional manual surveying. Technically, the method successfully captures and represents subtle architectural curves and complex rockery textures that are challenging for conventional documentation. Systematic comparison with historical drawings reveals important layout modifications, such as the non-linear configuration of the Peony Courtyard’s eastern and western walls and their non-perpendicular relationship with the southern wall, with such findings corroborated by restoration photographs from the late 1950s. This research also accurately documents detailed changes including newly added rocks at the southeastern corner and morphological evolution of the steps of Hanbi Spring. Limitations include some blurred representations of interior furniture and certain windows or doors due to insufficient scanning coverage, and the need for manual parameter adjustment in complex rockery areas. Notably, the established 3D point cloud model offers comprehensive data advantages, supporting cross-sectional extraction and drawing generation from any viewpoint, overcoming the fixed-perspective limitation of traditional methods. This provides unprecedented technical possibilities for long-term monitoring and dynamic documentation of garden heritage. The entire methodology ensures professional accuracy while significantly improving efficiency, enabling multi-angle output from single data acquisition and greatly reducing repetitive field measurements.
Conclusion Through systematic technological development and empirical research, this research successfully validates the practical value of digital surveying and intelligent algorithms in the documentation and conservation of classical gardens. Technically, the research confirms the effectiveness of combining Canny edge detection with gradient threshold masking for feature extraction, establishing a complete intelligent workflow from the 3D point cloud model to 2D drawings. Regarding application value, the proposed methodology not only generates professional-level high-precision drawings, but also, through its unique traceability, enables dynamic documentation and analysis of garden evolution, providing a scientific basis for heritage monitoring and conservation decisions. Compared to traditional methods, the new technology demonstrates clear advantages in data completeness, workflow efficiency, and output accuracy, particularly excelling in documenting complex features such as rockery textures and architectural curves. Future research should focus on the following aspects: First, incorporating convolutional neural networks to enhance automated feature recognition and semantic segmentation; second, developing specialized modules for intelligent analysis of classical garden elements like rockery texture patterns and architectural components; third, establishing intelligent comparison systems between historical and current survey data for quantitative analysis of garden evolution. These innovations will advance the digital conservation of classical gardens from basic documentation to intelligent analysis, providing more robust technical support for sustainable cultural heritage conservation. The research outcomes are applicable not only to Suzhou classical gardens but can also be extended to other types of cultural heritage conservation practices, demonstrating broad application prospects and significant academic value.
DownLoad: