The progressive TIN (triangular irregular network) densification (PTD) filter algorithm is widely used for filtering point clouds. In the PTD algorithm, the iterative densification parameters become smaller over the entire process of filtering. This leads to the performance—especially the type I errors of the PTD algorithm—being poor for point clouds with high density and standard variance. Hence, an improved PTD filtering algorithm for point clouds with high density and variance is proposed in this paper. This improved PTD method divides the iterative densification process into two stages. In the first stage, the iterative densification process of the PTD algorithm is used, and the two densification parameters become smaller. When the density of points belonging to the TIN is higher than a certain value (in this paper, we define this density as the standard variance intervention density), the iterative densification process moves into the second stage. In the second stage, a new iterative densification strategy based on multi-scales is proposed, and the angle threshold becomes larger. The experimental results show that the improved PTD algorithm can effectively reduce the type I errors and total errors of the DIM point clouds by 7.53% and 4.09%, respectively, compared with the PTD algorithm. Although the type II errors increase slightly in our improved method, the wrongly added objective points have little effect on the accuracy of the generated DSM. In short, our improved PTD method perfects the classical PTD method and offers a better solution for filtering point clouds with high density and standard variance.
The ridge beast is a beast placed on the ridge of the roof of ancient Chinese buildings, not only has a decorative function, and has a strict hierarchical meaning, the number and form of the ridge beast placed on different levels of buildings are strictly limited. The detection technology of ridge beast decorative parts has important application value in the fields of fine 3D reconstruction of ancient buildings, historical dating and cultural and tourism services. Aiming at the problem of poor detection performance of traditional detection algorithms due to high texture similarity and poor discrimination of ridge beast, this paper proposed an improved YOLOv3 based detection algorithm for ridge beast decorative pieces. In terms of basic network improvement, local features are aggregated to the deep separable convolution internal embedding summation layer, and point convolution is used to connect the channel information of original features and aggregated features, so as to expand the receptive field and learn more diverse features. The residual structure of the feature extraction network was constructed by using the convolution, and the extraction effect of the model on the fine-grained features of the ridge beast was optimized, so that the detection accuracy was improved. In the prediction head improvement of the model, the original linear structure was reconstructed, and the extrusion and excitation modules were introduced to model the channel relationship of multi-scale feature map, which suppressed the response of interference signals and made the feature more directivity. The parallel 1 × 1 and 3 × 3 convolution are used to construct a multi-size convolution structure, which enhances the semantic information extraction ability of the model and further improves the detection effect. Experiments were conducted on the constructed ridge-beast dataset, and the results showed that the mAP of the improved algorithm can reach 86.48%, which is 3.05% higher than YOLO-v3, and the model parameters are reduced by 70%, which has a better detection performance and can provide a reference for the automated detection of ancient building components.
Point cloud semantic segmentation is a key step in the scan-to-HBIM process. In order to reduce the information in the process of DGCNN, this paper proposes a Mix Pooling Dynamic Graph Convolutional Neural Network (MP-DGCNN) for the segmentation of ancient architecture point clouds. The proposed MP-DGCNN differs from DGCNN mainly in two aspects: (1) to more comprehensively characterize the local topological structure of points, the edge features are redefined, and distance and neighboring points are added to the original edge features; (2) based on a Multilayer Perceptron (MLP), an internal feature adjustment mechanism is established, and a learnable mix pooling operator is designed by fusing adaptive pooling, max pooling, average pooling, and aggregation pooling, to learn local graph features from the point cloud topology. To verify the proposed algorithm, experiments are conducted on the Qutan Temple point cloud dataset, and the results show that compared with PointNet, PointNet++, DGCNN, GACNet and LDGCNN, the MP-DGCNN segmentation network achieves the highest OA, mIOU and mAcc, reaching 90.19%,65.34% and 79.41%, respectively.
The ancient roof decorative components of the official-style architectures from the Ming and Qing dynasties in China hold both physical and symbolic significance. These roof structures are the essential objects in three-dimensional (3D) modeling of ancient architectures for traditional Chinese cultural preservation. Although ancient architectures can be surveyed by a 3D laser scanner, the complex geometry and diverse pattern of their roof decorative components make the 3D point cloud reconstruction challenging, or at some points, nearly impossible in a fully automated manner. In this paper, we propose a method to ensure that the 3D shape of each roof decorative component is accurately modeled. First, we establish a decorative components template library (or “template library” in short hereafter), which is the first of its kind for the roofs of Ming and Qing official-style architectures. The process of establishing the decorative components template library begins with a remote collection of survey data using a terrestrial laser scanner and digital camera. The next stage involves the design and construction of different 3D decorative components in the template library with reference to the manuscripts written in the Ming and Qing dynasties’ architectural pattern books. With the point cloud data collected on any Ming and Qing official-style architecture, we further propose a geo-registration mechanism to search for an optimal fitting of the decorative components from the template library on the collected point cloud automatically. Based on the experimental results, the accuracy of point cloud registration yields less than 0.02 m, which meets the accuracy of the 3D model at LoD 300 level. Time consumption is less than 5s and stable, for large volume computing capacity has good robustness. The proposed strategy provides a new way for the 3D modeling of large and clustered historical architectures, particularly with complex structures.
Aerial images are widely used for building detection. However, the performance of building detection methods based on aerial images alone is typically poorer than that of building detection methods using both LiDAR and image data. To overcome these limitations, we present a framework for detecting and regularizing the boundary of individual buildings using a feature-level-fusion strategy based on features from dense image matching (DIM) point clouds, orthophoto and original aerial images. The proposed framework is divided into three stages. In the first stage, the features from the original aerial image and DIM points are fused to detect buildings and obtain the so-called blob of an individual building. Then, a feature-level fusion strategy is applied to match the straight-line segments from original aerial images so that the matched straight-line segment can be used in the later stage. Finally, a new footprint generation algorithm is proposed to generate the building footprint by combining the matched straight-line segments and the boundary of the blob of the individual building. The performance of our framework is evaluated on a vertical aerial image dataset (Vaihingen) and two oblique aerial image datasets (Potsdam and Lunen). The experimental results reveal 89% to 96% per-area completeness with accuracy above almost 93%. Relative to six existing methods, our proposed method not only is more robust but also can obtain a similar performance to the methods based on LiDAR and images.
Point cloud semantic segmentation has played an important role in the scan-to-BIM process of the Ming and Qing Dynasties’ official-style architecture roof. To overcome the complexity of roof components’ shape and the scale differences between different roof component types, a point cloud semantic segmentation method for the MQDOAs roof considering the construction regulations is proposed in this paper. This method is composed of two stages. In the first stage, the features from the construction rules of MQDOAs, including the normalized symmetrical distance (NSD), relative height (RH) and local height difference (LHD), are extracted alongside the regular geometric features. To lower the influence of scale differences, a multi-scale feature connection strategy is also applied to construct the feature classification vector. In the second stage, RF method is applied to classify the point cloud. To verify the efficiency of the proposed method, we took the Hall of Complete Harmony as the study case. The experiments showed that our method achieved segmentation result in overall classification accuracy and reached 96.8%.