Roof Points Research Articles

Indoor scene reconstruction from LiDAR point cloud based on roof extraction

Indoor scene reconstruction from LiDAR point clouds is crucial for indoor navigation, scan-to-BIM, and virtual reality. However, occlusions caused by furniture and clutter make this task challenging. This paper introduces a novel framework for reconstructing 3D models using typically unoccluded ceiling point clouds, because the ceiling is difficult to be obstructed by indoor objects and is relatively well preserved. This framework starts with extracting the roof, roof is extracted by a proposed method based on cloth simulation which can extract various shape of roofs. Then a room instance map of the scene is obtained by input the point cloud density map to Mask R-CNN. By overlapping the roof point cloud and room instance map, the whole roof is segmented into roof points of different rooms. Next, we extracted the contours of every room's roof and a new algorithm was proposed to detect connections between different rooms to restore the topological relationship between rooms, generating the scene's floor plan. Finally, by detecting the contours and connections' height, the floor plan is stretched to detected height to generate a 3D model. To evaluate the proposed method's effectiveness, experiments were conducted on two indoor LiDAR point cloud datasets, GibLayout and ISPRS Benchmark, comprising a total of 13 scenes. The results were compared with representative methods, including Floor-sp and Heat for floor plan extraction, and Polyfit and KSR for 3D model reconstruction. The experimental results show that the new method outperform existing approaches, enabling the reconstruction of highly overlapping 3D models of real scenes.

A New Framework for Generating Indoor 3D Digital Models from Point Clouds

Three-dimensional indoor models have wide applications in fields such as indoor navigation, civil engineering, virtual reality, and so on. With the development of LiDAR technology, automatic reconstruction of indoor models from point clouds has gained significant attention. We propose a new framework for generating indoor 3D digital models from point clouds. The proposed method first generates a room instance map of an indoor scene. Walls are detected and projected onto a horizontal plane to form line segments. These segments are extended, intersected, and, by solving an integer programming problem, line segments are selected to create room polygons. The polygons are converted into a raster image, and image connectivity detection is used to generate a room instance map. Then the roofs of the point cloud are extracted and used to perform an overlap analysis with the generated room instance map to segment the entire roof point cloud, obtaining the roof for each room. Room boundaries are defined by extracting and regularizing the roof point cloud boundaries. Finally, by detecting doors and windows in the scene in two steps, we generate the floor plans and 3D models separately. Experiments with the Giblayout dataset show that our method is robust to clutter and furniture point clouds, achieving high-accuracy models that match real scenes. The mean precision and recall for the floorplans are both 0.93, and the Point–Surface Distance (PSD) and standard deviation of the PSD for the 3D models are 0.044 m and 0.066 m, respectively.

A Feature Line Extraction Method for Building Roof Point Clouds Considering the Grid Center of Gravity Distribution

A Feature Line Extraction Method for Building Roof Point Clouds Considering the Grid Center of Gravity Distribution

Application of Machine Learning to Detect Building Points in Photogrammetry-based Point Clouds

Different point cloud technologies such as Terrestrial Laser Scanners (TLS), Airborne Laser Scanners (ALS), Mobile Mapping Systems (MMS), and Unmanned Aerial Vehicles (UAV) have become increasingly more common in land surveying and geoinformatics over recent years. Thanks to these modern tools, experts can survey large areas cost-effectively with either high resolution or high accuracy. However, processing the point cloud, which consists of millions of points, can be a massive challenge. Manual processing of these large datasets can often be very time-consuming and hardware-demanding, and most of the time, only a limited part of the point cloud is used to derive the final products. The solution can be to automate the process as much as possible. Several advanced mathematical methods, especially Machine Learning (ML) algorithms, allow efficient automated processing of point clouds. This paper presents a processing chain to detect and separate building points from large-scale photogrammetry-based point clouds. The processing is based on the combination of Random Sample Consensus (RANSAC) and Machine Learning (ML) algorithms like Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Multi-Layer Perceptron (MLP). Presented methods were trained and tested on established and open available Heissigheim 3D (H3D) dataset to separate roof and vegetation points with over 90% accuracy in order to enhance the separation of building points on large-scale point clouds.

The Extraction of Roof Feature Lines of Traditional Chinese Village Buildings Based on UAV Dense Matching Point Clouds

Traditional Chinese buildings serve as a carrier for the inheritance of traditional culture and national characteristics. In the context of rural revitalization, achieving the 3D reconstruction of traditional village buildings is a crucial technical approach to promoting rural planning, improving living environments, and establishing digital villages. However, traditional algorithms primarily target urban buildings, exhibiting limited adaptability and less ideal feature extraction performance for traditional residential buildings. As a result, guaranteeing the accuracy and reliability of 3D models for different types of traditional buildings remains challenging. In this paper, taking Jingping Village in Western Hunan as an example, we propose a method that combines multiple algorithms based on the slope segmentation of the roof to extract feature lines. Firstly, the VDVI and CSF algorithms are used to extract the building and roof point clouds based on the MVS point cloud. Secondly, according to roof features, village buildings are classified, and a 3D roof point cloud is projected into 2D regular grid data. Finally, the roof slope is segmented via slope direction, and internal and external feature lines are obtained after refinement through Canny edge detection and Hough straight line detection. The results indicate that the CSF algorithm can effectively extract the roofs of I-shaped, L-shaped, and U-shaped traditional buildings. The accuracy of roof surface segmentation based on slope exceeds 99.6%, which is significantly better than the RANSAC algorithm and the region segmentation algorithm. This method is capable of efficiently extracting the characteristic lines of roofs in low-rise buildings within traditional villages. It provides a reference method for achieving the high-precision modeling of traditional village architecture at a low cost and with high efficiency.

Semantic Segmentation and Roof Reconstruction of Urban Buildings Based on LiDAR Point Clouds

In urban point cloud scenarios, due to the diversity of different feature types, it becomes a primary challenge to effectively obtain point clouds of building categories from urban point clouds. Therefore, this paper proposes the Enhanced Local Feature Aggregation Semantic Segmentation Network (ELFA-RandLA-Net) based on RandLA-Net, which enables ELFA-RandLA-Net to perceive local details more efficiently by learning geometric and semantic features of urban feature point clouds to achieve end-to-end building category point cloud acquisition. Then, after extracting a single building using clustering, this paper utilizes the RANSAC algorithm to segment the single building point cloud into planes and automatically identifies the roof point cloud planes according to the point cloud cloth simulation filtering principle. Finally, to solve the problem of building roof reconstruction failure due to the lack of roof vertical plane data, we introduce the roof vertical plane inference method to ensure the accuracy of roof topology reconstruction. The experiments on semantic segmentation and building reconstruction of Dublin data show that the IoU value of semantic segmentation of buildings for the ELFA-RandLA-Net network is improved by 9.11% compared to RandLA-Net. Meanwhile, the proposed building reconstruction method outperforms the classical PolyFit method.

A bottom-up method for roof plane extraction from airborne LiDAR point clouds

Accurate roof plane extraction is a crucial step in constructing a three-dimensional model for buildings. Due to the significant differences in size and shape of building roofs in airborne light detection and ranging point clouds, many existing plane extraction methods are struggling to achieve good performance. To solve the above problem, a bottom–up method for roof plane extraction is proposed in this paper. Starting with the division of the roof point cloud into voxels, the initial planes are obtained in the voxels. The initial planes are then expanded by a parameter-adaptive region growing algorithm. Then, the grown planes are merged according to predefined constraints. Finally, an energy minimization-based method is applied to optimize the results of roof plane extraction. The performance of our proposed method is evaluated on the Vaihingen dataset and the DALES dataset. Experiments demonstrate that our proposed method achieves a superior roof plane extraction result.

Detecting vertices of building roofs from ALS point cloud data

ABSTRACTRoof vertex information is vital for 3D roof structures. Reconstructing 3D roof structures from point cloud data using traditional methods remains a challenge because their extracted roof vertices are affected by uncertainty and additional errors from roof plane segmentation and supplementary sub-steps for extracting primitives. In this study, instead of segmenting roof planes and then extracting primitives based on them, a flexible rule-based method is proposed to directly detect the vertices of building roofs from point cloud data without the requirement of training data. The point cloud data is first voxelized with a dominant direction-based rotation. Based on the different features of the interior roof points and vertices, rules for voxel filtering and structure line determination are defined to extract the roof vertices. The experimental results on a custom dataset in Trondheim, Norway demonstrate that the proposed method can effectively and accurately extract roof vertices from point cloud data. The comparative experimental results with an unfine-tuned deep learning-based method on custom and benchmark datasets with different point densities further show that the proposed method has good generalization and can adapt to changes of datasets.

EVALUATION OF THE OLFACTORY FOSSA WITH COMPUTED TOMOGRAPHY FOR ENDOSCOPIC SURGERY

OBJECTIVE: The aim of this case-control study is to assess the olfactory fossa (OF) anatomy in computed tomography (CT) images of patients with clinical and radiological diagnoses of sinusitis as well as those of patients of a control group. MATERIAL AND METHODS: 100 patients without sinusitis and 100 patients with a clinical and radiological diagnosis of chronic sinusitis who were referred for CT scans were included. The OF types were recorded according to the Keros classification. Medial ethmoid roof point (MERP) height, cribriform plate (CP) height and width, OF depth and width, and angle of lateral lamella-cribriform plate (ALLCP) were also measured. RESULTS: The mean depth of OF was 5.9 mm and 6.1 mm on the right and left sides, respectively. The most common type was type 2 on the right (51%) and left (45.5%) sides. The mean height of the MERP was 27.9 mm in both the right and left sides. The mean height of CP was 22.0 mm and 21.8 mm on the right and left sides, respectively. The mean width of the OF was 4.1 mm and 3.4 mm on the right and left sides, respectively. The mean width of CP was 2.8 mm and 2.4 mm on the right and left sides, respectively.The mean right and left ALLCP were 77.6° and 79.1°, respectively. No significant difference was found between the parameters in the case and control groups. CONCLUSIONS: According to the results, the presence of sinusitis has no effect on the anatomy of the OF. However, preoperative evaluation of the OF anatomy is very important in minimizing complications that may occur during functional endoscopic sinus surgery (FESS).

Machine learning-based segmentation of aerial LiDAR point cloud data on building roof

ABSTRACT Three-dimensional (3D) reconstruction of a building can be facilitated by correctly segmenting different feature points (e.g. in the form of boundary, fold edge, and planar points) over the building roof, and then, establishing relationships among the constructed feature lines and planar patches using the segmented points. Present machine learning-based segmentation approaches of Light Detection and Ranging (LiDAR) point cloud data are confined only to different object classes or semantic labelling. In the context of fine-grained feature point classification over the extracted building roof, machine learning approaches have not yet been explored. In this paper, after generating the ground truth data for the extracted building roofs from three different datasets, we apply machine learning methods to segment the roof point cloud based on seven different effective geometric features. The goal is not to semantically enhance the point cloud, but rather to facilitate the application of 3D building reconstruction algorithms, making them easier to use. The calculated F1-scores for each class confirm the competitive performances over the state-of-the-art techniques, which are more than 95% almost in each area of the used datasets.

3D RECONSTRUCTION OF SIMPLE BUILDINGS FROM POINT CLOUDS USING NEURAL NETWORKS WITH CONTINUOUS CONVOLUTIONS (CONVPOINT)

Abstract. The automatic reconstruction of 3D building models from airborne laser scanning point clouds or aerial imagery data in a model-driven fashion most often consists of a recognition of standardized building primitives with typically rectangular footprints and parameterized roof shapes based on a pre-defined collection, and a parameter estimation so that the selected primitives best fit the input data. For more complex buildings that consist of multiple parts, several such primitives need to be combined. This paper focuses on the reconstruction of such simple buildings, and explores the potential of Deep Learning by presenting a neural network architecture that takes a 3D point cloud of a single building as input and outputs the geometric information needed to construct a 3D building model in half-space representation with up to four roof faces like saddleback, hip, and pyramid roof. The proposed neural network architecture consists of a roof face segmentation module implemented with continuous convolutions as used in ConvPoint, which performs feature extraction directly from a set of 3D points, and four PointNet modules that predict from sampled subsets of the feature-enriched points the presence of four roof faces and their slopes. Trained with the RoofN3D dataset, which contains roof point segmentations and geometric information for 3D reconstruction purposes for about 118,000 simple buildings, the neural network achieves a performance of about 80% intersection over union (IoU) for roof face segmentation, 1.8° mean absolute error (MAE) for roof slope angles, and 95% overall accuracy (OA) for predicting the presence of faces.

Fourfold Bounce Scattering-Based Reconstruction of Building Backs Using Airborne Array TomoSAR Point Clouds

Building reconstruction using high-resolution tomographic synthetic aperture radar (TomoSAR) point clouds has been very attractive in numerous applications, such as urban planning and dynamic city modeling. However, for side-looking TomoSAR, it is a challenge to reconstruct the obscured backs of buildings using traditional single-bounce scattering-based methods. It comes to our attention that the higher-order scattering points in airborne array TomoSAR point clouds may provide rich information on the backs of buildings. In this paper, the fourfold bounce (FB) scattering model of combined buildings in airborne array TomoSAR is derived, which not only explains the cause of FB scattering but also gives the distribution pattern of FB scattering points. Furthermore, a novel FB scattering-based method for the reconstruction of building backs is proposed. First, a two-step geometric constraint is used to detect the candidate FB scattering points. Subsequently, the FB scattering points are further detected by seed point selection and density estimation in the radar coordinate system. Finally, the backs of buildings can be reconstructed using the footprint inverted from the FB scattering points and the height information of the illuminated facades. To verify the FB scattering model and the effectiveness of the proposed method, the results from the simulated point clouds and the real airborne array TomoSAR point clouds are presented. Compared with the traditional roof point-based methods, the outstanding advantage of the proposed method is that it allows for the high-precision reconstruction of building backs, even in the case of poor roof points. Moreover, this paper may provide a novel perspective for the three-dimensional (3D) reconstruction of dense urban areas.

Building roof extraction from ASTIL echo images applying OSA-YOLOv5s.

Light detection and ranging (LiDAR) is a type of essential tool for urban planning and geoinformation extraction. Airborne streak tube imaging LiDAR (ASTIL) is a new system with great advantages in the rapid collection of remote sensing data. To the best of our knowledge, a new method to extract a building roof from the echo images of ASTIL is proposed. We improve YOLOv5s with a one-shot aggregation (OSA) module to improve efficiency. The experimental results show that the mean average precision of the OSA-YOLOv5s algorithm can reach 95.2%, and the frames per second can reach 11.74 using a CPU and 39.39 using a GPU. The method proposed can extract building objects efficiently from the echo images of ASTIL and acquire the building roof point cloud.

Automatic Filtering of Lidar Building Point Cloud in Case of Trees Associated to Building Roof

This paper suggests a new algorithm for automatic building point cloud filtering based on the Z coordinate histogram. This operation aims to select the roof class points from the building point cloud, and the suggested algorithm considers the general case where high trees are associated with the building roof. The Z coordinate histogram is analyzed in order to divide the building point cloud into three zones: the surrounding terrain and low vegetation, the facades, and the tree crowns and/or the roof points. This operation allows the elimination of the first two classes which represent an obstacle toward distinguishing between the roof and the tree points. The analysis of the normal vectors, in addition to the change of curvature factor of the roof class leads to recognizing the high tree crown points. The suggested approach was tested on five datasets with different point densities and urban typology. Regarding the results’ accuracy quantification, the average values of the correctness, the completeness, and the quality indices are used. Their values are, respectively, equal to 97.9%, 97.6%, and 95.6%. These results confirm the high efficacy of the suggested approach.

Historic Timber Roof Structure Reconstruction through Automated Analysis of Point Clouds.

We present a set of methods to improve the automation of the parametric 3D modeling of historic roof structures using terrestrial laser scanning (TLS) point clouds. The final product of the TLS point clouds consist of 3D representation of all objects, which were visible during the scanning, including structural elements, wooden walking ways and rails, roof cover and the ground; thus, a new method was applied to detect and exclude the roof cover points. On the interior roof points, a region-growing segmentation-based beam side face searching approach was extended with an additional method that splits complex segments into linear sub-segments. The presented workflow was conducted on an entire historic roof structure. The main target is to increase the automation of the modeling in the context of completeness. The number of manually counted beams served as reference to define a completeness ratio for results of automatically modeling beams. The analysis shows that this approach could increase the quantitative completeness of the full automatically generated 3D model of the roof structure from 29% to 63%.

Building Extraction from Terrestrial Laser Scanning Data with Density of Projected Points on Polar Grid and Adaptive Threshold

The extraction of building information with terrestrial laser scanning (TLS) has a number of important applications. As the density of projected points (DoPP) of facades is commonly greater than for other types of objects, building points can be extracted based on projection features. However, such methods usually suffer from density variation and parameter setting, as illustrated in previous studies. In this paper, we present a building extraction method for single-scan TLS data, mainly focusing on those problems. To adapt to the large density variation in TLS data, a filter using DoPP is applied on a polar grid, instead of a commonly used rectangular grid, to detect facade points. In DoPP filtering, the threshold to distinguish facades from other objects is generated adaptively for each cell by calculating the point number when placing the lowest building in it. Then, the DoPP filtering result is further refined by an object-oriented decision tree mainly based on grid features, such as compactness and horizontal hollow ratio. Finally, roof points are extracted by region growing on the non-facade points, using the highest point in each facade cell as a seed point. The experiments are conducted on two datasets with more than 1.7 billion points and with point density varying from millimeter to decimeter levels. The completeness and correctness of the first dataset containing more than 50 million points are 91.8% and 99.8%, with a running time of approximately 970 s. The second dataset is Semantic3D, of which the point number, completeness and correctness are about 1.65 billion, 90.2% and 94.5%, with a running time of about 14,464 s. The test shows that the proposed method achieves a better performance than previous grid-based methods and a similar level of accuracy to the point-based classification method and with much higher efficiency.

Radiological Evaluation of Olfactory Fossa with Cone-Beam Computed Tomography.

ABSTRACTObjectivesThe aim of this retrospective study was to evaluate the morphology of the olfactory fossa in the Turkish population using cone-beam computed tomography according to Keros classification and to investigate the effect of age, gender and nasal septum deviation on the olfactory fossa.Material and MethodsOlfactory fossa (OF) were analysed in coronal sections on cone-beam computed tomography images of 385 individuals. Nasal floor (NF), medial ethmoid roof point (MERP), cribriform plate (CP) heights, CP depth and width, OF width, lateral lamella-cribriform plate angle (LLCPA), and nasal septum deviation angle (NSDA) were measured. Keros and Gera classifications were made according to the measurements.ResultsAccording to the Keros classification, 137 of 770 OFs were type I (17.8%), 554 (71.9%) were type II, and 79 (10.3%) were type III. The most common combination was Keros type II and Gera type II (45.6%). There was a positive correlation between CP depth and LLCP angle, NF, MERP and CP heights (P ≤ 0.05). NF, MERP, and CP heights, CP depth and LLCP angle were statistically significant differences according to Keros classification (P ≤ 0.05). Only the right LLCP angle showed a statistically significant difference according to the NSD sides (P = 0.014).ConclusionsThe study shows that the lateral lamella-cribriform plate angle increases as the cribriform plate depth increases. This result suggests that it may moderate the risk during endoscopic sinus surgery. Also, according to the nasal septum deviation sides, the dimensions of the olfactory fossa did not change significantly, except for the lateral lamella-cribriform plate angle.

Airborne lidar planar roof point extraction using least‐squares fitting supervised by a posteriori variance estimation

AbstractThe least‐squares fitting method can be used for planar roof point extraction from airborne lidar points; however, it cannot avoid the impact of non‐planar roof points (blunders) due to lack of robustness. Therefore, this study has developed a least‐squares plane fitting based on a posteriori variance estimation, as proposed by Li in 1983, to reduce the weights of non‐planar roof points. Additionally, least absolute deviation (LAD) was integrated into the first step of this improved Li method, to increase blunder detection. For simulated data, the proposed approach increased the blunder detection rate by up to 6% compared to the original Li method. Test results with real data showed that the proposed approach demonstrated robustness, applicability and effectiveness.

Point Transformer for Shape Classification and Retrieval of Urban Roof Point Clouds

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input distribution and cannot learn long-range dependences. Recent works have shown that adding attention in conjunction with these methods improves performance. This raises a question: can attention layers completely replace convolutions? This letter proposes a fully attentional model—Point Transformer (PT) for deriving a rich point cloud representation. The model’s shape classification and retrieval performance are evaluated on a large-scale urban data set—RoofN3D and a standard benchmark data set ModelNet40. Extensive experiments are conducted to test the model’s robustness to unseen point corruptions for analyzing its effectiveness on real data sets. The proposed method outperforms other state-of-the-art models in the RoofN3D data set, gives competitive results in the ModelNet40 benchmark, and shows high robustness to various unseen point corruptions. Furthermore, the model is highly memory and space-efficient when compared to other methods.

HOLISTIC PARAMETRIC RECONSTRUCTION OF BUILDING MODELS FROM POINT CLOUDS

Abstract. Building models are conventionally reconstructed by building roof points via planar segmentation and then using a topology graph to group the planes together. Roof edges and vertices are then mathematically represented by intersecting segmented planes. Technically, such solution is based on sequential local fitting, i.e., the entire data of one building are not simultaneously participating in determining the building model. As a consequence, the solution is lack of topological integrity and geometric rigor. Fundamentally different from this traditional approach, we propose a holistic parametric reconstruction method which means taking into consideration the entire point clouds of one building simultaneously. In our work, building models are reconstructed from predefined parametric (roof) primitives. We first use a well-designed deep neural network to segment and identify primitives in the given building point clouds. A holistic optimization strategy is then introduced to simultaneously determine the parameters of a segmented primitive. In the last step, the optimal parameters are used to generate a watertight building model in CityGML format. The airborne LiDAR dataset RoofN3D with predefined roof types is used for our test. It is shown that PointNet++ applied to the entire dataset can achieve an accuracy of 83% for primitive classification. For a subset of 910 buildings in RoofN3D, the holistic approach is then used to determine the parameters of primitives and reconstruct the buildings. The achieved overall quality of reconstruction is 0.08 meters for point-surface-distance or 0.7 times RMSE of the input LiDAR points. This study demonstrates the efficiency and capability of the proposed approach and its potential to handle large scale urban point clouds.