Plane segmentation is a basic task in the automatic reconstruction of indoor and urban environments from unorganized point clouds acquired by laser scanners. As one of the most common plane-segmentation methods, standard Random Sample Consensus (RANSAC) is often used to continually detect planes one after another. However, it suffers from the spurious-plane problem when noise and outliers exist due to the uncertainty of randomly sampling the minimum subset with 3 points. An improved RANSAC method based on Normal Distribution Transformation (NDT) cells is proposed in this study to avoid spurious planes for 3D point-cloud plane segmentation. A planar NDT cell is selected as a minimal sample in each iteration to ensure the correctness of sampling on the same plane surface. The 3D NDT represents the point cloud with a set of NDT cells and models the observed points with a normal distribution within each cell. The geometric appearances of NDT cells are used to classify the NDT cells into planar and non-planar cells. The proposed method is verified on three indoor scenes. The experimental results show that the correctness exceeds 88.5% and the completeness exceeds 85.0%, which indicates that the proposed method identifies more reliable and accurate planes than standard RANSAC. It also executes faster. These results validate the suitability of the method.

Automatic building extraction from remote sensing imagery is important in many applications. The success of convolutional neural networks (CNNs) has also led to advances in using CNNs to extract man-made objects from high-resolution imagery. However, the large appearance and size variations of buildings make it difficult to extract both crowded small buildings and large buildings. High-resolution imagery must be segmented into patches for CNN models due to GPU memory limitations, and buildings are typically only partially contained in a single patch with little context information. To overcome the problems involved when using different levels of image features with common CNN models, this paper proposes a novel CNN architecture called a multiple-feature reuse network (MFRN) in which each layer is connected to all the subsequent layers of the same size, enabling the direct use of the hierarchical features in each layer. In addition, the model includes a smart decoder that enables precise localization with less GPU load. We tested our model on a large real-world remote sensing dataset and obtained an overall accuracy of 94.5% and an 85% F1 score, which outperformed the compared CNN models, including a 56-layer fully convolutional DenseNet with 93.8% overall accuracy and an F1 score of 83.5%. The experimental results indicate that the MFRN approach to connecting convolutional layers improves the performance of common CNN models for extracting buildings of different sizes and can achieve high accuracy with a consumer-level GPU.

Recent developments in laser scanning systems have inspired substantial interest in indoor modeling. Semantically rich indoor models are required in many fields. Despite the rapid development of 3D indoor reconstruction methods for building interiors from point clouds, the indoor reconstruction of multi-room environments with curved walls is still not resolved. This study proposed a novel straight and curved line tracking method followed by a straight line test. Robust parameters are used, and a novel straight line regularization method is achieved using constrained least squares. The method constructs a cell complex with both straight lines and curved lines, and the indoor reconstruction is transformed into a labeling problem that is solved based on a novel Markov Random Field formulation. The optimal labeling is found by minimizing an energy function by applying a minimum graph cut approach. Detailed experiments were conducted, and the results indicate that the proposed method is well suited for 3D indoor modeling in multi-room indoor environments with curved walls.

Ancient Chinese-style architecture has received increased attention during the last century as a segment of cultural heritage and is of great significance, specifically in regard to the process of digitizing and modeling these buildings to preserve and protect this heritage. Because the roof form reflects the age of the structure, the structural character and the historical culture of the ancient building, constructing a refined model for the roof is a primary aspect of the 3D modeling procedure. To avoid cumbersome traditional modeling approaches that use geometry units, such as points, lines and triangles, a flexible semantic method is proposed in this study to improve modeling efficiency and reduce the professional requirements. In this method, a two-level semantic decomposition of the roof is presented according to the characteristics of ancient Chinese-style architecture. The structural level reveals the basic components that determine its structural shape, and the decorative level refers to the attached components that influence the exterior appearance. The assembly validity of the decomposed elements and the combined diversity of the integrated entities are ensured by topological constraints and derived transformations of the semantic components. This proposed method was implemented by utilizing CityGML (City Geography Markup Language) via the ADE (Application Domain Extension) mechanism and was tested by modeling the principal buildings included in the Palace Museum.

Social media check-in data as a geo-tagged information source have been used for revealing spatio-temporal patterns in the field of social and urban study, such as human behavior or public issues. This paper investigates a case study and presents a new method of representing the mobility of people within a city from check-in data. By dividing the data in a temporal sequence, this study examines the overall mobility in the case study city through the gradient/difference of population density with a series of time after computing the population density from the check-in data using an incorporated Thiessen polygon method. By classifying check-in data with their geo-tags into several groups according to travel purposes, and partitioning the data according to administrative district boundaries, various moving patterns for those travel purposes in those administrative districts are identified by scrutinizing a series of spatial geometries of a weighted standard deviational ellipse (WSDE). Through deep analyses of those data by the adopted approaches, the general pattern of mobility in the case city, such as people moving to the central urban area from the suburb from 4 am to 8 am, is ascertained, and different characteristics of movement in those districts are also depicted. Furthermore, it can tell that in which district less movement is likely for a certain purpose (e.g., for dinner or entertainment). This study has demonstrated the availability of the proposed methodology and check-in data for investigating intra-urban human mobility.

The fast and stable reconstruction of building interiors from scanned point clouds has recently attracted considerable research interest. However, reconstructing long corridors and connected areas across multiple floors has emerged as a substantial challenge. This paper presents a comprehensive segmentation method for reconstructing a three-dimensional (3D) indoor structure with multiple stories. With this method, the over-segmentation that usually occurs in the reconstruction of long corridors in a complex indoor environment is overcome by morphologically eroding the floor space to segment rooms and by overlapping the segmented room-space with partitioned cells via extracted wall lines. Such segmentation ensures both the integrity of the room-space partitions and the geometric regularity of the rooms. For spaces across floors in a multistory building, a peak-nadir-peak strategy in the distribution of points along the z-axis is proposed in order to extract connected areas across multiple floors. A series of experimental tests while using seven real-world 3D scans and eight synthetic models of indoor environments show the effectiveness and feasibility of the proposed method.