Keywords: Indoor pathfinding, octree, network graph, connectivity, point cloud, collision avoidance There is a growing demand of 3D indoor pathfinding applications. Researched in the field of robotics during the last decades of the 20th century, these methods focussed on 2D navigation. Nowadays we would like to have the ability to help people navigate inside buildings or send a drone inside a building when this is too dangerous for people. What these examples have in common is that an object with a certain geometry needs to find an optimal collision free path between a start and goal point. This paper presents a new workflow for pathfinding through an octree representation of a point cloud. We applied the following steps: 1) the point cloud is processed so it fits best in an octree; 2) during the octree generation the interior empty nodes are filtered and further processed; 3) for each interior empty node the distance to the closest occupied node directly under it is computed; 4) a network graph is computed for all empty nodes; 5) the A* pathfinding algorithm is conducted. This workflow takes into account the connectivity for each node to all possible neighbours (face, edge and vertex and all sizes). Besides, a collision avoidance system is pre-processed in two steps: first, the clearance of each empty node is computed, and then the maximal crossing value between two empty neighbouring nodes is computed. The clearance is used to select interior empty nodes of appropriate size and the maximal crossing value is used to filter the network graph. Finally, both these datasets are used in A* pathfinding.
Discrete global grid systems (DGGSs) have emerged in recent years as a new specification for working with global heterogeneous data sets in a Digital Earth framework. Point clouds originating from different sources usually have varying initial characteristics. This research aims to analyze to what extent a DGGS can be used to handle point clouds having varying coordinate systems, acquired at different levels of detail (densities), and at different times in the creation of a global map of point clouds. DGGSs, which are currently limited to a 2D (surface) space, are extended into 3D and 4D spaces to fully harness the multidimensional nature of point clouds. A continuous spatial indexing strategy, based on a space-filling curve, is then developed on an ellipsoidal model of the Earth and used to efficiently cluster and retrieve DGGS-based point clouds stored in a database. Finally, the queried points are visualized in a Web browser. The hierarchical, multi-resolution nature of a DGGS is exploited to achieve a variable-scale smooth-zoom visualization. The challenges and opportunities of point cloud integration in a DGGS are presented.
Sustainable development can only be achieved with an innovative improvement from the way we currently analyze, design, build and manage our urban spaces. Current digital analysis and design methods for cities, such as visibility analysis, deeply rely on mapping and modeling techniques. However, most methods fall short of depicting the real visual landscape in the urban realm and this could bring a significant error in visibility calculations which may lead to an improper decision for urban spaces. The technical development of light detection and ranging(LiDAR) technology introduces new approaches for urban study. LiDAR utilizes point clouds including thousands or even millions of georeferenced points, and thus can support 3-D digital representation of urban landscape with detailed information and high resolution. Besides the superiority in representing urban landscape, LiDAR point clouds also has a clear advantage in quantitative analysis and provides better visibility than traditional models. In this paper, we first introduced a novel approach to map visibility in the urban built environment involving vegetation data directly using airborne LiDAR point clouds. This approach calculates neighborhood statistics for occlusion detection. Then we presented 2 case with different scenarios showing how our approach can be used to obtain a precise visibility in an urban area in the Netherlands. At last, we discussed how point clouds based visibility models can be further explored and can better assist urban design.
Point cloud data have rich semantic representations and can benefit various applications towards a digital twin. However, they are unordered and anisotropically distributed, thus being unsuitable for a typical Convolutional Neural Networks (CNN) to handle. With the advance of deep learning, several neural networks claim to have solved the point cloud semantic segmentation problem. This paper evaluates three different neural networks for semantic segmentation of point clouds, namely PointNet++, PointCNN and DGCNN. A public indoor scene of the Amersfoort railway station is used as the study area. Unlike the typical indoor scenes and even more from the ubiquitous outdoor ones in currently available datasets, the station consists of objects such as the entrance gates, ticket machines, couches, and garbage cans. For the experiment, we use subsets from the data, remove the noise, evaluate the performance of the selected neural networks. The results indicate an overall accuracy of more than 90% for all the networks but vary in terms of mean class accuracy and mean Intersection over Union (IoU). The misclassification mainly occurs in the classes of couch and garbage can. Several factors that may contribute to the errors are analyzed, such as the quality of the data and the proportion of the number of points per class. The adaptability of the networks is also heavily dependent on the training location: the overall characteristics of the train station make a trained network for one location less suitable for another.
13 September 2017 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Many research works have been oriented to the formulation of different algorithms for estimating the paths in indoor environments from three-dimensional representations of space. The architectural configuration, the actions that take place within it, and the location of some objects in the space influence the paths along which is it possible to move, as they may cause visibility problems. To overcome the visibility issue, different methods have been proposed which allow to identify the visible areas and from a certain point of view, but often they do not take into account the user’s visual perception of the environment and not allow estimating how much may be complicated to follow a certain path. In the field of space syntax and cognitive science, it has been attempted to describe the characteristics of a building or an urban environment by the isovists and visibility graphs methods; some numerical properties of these representations allow to describe the space as for how it is perceived by a user. However, most of these studies are directed to analyze the environment in a two-dimensional space. In this paper we propose a method to evaluate in a quantitative way the complexity of a certain path within an environment represented by a three-dimensional point cloud, by the combination of some of the previously mentioned techniques, considering the space visible from a certain point of view, depending on the moving agent (pedestrian , people in wheelchairs, UAV, UGV, robot).