3-D model construction using range and image data

Some types of laser range scanner measuring range and color data simultaneously are used to acquire 3D structure of outdoor scenery. However, a laser range scanner cannot give us perfect information about target objects such as buildings, and various factors incur defects of range data. We present a defect detection scheme based on the region segmentation using observed range and color data, and apply a time-evolution method to the repair of defective range data. As to the defect detection, performing the segmentation, we divide observed data into several regions corresponding to buildings, the ground and so on. Using the segmentation results, we determine defect regions. Given defect regions, their range data will be repaired from observed data in their neighborhoods. Reforming the transportation-based inpainting algorithm, previously developed for the defect repair of an intensity image, we construct a new defect-repair method that applies the interleaved sequential updates, composed of the transportation-based inpainting and the data projection onto the viewing direction of each range sample, to 3D point data converted from observed range data. The performance evaluations using artificially damaged test range data demonstrate that our repair method outperforms the existing repair methods both in quantitative performance and in subjective quality.

Virtual Reality (VR) technology has been applied in many fields since 1960s, such as research, education, manufacture, entertainment, medical, and urban planning. This chapter focuses on the current situation and progress of VR application in urban planning and managing, as well as on the future perspective oriented to digital urban planning and managing.

3D building models play a critical role in smart cities and strongly support applications in urban planning, augmented reality and urban event simulation. Urban scale city modelling with City Geography Markup Language (CityGML) LOD2 building models have been constructed in over several developed cities due to their significant role and relatively high cost. However, existing single-building reconstruction methods for LOD2 models are unsatisfactory in preserving roof details, and large-scale 3D building reconstruction still requires extensive manual editing. This paper proposes a fully automated framework for generating CityGML LOD2 building models with preferred roof details from photogrammetric point clouds from aerial oblique images, aiming to address two key challenges: (1) difficulties in LOD2 building model generation caused by missing facade photogrammetric point clouds, and (2) insufficient fidelity of building roof details. Based on the observation that buildings have typical “roof-vertical walls-ground” structures, this paper infers facade areas by height maps generated from roof point clouds. Besides, the Hypothesis-Selection-Based (HSB) polygon surface reconstruction frameworks are extended by introducing a novel voxel depth index to measure the importance of each candidate planar unit in preserving roof details. Experimental comparison with existing HSB methods and deep-learning-based methods revealed that the reconstruction of proposed methods achieves the best geometry accuracy in Root Mean Squared Error (RMSE) ranging from 0.157m to 0.660m, and also achieves the best model coverage that is between 75.14% to 93.15%. Reconstruction applications using two typical datasets which include 288 buildings and 106 buildings respectively indicate that our method is competent for the task of large-scale 3D building reconstruction, thus, supporting various urban computing applications related to fine-scale 3D building models.

Using range data in automatic modeling of buildings

A fusion technique is presented for 3-D representation. The fusion involves laser range data and segmented image data, using human expertise related to the environment. In particular, the range data may contain noise due to reflections on sloped surfaces or long open corridors; the proposed approach removes the noise by using human expertise from 3-D environments. This method could be utilized either by an autonomous robot in an unknown environment, or by an inspection machine in a complex manufacturing environment, or by a visual navigation device used by blind people. Additional applications for this technique are to correct measurement deficiencies in a laser scan and to provide a true color and 3-D perceived-shape representation for a given object in a modeling environment.

Unmanned ground vehicle for facility protection mostly uses model of territory for autonomous navigation. However, modeling of territory using several sensors is highly time consuming and sometimes inefficient for road application. Therefore, an estimation of drivable path based on features of road is required for high speed autonomous navigation on road. In this paper, an estimation method of drivable path using camera and 2D laser rangefinder is proposed. First, a vanishing point is estimated based on image data from CCD camera. Second, a road width is estimated based on range data from 2D laser rangefinder. Finally, the drivable path is estimated by fusing the vanishing point and the road width. The proposed method is tested on both well-structured road and unpaved road like cross-country situation.

This paper considers the segmentation of range image measurements into surface patches which are either plane or curved and which are described formally by a function. After a formal description of the segmentation, we present and compare three methods suited for plane and curved patch segmentation and show the results of experiments conducted for testing their practical behaviour. The two first methods use the classical approach of region growing whereas the third method is based on a relaxation process. This original and last method exhibits simplicity and low computational complexity. Thanks to its parallel nature, it can be considered as a good candidate for range image segmentation in real-time applications.

Multiscale feature extraction in image data has been investigated for many years. More recently the problem of processing images containing irregularly distribution data has became prominent. We present a multiscale Laplacian approach that can be applied directly to irregularly distributed data and in particular we focus on irregularly distributed 3D range data. Our results illustrate that the approach works well over a range of irregular distributed and that the use of Laplacian operators on range data is much less susceptive to noise than the equivalent operators used on intensity data.

We propose a novel range finding technique for measuring the 3D shape of objects. Experiments were carried out to verify the principle of this technique, and effectiveness of the technique was demonstrated through the experiments. The new range finding technique, which is based on a spatial encoding method, uses a single light pattern encoded with multiple values and enables the acquisition of range information of an object in a single shot. The conventional spatial encoding method uses a projector for projecting a light pattern onto an object and a CCD camera for measuring the 3D shape of the object. In this new technique, we use an additional CCD camera to cancel the influence of the texture of the object. The additional CCD camera is positioned so that the principal point and optical axis of the camera's lens become the same as those of the projector's lens. The light pattern projected onto the object is encoded again using image data captured by the additional CCD camera. Range image data acquired using this technique is highly accurate. We call this technique the Spatial Re-encoding method or SR method. We made an experimental model and captured range data of an object form different viewpoints to evaluate the effectiveness of the SR method. The whole 3D shape of the object was successfully built using those range data. This paper describes the new range finding technique called the SR method.© (2002) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Predictive analytics powered by machine learning (ML) techniques is revolutionizing urban development. By enabling data-based ethics. ML models can be applied to analyze large data sets, followed by predicting urban growth patterns and optimizing them through the allocation of resources and enhanced infrastructure planning, which is a point covered in further depth in this chapter. Combining data from various sources—satellite imagery, census records, and IoT devices—these models can yield valuable insights into traffic management, housing demand, environmental sustainability, and energy consumption. The article covers techniques including regression analysis, clustering, and neural networks focused on their urban planning applications. The chapter also discusses challenges and limitations, such as data privacy issues, model interpretability, and the digital divide, and suggests potential solutions. The integration of ML in urban development can lead to intelligent, sustainable cities worldwide, improving quality of life and resource utilization for future generations.

Purpose: To develop a simple, analytic parameterization of stopping power and range, which covers a wide energy interval and is applicable to many species of projectile ions and target materials, with less than 15% disagreement in linear stopping power and 1 mm in range. Methods: The new parameterization was required to be analytically integrable from stopping power to range, and continuous across the range interval of 1 µm to 50 cm. The model parameters were determined from stopping power and range data for hydrogen, carbon, iron, and uranium ions incident on water, carbon, aluminum, lead and copper. Stopping power and range data was taken from SRIM. A stochastic minimization algorithm was used to find model parameters, with 10 data points per energy decade. Additionally, fitting was performed with 2 and 26 data points per energy decade to test the model's robustness to sparse Results: 6 free parameters were sufficient to cover the therapeutic energy range for each projectile ion species (e.g. 1 keV – 300 MeV for protons). The model agrees with stopping power and range data well, with less than 9% relative stopping power difference and 0.5 mm difference in range. As few as, 4 bins per decade were required to achieve comparable fitting results to the full data set. Conclusion: This study successfully demonstrated that a simple analytic function can be used to fit the entire energy interval of therapeutic ion beams of hydrogen and heavier elements. Advantages of this model were the small number (6) of free parameters, and that the model calculates both stopping power and range. Applications of this model include GPU-based dose calculation algorithms and Monte Carlo simulations, where available memory is limited. This work was supported in part by a research agreement between United States Naval Academy and Louisiana State University: Contract No N00189-13-P-0786. In addition, this work was accepted for presentation at the American Nuclear Society Annual Meeting 2016.

The paper proposes two approaches to improve the Iterative Closest Point (ICP) algorithm in the registration of large scale range data obtained by a Velodyne LIDAR at different locations in an outdoor environment. The first proposed approach discards points that cannot be matched in the datasets during the registration process to prevent errors from these points from affecting the results. The second approach extracts feature points that are representative of the datasets to perform the registration process and similarly preventing mismatching points from affecting the results. Experiments show that both approaches perform better than the original ICP algorithm.

Roads are important for many urban planning applications, such as traffic modelling and delivery vehicle routing. At present, most available datasets represent roads only as centrelines. This is particularily true for OpenStreetMap which provides, among many features, road networks at worldwide coverage. Furthermore, most approaches for creating more detailed networks, such as carriageways or lanes, focus on doing so from sources that are not easy to acquire, such as satellite imagery or LiDAR scans. In this paper we present a methodology to create carriageways based on OpenStreetMap’s centrelines and open access areal representations (i.e. polygons) to determine which roads should be represented as two individual carriageways. We applied our methodology in five areas across four different countries with different built environments. We analysed the outcome in a delivery routing problem to evaluate the validity of our results. Our results suggest that this method can be effectively applied to create carriageways anywhere in the world, as long as there is sufficient coverage by OpenStreetMap and an areal representation dataset of roads.

Not seeing the forest for the trees: Modeling exurban viewscapes with LiDAR

Urban forest is of great interest to a variety of scientific and urban planning applications. This paper presents a strategy for calculating tree canopy density in urban areas using Landsat ETM+ imagery and calculating its ecological value. The strategy consists of two key steps: one is to extract urban tree canopy area from remote sensing images; the other is to calculate the ecological value of urban forest. The extraction of tree canopy area from remote sensing imagery is carried out using classification models, which are based on empirical relationships between forest coverage and the spectrum on Landsat imagery, and are generated using regression tree techniques. The calculation about urban forest is carried out introducing CITYgreen model. In the analysis, the zone inside the 4th Ring Road in Beijing is chosen as study area; and a Landsat ETM+ image taken in 2001 is used applying this strategy to analyze the urban forest. In the following part, the results of the analysis are presented. At the end, the accuracy of tree canopy density is reviewed, and some possible reasons for the error are discussed, as well as the advantages and disadvantages of this strategy.