Enhancing Urban Façades via LiDAR‐Based Sculpting

Buildings with symmetrical façades are ubiquitous in urban landscapes and detailed models of these buildings enhance the visual realism of digital urban scenes. However, a vast majority of the existing urban building models in web‐based 3D maps such as Google earth are either less detailed or heavily rely on texturing to render the details. We present a new framework for enhancing the details of such coarse models, using the geometry and symmetry inferred from the light detection and ranging (LiDAR) scans and 2D templates. The user‐defined 2D templates, referred to as coded planar meshes (CPMs), encodes the geometry of the smallest repeating 3D structures of the façades via face codes. Our encoding scheme, take into account the directions, type as well as the offset distance of the sculpting to be applied at the respective locations on the coarse model. In our approach, LiDAR scan is registered with the coarse models taken from Google earth 3D or Bing maps 3D and decomposed into dominant planar segments (each representing the frontal or lateral walls of the building). The façade segments are then split into horizontal and vertical tiles using a weighted point count function defined over the window or door boundaries. This is followed by an automatic identification of CPM locations with the help of a template fitting algorithm that respects the alignment regularity as well as the inter‐element spacing on the façade layout. Finally, 3D boolean sculpting operations are applied over the boxes induced by CPMs and the coarse model, and a detailed 3D model is generated. The proposed framework is capable of modelling details even with occluded scans and enhances not only the frontal façades (facing to the streets) but also the lateral façades of the buildings. We demonstrate the potentials of the proposed framework by providing several examples of enhanced Google earth models and highlight the advantages of our method when designing photo‐realistic urban façades.     

3D city models for urban farming site identification in buildings

Studies have suggested that there is farming potential in urban residential buildings. However, these studies are limited in scope, require field visits and time-consuming measurements. Furthermore, they have not suggested ways to identify suitable sites on a larger scale let alone means of surveying numerous micro-locations across the same building. Using a case study area focused on high-rise buildings in Singapore, this paper examines a novel application of three-dimensional (3D) city models to identify suitable farming micro-locations (level and orientation) in residential buildings. We specifically investigate whether the vertical spaces of these buildings comprising outdoor corridors, façades and windows receive sufficient photosynthetically active radiation (PAR) for growing food crops and do so at a high resolution. We also analyze the spatio-temporal characteristics of PAR, and the impact of shadows and different weather conditions on PAR in the building. Environmental simulations on the 3D model of the study area indicated that the cumulative daily PAR or Daily Light Integral (DLI) at a location in the building was dependent on its orientation and shape, sun's diurnal and annual motion, weather conditions, and shadowing effects of the building's own façades and surrounding buildings. The DLI in the study area generally increased with building's levels and, depending on the particular micro-location, was found suitable for growing moderately light-demanding crops such as lettuce and sweet pepper. These variations in DLI at different locations of the same building affirmed the need for such simulations. The simulations were validated with field measurements of PAR, and correlation coefficients between them exceeded 0.5 in most cases thus, making a case that 3D city models offer a promising practical solution to identifying suitable farming locations in residential buildings, and have the potential for urban-scale applications.     

Geometry and Bonding Rules Position Analysis in the Formation of Traditional Iranian Architectural Brick Facades

Over time, architectural ornaments have had a variety of forms that are created from a combination of different types of materials and factors. Brick decorations are one such example, a type of ornament that is often formed on the exterior façade of buildings. Investigating covert rules and brick bonds geometry can reveal a part of the ancient architectural secrets and ways used to reduce the ravages upon new brick façades. Shaped bricks in traditional Iranian architecture directly affect the placement, size and brick arrangement rules. This article is the first attempt to study the effects of geometry and the principal rules of arrangement that help to shape the formation of brick façades specifically, as well as analysing the samples of brick façades taken from monuments, field recordings and discussion with the workmen themselves. The analysis has revealed that permanent rules govern the bonding of brick façades, along with the size and dimensions of the brick effects, which shape the final look of the decoration.     

Impacts of tree and building shades on the urban heat island: Combining remote sensing, 3D digital city and spatial regression approaches

The continued increase in average and extreme temperatures around the globe is expected to strike urban communities more harshly because of the urban heat island (UHI). Devising natural and design-based solutions to stem the rising heat has become an important urban planning issue. Recent studies have examined the impacts of 2D/3D urban land-use structures on land surface temperature (LST), but with little attention to the shades cast by 3D objects, such as buildings and trees. It is, however, known that shades are particularly relevant for controlling summertime temperatures. This study examines the role of urban shades created by trees and buildings, focusing on the effects of shade extent and location on LST mitigation. A realistic 3D digital representation of urban and suburban landscapes, combined with detailed 2D land cover information, is developed. Shadows projected on horizontal and vertical surfaces are obtained through GIS analysis, and then quantified as independent variables explaining LST variations over grids of varying sizes with spatial regression models. The estimation results show that the shades on different 3D surfaces, including building rooftops, sun-facing façades, not-sun-facing façades, and on 2D surfaces including roadways, other paved covers, and grass, have cooling effects of varying impact, showing that shades clearly modify the thermal effects of urban built-up surfaces. Tree canopy volume has distinct effects on LST via evapotranspiration. One of the estimated models is used, after validation, to simulate the LST impacts of neighborhood scenarios involving additional greening. The findings illustrate how urban planners can use the proposed methodology to design 3D land-use solutions for effective heat mitigation.     

Urban 3D segmentation and modelling from street view images and LiDAR point clouds

3D urban maps with semantic labels and metric information are not only essential for the next generation robots such autonomous vehicles and city drones, but also help to visualize and augment local environment in mobile user applications. The machine vision challenge is to generate accurate urban maps from existing data with minimal manual annotation. In this work, we propose a novel methodology that takes GPS registered LiDAR (Light Detection And Ranging) point clouds and street view images as inputs and creates semantic labels for the 3D points clouds using a hybrid of rule-based parsing and learning-based labelling that combine point cloud and photometric features. The rule-based parsing boosts segmentation of simple and large structures such as street surfaces and building facades that span almost 75% of the point cloud data. For more complex structures, such as cars, trees and pedestrians, we adopt boosted decision trees that exploit both structure (LiDAR) and photometric (street view) features. We provide qualitative examples of our methodology in 3D visualization where we construct parametric graphical models from labelled data and in 2D image segmentation where 3D labels are back projected to the street view images. In quantitative evaluation we report classification accuracy and computing times and compare results to competing methods with three popular databases: NAVTEQ True, Paris-Rue-Madame and TLS (terrestrial laser scanned) Velodyne.     

Automatic façade recovery from single nighttime image

Nighttime images are difficult to process due to insufficient brightness,lots of noise,and lack of details.Therefore,they are always removed from time-lapsed image analysis.It is interesting that nighttime images have a unique and wonderful building features that have robust and salient lighting cues from human activities.Lighting variation depicts both the statistical and individual habitation,and it has an inherent man-made repetitive structure from architectural theory.Inspired by this,we propose an automatic nighttime fa?ade recovery method that exploits the lattice structures of window lighting.First,a simple but efficient classification method is employed to determine the salient bright regions,which may be lit windows.Then we groupwindows into multiple lattice proposals with respect to fa?ades by patch matching,followed by greedily removing overlapping lattices.Using the horizon constraint,we solve the ambiguous proposals problem and obtain the correct orientation.Finally,we complete the generated fa?ades by filling in the missing windows.This method is well suited for use in urban environments,and the results can be used as a good single-view compensation method for daytime images.The method also acts as a semantic input to other learning-based 3D image reconstruction techniques.The experiment demonstrates that our method works well in nighttime image datasets,and we obtain a high lattice detection rate of 82.1%of 82 challenging images with a low mean orientation error of 12.1±4.5 degrees.     

Procedural Modeling of a Building from a Single Image

Creating a virtual city is demanded for computer games, movies, and urban planning, but it takes a lot of time to create numerous 3D building models. Procedural modeling has become popular in recent years to overcome this issue, but creating a grammar to get a desired output is difficult and time consuming even for expert users. In this paper, we present an interactive tool that allows users to automatically generate such a grammar from a single image of a building. The user selects a photograph and highlights the silhouette of the target building as input to our method. Our pipeline automatically generates the building components, from large‐scale building mass to fine‐scale windows and doors geometry. Each stage of our pipeline combines convolutional neural networks (CNNs) and optimization to select and parameterize procedural grammars that reproduce the building elements of the picture. In the first stage, our method jointly estimates camera parameters and building mass shape. Once known, the building mass enables the rectification of the façades, which are given as input to the second stage that recovers the façade layout. This layout allows us to extract individual windows and doors that are subsequently fed to the last stage of the pipeline that selects procedural grammars for windows and doors. Finally, the grammars are combined to generate a complete procedural building as output. We devise a common methodology to make each stage of this pipeline tractable. This methodology consists in simplifying the input image to match the visual appearance of synthetic training data, and in using optimization to refine the parameters estimated by CNNs. We used our method to generate a variety of procedural models of buildings from existing photographs.     

Building renovation adopts mass customization

This work is motivated by an industrial need of manufacturing façades insulating envelopes in order to reduce energy consumption in residential buildings. An insulating envelope is a configuration of a set of rectangular panels that respects a set of limitations. Due to the number of façades to be renovated and the number of possible configurations for a single façade, the envelope configuration is both a mass customization problem as well as a combinatorial one. The paper then introduces a decision support system based on the framework of constraint satisfaction, as it fits neatly the constrained nature of the problem. Two configuration tasks have been identified as prerequisite to envelopes configurations: (1) the configuration of a questionnaire for information inputs and (2) the configuration of a constraint satisfaction problem for each one of the façades to be renovated. The system architecture promotes maintenance, modularity and efficiency as different configuration tasks are divided into web-services. Conception and implementation of the massive building thermal renovation are then supported.     

A curvature estimation for pen input segmentation in sketch-based modeling

A proper segmentation of pen marking enhances shape recognition and enables a natural interface for sketch-based modeling from simple line drawing tools to 3D solid modeling applications; user input is otherwise restricted to draw only one segment per one stroke. In general, the pen marking segmentation is achieved by detecting the points of high curvature-called, segmenting points-and splitting the pen marking at those points. This paper presents a curvature estimation method, which considers only local shape information. The proposed method can therefore estimate curvature on-the-fly while user is drawing on a pen-input display, such as tablet PCs.     

Automatic generation of fabrication drawings for façade mullions and transoms through BIM models

Fabrication drawings are essential for manufacturing, design evaluation and inspection of building components, especially for building façade structural components. In order to clearly represent the physical characteristics of the façade structural components, a large number of section views need to be produced, which is very time-consuming and labor intensive. Therefore, automatic generation of fabrication drawings for building façade components (such as mullions and transoms) is of paramount importance. In this paper, attempts have been made to develop an efficient framework in order to automatically generate fabrication drawings for building façade structural components, including mullions and transoms. To represent the complex physical characteristics (such as holes and notches) on mullions and transoms using minimum number of drawing views, a computational algorithm based on graph theory is developed to eliminate duplicated section views. Another methodology regarding the generation of breaks for top views is also proposed to further improve the quality of drawing layouts. The obtained drawing views are then automatically arranged using a developed approach. In addition, primary dimensions of the drawing views focusing on the physical features are also generated. Furthermore, in order to maintain the consistency of drawing formats across multiple drawings, a methodology is proposed to determine the scaling factors of the drawings by using clustering technique. In an illustrative example, the proposed framework is used to generate the fabrication drawings for a typical BIM model containing façade structural components, and saving in time is observed.     

Image Registration in a Coarse Three-Dimensional Virtual Environment

In recent years, the availability of off‐the‐shelf geometric data for an urban environment has increased. During rendering, ground level images are mapped onto the façades of the buildings to improve the visual quality of the scene. This paper focuses on a technique that enables ground level images to be automatically integrated into an existing coarse three‐dimensional environment. The approach utilises the planar nature of architectural scenes to enable the automatic extraction of a building façade from an image and its registration into the virtual environment.     

Extracting inundation patterns from flood watermarks with remote sensing SfM technique to enhance urban flood simulation: The case of Ayutthaya,Thailand

Flood watermarks stipulate peak water depths from a flood event, indicating a magnitude of inundation that took place. Such information is invaluable for instantiation and validation of urban flood models. However, collecting and processing such data from land surveys can be costly and time-consuming. New remote sensing and data processing technologies offer improved opportunities to address these issues. The present paper deals with the new structure from motion (SfM) technology and its application in extracting flood watermarks. For this purpose, the first of its kind, side-view SfM surveys with two mobile units were utilised. Survey works were carried out in the vicinity of Ayutthaya heritage area (Thailand) and data obtained were used for setting up numerical models and simulations of the 2011 flood event. The work undertaken demonstrates the significant capability of SfM technology for extraction of flood watermarks. With such technology, it was possible to indicate façades, low-level structures, and susceptible openings, which in turn have improved schematizations of two-dimensional (2D) flood models. The resulting model simulations were found to be more accurate (i.e., more close to the measurements of flood watermarks) than those obtained from models with conventional top-view light detection and ranging (LiDAR) data.     

融合稀疏注意力和实例增强的雷达点云分割

目的 雷达点云语义分割是3维环境感知的重要环节,准确分割雷达点云对象对无人驾驶汽车和自主移动机器人等应用具有重要意义。由于雷达点云数据具有非结构化特征,为提取有效的语义信息,通常将不规则的点云数据投影成结构化的2维图像,但会造成点云数据中几何信息丢失,不能得到高精度分割效果。此外,真实数据集中存在数据分布不均匀问题,导致小样本物体分割效果较差。为解决这些问题,本文提出一种基于稀疏注意力和实例增强的雷达点云分割方法,有效提高了激光雷达点云语义分割精度。方法 针对数据集中数据分布不平衡问题,采用实例注入方式增强点云数据。首先,通过提取数据集中的点云实例数据,并在训练中将实例数据注入到每一帧点云中,实现实例增强的效果。由于稀疏卷积网络不能获得较大的感受野,提出Transformer模块扩大网络的感受野。为了提取特征图的关键信息,使用基于稀疏卷积的空间注意力机制,显著提高了网络性能。另外,对不同类别点云对象的边缘,提出新的TVloss用于增强网络的监督能力。结果 本文提出的模型在SemanticKITTI和nuScenes数据集上进行测试。在SemanticKITTI数据集上,本文方法在线单帧...     

基于二维自动主动形状模型的椎间盘核磁共振图像分割算法

针对椎间盘手动建模主观耗时以及现有分割方法不够准确的问题,提出了一种二维自动主动形状模型(2D-AASM)方法,由基于最小描述长度的椎间盘自动统计形状建模、二维局部梯度建模和分割三部分组成。将25组脊柱核磁共振图像(MRI)的椎间盘专家分割结果作为训练集,采用基于最小描述长度的方法确定点对应关系,建立椎间盘T4-5的统计形状模型和二维局部梯度模型,生成形状模型的方差和目标函数值均小于手工和弧长参数方法。模型建立后,通过3组脊柱MRI数据测试提出的分割方法,与传统主动形状模型（ASM）和加入一维局部梯度模型的ASM方法相比,其分割结果具有更高的戴斯系数值,更低的过分割率和欠分割率。实验结果表明,所提方法建立的模型更准确,分割结果更精确。     

Interaction with Media Façades

Media façades are a prominent example of the digital augmentation of urban spaces. They denote the concept of turning the surface of a building into a large-scale urban screen. Because of their enormous size, they require interaction at a distance and they have a high level of visibility. Additionally, they are situated in a highly dynamic urban environment with rapidly changing conditions, which results in settings which are neither comparable, nor reproducible. Altogether, this makes the development of interactive media façade installations a challenging task.     

结合超体素和区域增长的植物器官点云分割

点云分割是点云识别与建模的基础。为提高点云分割准确率和效率，提出一种结合超体素和区域增长的自适应分割算法。根据三维点云的空间位置和法向量信息，利用八叉树对点云进行初始分割得到超体素。选取超体素的中心体素组成一个新的重采样后的密度均匀点云，降低原始点云数据处理量，从而减少运算时间。建立重采样后点云数据的K-D树索引，根据其局部特征得到点云簇。最后将聚类结果返回到原始点云空间。分别选取植物三个物候期的激光扫描点云，对该方法的有效性进行验证。实验结果表明，该方法分割后点云与手工分割平均拟合度达到93.38%，高于其他同类方法，且算法效率得到明显提升。     

地面LiDAR数据中建筑轮廓和角点提取

建筑轮廓和角点作为多平台激光雷达数据常用的配准基元,其提取方法正受到越来越多的关注.投影密度法是一种常用的从地面LiDAR数据中提取建筑轮廓和角点的方法,然而以往研究对于直接影响建筑轮廓提取结果的格网密度阈值考虑较少.提出一种轮廓密度估计的方法,能够根据点云实际情况自动准确地计算出格网密度阈值,从而提取较为准确的建筑轮廓格网.在此基础上,利用轮廓线段高程分割和密度延伸的方法对轮廓进行分割和恢复,能够提取完整的建筑轮廓.最后,利用轮廓线段的相交关系获得建筑角点.实验结果表明,本文方法能够有效从地面LiDAR数据中提取建筑轮廓和角点,正确性、完整性和定位精度较高.     

基于知识的车载LiDAR地物自动分类

车载LiDAR已广泛应用于三维数字城市建模、道路信息数据采集等领域。海量点云信息中不同地物目标的自动识别和分类是LiDAR数据后处理的难点之一。根据不同地物目标物理特性、空间拓扑关系及其在点云中的相关特征知识,建立地物分类规则,依据分类知识进行地物自动识别和分类。通过实测数据分类试验,证明该方法可以较好实现建筑物、树木、线杆、行人等不同地物的自动识别和分类。