Classification Of Building Types Research Articles

Machine Learning Model for Building Type Classification of Cultural Heritage Sites along Jiangnan Canal: A Comparative Study of Historical and Modern Images

Machine Learning Model for Building Type Classification of Cultural Heritage Sites along Jiangnan Canal: A Comparative Study of Historical and Modern Images

Residential building type classification from street-view imagery with convolutional neural networks

Residential building type classification from street-view imagery with convolutional neural networks

Can linguistic features extracted from geo-referenced tweets help building function classification in remote sensing?

The fusion of two or more different data sources is a widely accepted technique in remote sensing while becoming increasingly important due to the availability of big Earth Observation satellite data. As a complementary source of geo-information to satellite data, massive text messages from social media form a temporally quasi-seamless, spatially multi-perspective stream, but with unknown and diverse quality. Despite the uncontrolled quality: can linguistic features extracted from geo-referenced tweets support remote sensing tasks? This work presents a straightforward decision fusion framework for very high-resolution remote sensing images and Twitter text messages. We apply our proposed fusion framework to a land-use classification task – the building function classification task – in which we classify building functions like commercial or residential based on linguistic features derived from tweets and remote sensing images. Using building tags from OpenStreetMap (OSM), we labeled tweets and very high-resolution (VHR) images from Google Maps. We collected English tweets from San Francisco, New York City, Los Angeles, and Washington D.C. and trained a stacked bi-directional LSTM neural network with these tweets. For the aerial images, we predicted building functions with state-of-the-art Convolutional Neural Network (CNN) architectures fine-tuned from ImageNet on the given task. After predicting each modality separately, we combined the prediction probabilities of both models building-wise at a decision level. We show that the proposed fusion framework can improve the classification results of the building type classification task. To the best of our knowledge, we are the first to use semantic contents of Twitter messages and fusing them with remote sensing images to classify building functions at a single building level.

Classification of Building Types in Germany: A Data-Driven Modeling Approach

Details on building levels play an essential part in a number of real-world application models. Energy systems, telecommunications, disaster management, the internet-of-things, health care, and marketing are a few of the many applications that require building information. The essential variables that most of these models require are building type, house type, area of living space, and number of residents. In order to acquire some of this information, this paper introduces a methodology and generates corresponding data. The study was conducted for specific applications in energy system modeling. Nonetheless, these data can also be used in other applications. Building locations and some of their details are openly available in the form of map data from OpenStreetMap (OSM). However, data regarding building types (i.e., residential, industrial, office, single-family house, multi-family house, etc.) are only partially available in the OSM dataset. Therefore, a machine learning classification algorithm for predicting the building types on the basis of the OSM buildings’ data was introduced. Although the OSM dataset is the fundamental and most crucial one used for modeling, the machine learning algorithm’s training was performed on a dataset that was prepared by combining several features from three other datasets. The generated dataset consists of approximately 29 million buildings, of which about 19 million are residential, with 72% being single-family houses and the rest multi-family ones that include two-family houses and apartment buildings. Furthermore, the results were validated through a comparison with publicly available statistical data. The comparison of the resulting data with official statistics reveals that there is a percentage error of 3.64% for residential buildings, 13.14% for single-family houses, and −15.38% for multi-family houses classification. Nevertheless, by incorporating the building types, this dataset is able to complement existing building information in studies in which building type information is crucial.

Opportunities for passive cooling to mitigate the impact of climate change in Switzerland

Energy systems need to decarbonize rapidly whilst satisfying heating and cooling needs. In Switzerland, residential cooling has so far only a small impact on the national energy demand, but climate change and a larger uptake of cooling devices are expected to lead to future increases. This requires novel approaches for sustainable cooling solutions suitable for implementation at a national scale. Here, we explore the potential of night ventilation and window shading to reduce the buildings cooling demand in a changing climate. A physical bottom-up approach is used to simulate residential space cooling demand and to identify the passive cooling potential whilst considering a detailed representation of the Swiss building stock, featuring building age, construction properties, regional climate, urban layout and occupant behaviour. A supervised building type classification approach is applied to enable up-scaling to the national level. Results show that in 2050, the residential Swiss building stock will require a national cooling demand of around 10.2 TWh for a Representative Concentration Pathway scenario 4.5. Under such future climatic conditions, we simulated a potential to reduce the total cooling demand by 84%, with both passive cooling solutions combined. Individually, window shading could reduce cooling demands by 71% and night ventilation by 38%. We found that newer buildings (built after 2000) already account for about 50% of the total current cooling energy demand. Results demonstrate that night ventilation and window shading have the potential to mitigate the impact of climate change in Switzerland and to improve the sustainability and resilience of residential cooling.

Deep Learning Classification of Building Types in Northern Cyprus

Among the areas where AI studies centered on developing models that provide real-time solutions for the real estate industry are real estate price forecasting, building age, and types and design of the building (villa, apartment, floor number). Nevertheless, within the ML sector, DL is an emerging region with an Interest increases every year. As a result, a growing number of DL research are in conferences and papers, models for real estate have begun to emerge. In this study, we present a deep learning method for classification of houses in Northern Cyprus using Convolutional neural network. This work proposes the use of Convolutional neural networks in the classification of houses images. The classification will be based on the house age, house price, number of floors in the house, house type i.e. Villa and Apartment. The first category is Villa versus Apartments class; based on the training dataset of 362 images the class result shows the overall accuracy of 96.40%. The second category is split into two classes according to age of the buildings, namely 0 to 5 years Apartments 6 to 10 years Apartments. This class is to classify the building based on their age and the result shows the accuracy of 87.42%. The third category is villa with roof versus Villa without roof apartments class which also shows the overall accuracy of 87.60%. The fourth category is Villa Price from 10,000 euro to 200,000 Versus Villa Price from 200,000 Euro to above and the result shows the accuracy of 81.84%. The last category consists of three classes namely 2 floor Apartment versus 3 floor Apartment, 2 floor Apartment versus 4 floor Apartment and 2 floor Apartment versus 5 floor Apartment which all shows the accuracy of 83.54%, 82.48% and 84.77% respectively. From the experiments carried out in this thesis and the results obtained we conclude that the main aims and objectives of this thesis which is to used Deep learning in Classification and detection of houses in Northern Cyprus and to test the performance of AlexNet for houses classification was successful. This study will be very significant in creation of smart cities and digitization of real estate sector as the world embrace the used of the vast power of Artificial Intelligence, machine learning and machine vision.

Fast generation of microclimate weather data for building simulation under heat island using map capturing and clustering technique

In this research, Urban Weather Generator (UWG) is utilized for UHI modeling in a center city area of Shenzhen based on urban morphologic data collected by an information-collection framework. The framework uses map capturing technique and unsupervised clustering for building type classification to gather input parameters for UHI model. The developed building type clustering technique, which adopted principal component analysis and Gaussian Mixture Model, is shown to have potential application in district-scale UHI modeling. Together with a differential-evolution-based calibration procedure, the proposed framework is implemented to the UWG modeling for the selected urban tissue. After calibration, it is found that the weighted sum of coefficient of variance for temperature and relative humidity has been reduced from 7.45 % to around 5.5 % compared with the uncalibrated model. The simulation results shows that the annual mean UHI index and max UHI index in center city Shenzhen is found to be 0.50 °C and 5.9 °C. After applying UHI effect to the typical meteorological year (TMY) data, the cooling degree day and heating degree day change by +12.60 % and −11.92 % compared with the original TMY. The developed method is computationally efficient and the morphed TMY data is a more accurate reflection on local urban microclimate.

The Building Data Genome Project 2, energy meter data from the ASHRAE Great Energy Predictor III competition

This paper describes an open data set of 3,053 energy meters from 1,636 non-residential buildings with a range of two full years (2016 and 2017) at an hourly frequency (17,544 measurements per meter resulting in approximately 53.6 million measurements). These meters were collected from 19 sites across North America and Europe, with one or more meters per building measuring whole building electrical, heating and cooling water, steam, and solar energy as well as water and irrigation meters. Part of these data was used in the Great Energy Predictor III (GEPIII) competition hosted by the American Society of Heating, Refrigeration, and Air-Conditioning Engineers (ASHRAE) in October-December 2019. GEPIII was a machine learning competition for long-term prediction with an application to measurement and verification. This paper describes the process of data collection, cleaning, and convergence of time-series meter data, the meta-data about the buildings, and complementary weather data. This data set can be used for further prediction benchmarking and prototyping as well as anomaly detection, energy analysis, and building type classification.

Damage Probability Assessment of Hospital Buildings in Yogyakarta, Indonesia as Essential Facility due to an Earthquake Scenario

Indonesia is a country located in an earthquake-prone region, and is characterized by significantly increased peak ground acceleration value. The seismic hazard map of Indonesia stated in SNI 1726-2012 and the current statistics published by PUSGEN in 2017 emphasized on the significance of assessing building damage probabilities, especially for essential structures in Yogyakarta. However, immediate action is required to handle response and recovery operations during and after a disaster. The aim of this study, therefore, is to ascertain the vulnerability and damage probability of hospital buildings in Yogyakarta by employing the 2006 earthquake scenario, where reports showed the destruction of over 156,000 houses and other structures. Furthermore, a Hazard-US (HAZUS) method was used for structural analysis, while a ground motion prediction equation was adopted to produce the building response spectra, following the characteristics of the earthquake incidence. The vital step in this assessment involves building type classification and identification of seismic design levels. However, the damage tendency of buildings is determined using the peak building response, which ensures the generation of capacity curves. The most significant findings on building damage probability value were less than 15% in each damage state (slight, moderate, extensive, complete). In addition, the optimum value was achieved at the minimum level of damage (minor), while the least values were recorded at the highest damage level (complete).

Prediction of Socio-Economic Indicators for Urban Planning Using VHR Satellite Imagery and Spatial Analysis

Ongoing urbanization leads to steady growth of urban areas. In the case of highly dynamic change of municipalities, due to the rates of change, responsible administrations often are challenged or struggle with capturing present states of urban sites or accurately planning future urban development. An interest for urban planning lies on socio-economic conditions, as consumption and production of disposable goods are related to economic possibilities. Therefore, we developed an approach to generate relevant parameters for infrastructure planning by means of remote sensing and spatial analysis. In this study, the single building defines the spatial unit for the parameters. In the case city Belmopan (Belize), based on WorldView-1 data we manually define a city covering building dataset. Residential buildings are classified to eight building types which are locally adapted to Belmopan. A random forest (RF) classifier is trained with locally collected training data. Through household interviews focusing on household assets, income and educational level, a socio-economic point (SEP) scaling is defined, which correlates very well with the defined building typology. In order to assign socio-economic parameters to the single building, five socio-economic classes (SEC) are established based on SEP statistics for the building types. The RF building type classification resulted in high accuracies. Focusing on the three categories to describe residential socio-economic states allowed high correlations between the defined building and socio-economic points. Based on the SEP we projected a citywide residential socio-economic building classification to support supply and disposal infrastructure planning.

Has Dongying developed to a ghost city? - Evidence from multi-temporal population estimation based on VHR remote sensing and census counts

With ongoing growth and continuous development of cities, the world is turning into an urban society. In this context, urbanization, population growth and migration towards urban areas are global trends. These processes are highly dynamic especially in China, with highest rates of urbanization worldwide. In contrast to these well-known trends, a recently emerging and rarely studied side effect is “ghost cities”, which became a notable phenomenon in China recently. A ghost city is commonly defined as a new urban development that is running at severe undercapacity with respect to population and businesses and where the availability of housing and public infrastructure significantly exceeds the practical demand. Against this background, this study presents a framework based on remote sensing for the assessment of the presence or absence of the ghost city phenomenon in a typical highly dynamic Chinese city. For this purpose, remote sensing data with very-high resolution (VHR) are employed for establishment of a 4d functional city model. Subsequently population capacity estimates are based on a statistical approach. The components of the functional 4d city model, i.e. the multi-temporal building model and the classification of building types associated with residential and non-residential function returned very high accuracies with κ of 0.73 and 0.89, respectively. The number of floors was estimated with coefficient of determination of 0.91. Compared to the numbers of official census counts, the multi-temporal population capacity estimation revealed a considerable mismatch of available living space based on VHR remote sensing data and actual population counts. According to the conceptual framework of this study, this disagreement indicates a high likelihood and significant evidence for the emergence and presence of the ghost city phenomenon for the city of Dongying. In addition, a detailed spatial assessment was conducted in terms of an index comparing the dynamics of residential developments and population numbers to provide an impression of specific regions of the urban area which are most likely to suffer from the ghost city phenomenon.

Model Fusion for Building Type Classification from Aerial and Street View Images

This article addresses the question of mapping building functions jointly using both aerial and street view images via deep learning techniques. One of the central challenges here is determining a data fusion strategy that can cope with heterogeneous image modalities. We demonstrate that geometric combinations of the features of such two types of images, especially in an early stage of the convolutional layers, often lead to a destructive effect due to the spatial misalignment of the features. Therefore, we address this problem through a decision-level fusion of a diverse ensemble of models trained from each image type independently. In this way, the significant differences in appearance of aerial and street view images are taken into account. Compared to the common multi-stream end-to-end fusion approaches proposed in the literature, we are able to increase the precision scores from 68% to 76%. Another challenge is that sophisticated classification schemes needed for real applications are highly overlapping and not very well defined without sharp boundaries. As a consequence, classification using machine learning becomes significantly harder. In this work, we choose a highly compact classification scheme with four classes, commercial, residential, public, and industrial because such a classification has a very high value to urban geography being correlated with socio-demographic parameters such as population density and income.

A Novel Building Type Classification Scheme Based on Integrated LiDAR and High-Resolution Images

Building type information is crucial to many urban studies, including fine-resolution population estimation, urban planning, and management. Although scientists have developed many methods to extract buildings via remote sensing data, only a limited number of them focus on further classification of the extracted results. This paper presents a novel building type classification scheme based on the integration of building height information from LiDAR, textural, spectral, and geometric information from high-resolution remote sensing images, and super-object information from the integrated dataset. Building height information is firstly extracted from LiDAR point clouds using a progressive morphological filter and then combined with high-resolution images for object-oriented segmentation. Multi-resolution segmentation of the combined image is performed to collect super-object information, which provides more information for classification in the next step. Finally, the segmentation results, as well as their super-object information, are inputted into the random forest classifier to obtain building type classification results. The classification scheme proposed in this study is tested through applications in two urban village areas, a type of slum-like land use characterized by dense buildings of different types, heights, and sizes, in Guangzhou, China. Segment level classification of the study area and validation area reached accuracies of 80.02% and 76.85%, respectively, while the building-level results reached accuracies of 98.15% and 87.50%, respectively. The results indicate that the proposed building type classification scheme has great potential for application in areas with multiple building types and complex backgrounds. This study also proves that both building height information and super-object information play important roles in building type classification. More accurate results could be obtained by incorporating building height information and super-object information and using the random forest classifier.

Building Types’ Classification Using Shape-Based Features and Linear Discriminant Functions

In this paper, the applicability and performance of linear discriminant analysis (LDA) for building types’ classification are investigated. Building models at a level of detail 1 (LoD1) are derived from real estate cadastral building footprints and digital surface models from stereoscopic airborne images. In several experiments for two cities in Germany (Berlin and Munich), we first evaluate the discriminatory power of 26 different shape-based features which describe the physiognomy of individual buildings in terms of 1-D (e.g., length), 2-D (e.g., area), and 3-D (e.g., volume) features. While 1-D features show low contributions to the discrimination of the five building types, we observe high contributions of the 3-D shape index and 2-D measures of compactness. In a second group of experiments, the size of training samples for the classification process is investigated with the outcome that a size of 10% of the total number of labeled features is practicable in terms of size and accuracy. In a third battery of experiments, the selected features and training sample size are used for the classification of building types resulting in kappa values of 0.94 for both cities. In the final experiments, the geographical transfer between the two cities is investigated reaching kappa values of 0.93 and 0.91, respectively. The tests show that a simple linear classifier like LDA can handle building types’ classification without much user interaction compared to more complex classification methods but is limited when similar building types (e.g., perimeter block development and block development ) are to be discriminated.

Can street segments indexed for accessibility form the basis for housing submarket delineation?

We test an approach to spatial housing submarket delineation using street segment as the spatial unit and using finely grained measures of accessibility derived from spatial network analysis. The underlying idea is that street segment connectivity captures fine variations in homebuyers’ preferences for the location. The advantage of the approach is that it is spatially fine grained; it uses the street segment, intuitively the most fundamental spatial unit for spatial housing market analysis; it allows the use of statistical tests to optimize within-submarket similarities, identifying spatial groups of street segments with the most similar accessibility features; it avoids the predefined arbitrary geographic boundaries usually used in spatial submarket delineation; it increases the variability of accessibility information in submarket delineation, accessibility being the principal spatial determinant of housing price; and it allows for normalized measures of accessibility at different spatial scales making it appropriate for comparative analysis across cities and across time. Using a case study of Cardiff, UK, we compare the results with a market segmentation scheme based on prior-knowledge, notably one relying on building-type classification. We conclude that street layout can be used to efficiently delineate housing submarkets, and that the estimation is very close to the scheme requiring prior-knowledge. It has advantages, however, that make it worthy of further investigation, namely its adaptability, scale-specificity and lower reliance on local knowledge of housing market culture and data.

Building type classification using spatial and landscape attributes derived from LiDAR remote sensing data

Building information is one of the key elements for a range of urban planning and management practices. In this study, an investigation was performed to classify buildings delineated from light detection and ranging (LiDAR) remote sensing data into three types: single-family houses, multiple-family houses, and non-residential buildings. Four kinds of spatial attributes describing the shape, location, and surrounding environment of buildings were calculated and subsequently employed in the classification. Experiments were performed in suburban and downtown sites in Denver, CO, USA, considering different building components and neighborhood environments. Building type classification results yielded overall accuracy>70% and Kappa>0.5 for both sites, demonstrating the feasibility of obtaining building type information from LiDAR data. The shape attributes, such as width, footprint area, and perimeter, were most useful for identifying building types. Environmental landscape attributes surrounding buildings, such as the number of road and parking lot pixels, also contributed to obtaining building type information. Combining shape and environmental landscape attributes was necessary to obtain accurate and consistent classification results.

Ontology-Based Classification of Building Types Detected from Airborne Laser Scanning Data

Accurate information on urban building types plays a crucial role for urban development, planning, and management. In this paper, we apply Object-Based Image Analysis (OBIA) methods to extract buildings from Airborne Laser Scanner (ALS) data and investigate the possibility of classifying detected buildings into “Residential/Small Buildings”, “Apartment Buildings”, and “Industrial and Factory Building” classes by means of domain ontology and machine learning techniques. The buildings objects are classified using exclusively the information computed from the ALS data. To select the relevant features for predicting the classes of interest, the Random Forest classifier has been applied. The ontology-based classification yielded convincing results for the “Residential/Small Buildings” class (F-Measure 97.7%), whereas the “Apartment Buildings” and “Industrial and Factory Buildings” classes achieved less accurate results (F-Measure 60% and 51%, respectively).

Automatic classification of building types in 3D city models

This article presents a classifier based on Support Vector Machines (SVMs), an advanced machine learning method for semantic enrichment of coarse 3D city models by deriving the building type. The i...

Automatic classification of building types in 3D city models

This article presents a classifier based on Support Vector Machines (SVMs), an advanced machine learning method for semantic enrichment of coarse 3D city models by deriving the building type. The information on the building type (detached building, terraced building, etc.) is essential for a variety of relevant applications of 3D city models like spatial marketing, real estate management and marketing, and for visualization. The derivation of the building type from coarse data (mainly 2D footprints, building heights and functions) seems impossible at first sight. However it succeeds by incorporating the spatial context of a building. Since the input data can be derived easily and at very low cost, this method is widely applicable. Nevertheless, as with all supervised learning algorithms, obtaining labelled training data is very time-consuming. Herewith, we provide a method which uses outlier detection and clustering methods to support users in efficiently and rapidly obtaining adequate training data.

Sketch for an Archetypal Building

An archetypal form of building is proposed, to which the forms of actual buildings may be related by continuous deformation of parts and by suppression of some parts altogether. Parallels are drawn with pre-Darwinian ideas about archetypal forms in biology. The archetypal building serves to represent those overall properties of the envelope which are determined by the constraints of lighting and the close-packing of certain generic types of space—'cellular space’, ‘open-plan space’, and ‘halls’. Four worked examples are given showing the transformation of the archetype into real historical buildings. Potential applications are suggested in the classification of building types, in building science, in architectural history, and in design support systems.