Urban Mapping Research Articles

Automatic Detection and 3D Reconstruction of Buildings from Historical Maps

ABSTRACT This paper presents an automatic 3D building reconstruction methodology for historical urban maps. It uses facade and openings detection on the maps, followed by rectification, regularization, and 3D model generation techniques. Evaluation metrics confirm the effectiveness of the approach, with high accuracy in detecting facades and their openings while maintaining geometric integrity. The flexibility and interoperability of the chosen 3D building representation method allow for adjustments in dimensions without compromising layout, making it suitable for completing the urban environments where facades may not be directly visible. This methodology represents a significant step toward automating the reconstruction of 3D historical urban landscapes, contributing to heritage preservation and architectural understanding.

Urban Color Plan: The case study of the Ledro Valley (Italy)

AbstractThis research delves into the development of the Urban Color Plan for Ledro Valley, in Italy. Urban color, encompassing both natural and built elements, plays a crucial role in spatial perception, impacting an individual's cognitive and sensory experiences. This study aims to address the complexity of color planning by an operational method grounded in scientific research. Through the analysis of existing color plans and the study of this specific case, the paper proposes a methodology which emphasizes scientific scrutiny by encompassing factors like historical context, social aspects, environmental influences and a chromatic and material facade survey. The research outlines the multifaceted scales of intervention, ranging from urban mapping to material quality considerations. The Ledro Valley case study exemplifies the application of this methodology, revealing the challenge in harmonizing the diverse historical‐political realities of this Valley. The results showcase a flexible color plan that unifies the territory while still preserving the distinct identities of individual previous municipalities, demonstrating the plan's adaptability and potential for enhancing the overall urban environment.

Obtaining LULC distribution at 30-m resolution from Pixxel’s first technology demonstrator hyperspectral imagery

ABSTRACT The recent deployment of new satellite-based hyperspectral imaging sensors, along with advances in classification methods, has enhanced the acquisition of information on the spatiotemporal patterns of Land Use/Land Cover (LULC).. With this context, the study presented in this paper seeks to assess the combined utilization of the Pixxel’s technology demonstrator hyperspectral satellite mission with the Support Vector Machines (SVM) and Random Forest (RF) machine learning classifiers for LULC mapping in an agricultural area located in Queensland, Australia. Accuracy assessment of the resulting LULC maps has been done based on relevant classification accuracy metrics. It has been observed that SVMs outperformed RF in terms of both overall classification and urban vegetation cover mapping accuracy. An overall accuracy of 92.34% with kappa of 0.90 was reported for the SVMs’ results, whereas for RF, the accuracy was 89.65% with 0.89 kappa, respectively. Both classifiers produced similar results for the classes of mango tree and sugarcane crops, whereas minor differences were observed in the depiction of water bodies and artificial surfaces. Our study findings provide insightful perspectives on the potential of Pixxel datasets for delineating the spatiotemporal distribution of LULC in agricultural landscapes, showcasing Pixxel’s hyperspectral sensors’ promising potential in this field.

Fusion of multi-temporal PlanetScope data and very high-resolution aerial imagery for urban tree species mapping

Detailed assessment of the ecosystem services provided by urban green spaces requires data on urban tree species. While many approaches for mapping of urban trees from remotely sensed data have been proposed, the fusion of multi-temporal satellite imagery with very high resolution orthophotos remains relatively underexplored. In this research, we assess the potential of a multimodal deep learning approach with intermediate data fusion for classifying common tree species found in the Brussels Capital Region. Our method combines two image sources: (a) multi-temporal PlanetScope data and (b) high-resolution aerial imagery. To evaluate the contribution of each image source, we separately train and assess each branch of the network. Both image sources demonstrate the ability to predict prevalent tree species with high accuracy. However, the fusion of the two image sources yields the best results, achieving an overall accuracy of 0.88 for the five most common tree species in the region. Our approach is compared to two conventional machine learning methods: a random forest (RF) and a support vector machine classifier (SVM) and outperforms both with a 11 percentage point increase in overall accuracy over RF and a 10 percentage point increase over SVM. Increasing the number of species from five to thirteen, including all species with more than 500 tree samples, results in a marginal decrease in accuracy (from 0.88 to 0.84). Overall, our deep learning approach demonstrates its efficacy in classifying common tree species in urban settings and provides a foundation for a comprehensive quantification of ecosystem services offered by urban trees through remote sensing data.

Classification of compressed full-waveform airborne lidar data

ABSTRACT Airborne laser scanners produce 3D data that can be used for a range of applications, such as urban planning, facility monitoring, flood mapping, and forest management. Additional information on the surveyed area can be obtained from the backscattered waveforms recorded by modern light detection and ranging (lidar) sensors. However, the high-dimensional representation of full-waveform data has hindered progress in its use due to difficulties in processing and storage. This paper develops a quantized convolutional autoencoder network to compress lidar waveform data into a condensed feature representation, resulting in a compression rate of up to 20:1. This, together with height information, is fed into a U-net convolutional neural network that achieves an accuracy of 93.7% on six classes.

Dynamic heatmap pyramid computation for massive high-parallel spatial streaming in urban environments

ABSTRACT It is necessary to integrate data and information effectively in order to build an integrated digital and refined urban system. A multi-granularity and multi-view urban heat map formed by integrating multi-source urban information flow can assist in immediate decision-making. Managing urban big data in the form of streams requires a stable operating environment that can efficiently handle millions of sensors and devices connected to the Internet of Things (IoT) in a highly concurrent environment. Urban management data contain spatiotemporal multi-dimensional information that presents the complexity of spatiotemporal dynamic associations, further increasing the difficulty of data streaming. To overcome these challenges, we have proposed a spatiotemporal-pyramid (ST-pyramid) model that organizes multidimensional and dynamic data streams logically using a data partition strategy based on geographical grid subdivision. Accordingly, we have proposed a load-balanced heatmap pyramid computation framework that can be used to build streaming processing procedures in a distributed environment. In addition, we implemented an urban traffic heatmap prototype system based on an open-source Flink framework. The experimental results show that the real-time heatmap pyramid construction algorithm proposed in this paper has high throughput, low latency, and flexible scalability and can provide large-scale public services in time in digital earth construction.

Urban functional zone mapping by coupling domain knowledge graphs and high‐resolution satellite images

AbstractTimely and accurate mapping of urban functional zones (UFZs) is crucial to urban planning and management. Although existing methods for identifying urban functions have made remarkable progress, they still suffer from limitations, such as high sample dependency, insufficient semantic relationship representation, and poor interpretability due to being data‐driven models. To bridge this gap between these methods and the way humans identify functional areas, a new framework that couples domain knowledge and remote sensing images was proposed for the mapping of UFZs. First, to model the concepts, attributes, and spatial and semantic relationships of urban functional objects, a UFZ knowledge graph (UFZ‐KG) was constructed to assist in the mapping of UFZs. Then, the contrastive language‐image pretraining model was adopted to encode jointly the semantic features of UFZ‐KG and the visual features of UFZ images. In this model, a nonlinear embedding module was designed to achieve semantic alignment of these two different modal features in shared space. The effectiveness of the proposed method was verified in three test areas in Shenzhen, China. Results demonstrate that the proposed method of coupling UFZ‐KG with satellite images significantly enhances the UFZ classification accuracy compared to the method that solely relies on image features. Furthermore, it exhibits good generalization performance.

The Correlation Between Asian Port Cities and Traditional Portuguese Urban Forms Based on Map and Machine Learning Analyses

In the 16th and 17th centuries, under the influence of the Portuguese Empire’s overseas expansion and cultural integration, the island city of Macau became an important international trading port in the Eastern Sea, with close ties to the Asian port cities governed by Portugal. This study introduces a new method for comparing urban morphological layouts using machine learning and investigates the potential benefits of combining urban morphological analysis with machine learning techniques. In addition, a combination of urban morphology theory and machine learning is used to excise samples of urban morphology from Portuguese urban geographical information maps. The morphological characteristics of port city areas are further extracted, and training labels for typical Portuguese urban textures are established. Using the YOLOv4 object detection algorithm, the results are compared with the urban textures of typical island and port cities of the Asian Silk Road—Goa in India, Malacca in Malaysia, Macau in China, and Dili in Timor-Leste—revealing the similarities and differences among the port cities in Asia influenced by traditional Portuguese urban practices. The results reveal the relationship between maritime trade and urban form.

Open-source data alternatives for regenerating urban road fine-grained features

The extraction of urban road features provides indispensable support to numerous high-accurate applications such as autonomous driving and urban high-definition mapping. However, approaches mainly focus on road connectivity, while often overlooking finer details of urban road constituent structures. Data that captures road details, such as LiDAR, may not be always readily available. This article proposes an operational framework for mapping fine-grained urban road features by integrating open-source data (OSD). The geometric measurement method is successively presented using projective geometry and prior knowledge for urban road sections. And a feature generation strategy is introduced to achieve and express the fine-grained road features. Compared with the corresponding large-scale topographic map (LTM) and available optical remote sensing image (AORSI), the proposed method regenerated fine-grained features of urban roads with m-level. It provides a cost-effective innovative and alternative method to acquiring fine-grained road datasets in other data-scarce regions.

Revolutionizing urban mapping: deep learning and data fusion strategies for accurate building footprint segmentation

In the dynamic urban landscape, understanding the distribution of buildings is paramount. Extracting and delineating building footprints from high-resolution images, captured by aerial platforms or satellites, is essential but challenging to accomplish manually, due to the abundance of high-resolution data. Automation becomes imperative, yet it introduces complexities related to handling diverse data sources and the computational demands of advanced algorithms. The innovative solution proposed in this paper addresses some intricate challenges occurring when integrating deep learning and data fusion on Earth Observed imagery. By merging RGB orthophotos with Digital Surface Models, deriving from the same aerial high-resolution surveys, an integrated consistent four-band dataset is generated. This unified approach, focused on the extraction of height information through stereoscopy utilizing a singular source, facilitates enhanced pixel-to-pixel data fusion. Employing DeepLabv3 algorithms, a state-of-the-art semantic segmentation network for multi-scale context, pixel-based segmentation on the integrated dataset was performed, excelling in capturing intricate details, particularly when enhanced by the additional height information deriving from the Digital Surface Models acquired over urban landscapes. Evaluation over a 21 km2 area in Turin, Italy, featuring diverse building frameworks, showcases how the proposed approach leads towards superior accuracy levels and building boundary refinement. Notably, the methodology discussed in the present article, significantly reduces training time compared to conventional approaches like U-Net, overcoming inherent challenges in high-resolution data automation. By establishing the effectiveness of leveraging DeepLabv3 algorithms on an integrated dataset for precise building footprint segmentation, the present contribution holds promise for applications in 3D modelling, Change detection and urban planning. An approach favouring the application of deep learning strategies on integrated high-resolution datasets can then guide decision-making processes facilitating urban management tasks.

Evaluation of a Ground Subsidence Zone in an Urban Area Using Geophysical Methods.

An important geological risk to which many towns in Puglia are exposed is sinking cavities in urban areas. For urban centers, studying, mapping, providing geological and speleological descriptions, classifying, and cataloging the forms and types of cavities is essential because cavities are linked to past local anthropic and natural processes at different sites. These circumstances could lead to the enhancement of existing underground cavities in urban areas through conservation and continuous monitoring. Unfortunately, in many cases, these underground cavities have been used as landfills and subsequently abandoned. In late March 2007, one of these cavities collapsed inside Gallipoli's inhabited center, causing damage to the structures but fortunately not human lives. In the area surrounding the collapsed cavity, a series of geophysical investigations were undertaken using ground penetrating radar in an attempt to delimit the area of collapse and develop possible interventions for restoration. In the same area, these measures were repeated 16 years later in December 2022 due to another collapse. The comparison between data acquired in these two periods shows that there were no strong changes apart from an increased presence of subsoil moisture in 2022.

From Material Cadastres to a Materiality Informed City Information Modelling

Abstract Urbanization and built environment significantly impact resource consumption, posing sustainability challenges, especially regionally, due to bulk material dominance. Circular practices, like closing, slowing, and narrowing offer solutions. However, effective circularity management requires understanding built environment material stock comprehensively. Material cadastres model city and regional materiality using typology approaches and GIS Modelling, offering insights into circularity potential and supporting strategic circular city management. Conversely, urban planning digitalization introduced City Information Modelling, linking GIS for urban structure mapping with Building Information Modelling systems for digital building integration and thus support urban planning. Yet, empirically, materiality and circularity issues lack systematic and comprehensive integration in such approaches. To this end, this paper discusses the potential of developing digital material cadastre concepts towards materiality-based urban information modelling using case study results that reveal strengths and limitations of existing cadastre concepts. We present a methodological overview covering a general approach to built environment material cadastres and the main components of the underlying bottom up Material Flow approach: material composition indicators and GIS based building stock modelling and a dynamization approach. To discuss circularity potentials of the built environment in a larger urban regional development context, we furthermore designed material cadastres for two case study cities and calculated exemplary circularity potentials for closing, slowing and narrowing approaches. The findings and drafted conclusions were then reflected with urban planning and development actors in workshops and group discussions. As a result, we present consolidated propositions with respect to bridging the methodological gap between strategic and operational materiality informed urban and regional planning in the transition of the built environment towards circularity.

Multi-Scale Urban Natural Ventilation Climate Guidance: A Case Study in the Shijiazhuang Metropolitan Area

The rapid development of urbanization has caused obstructed urban natural ventilation and the contribution rate of urbanization is relatively high. Therefore, there is an urgent need for urban development planning that should respect natural ventilation and local climate to reduce negative impacts. By optimizing the urban construction layout to reduce obstruction and leave a passageway for wind to blow in, the natural ventilation environment could be improved. This paper presents a promising approach for natural ventilation planning at both the city and community scales. Based on the assessment of wind environment, heat island intensity, and ventilation potential, the results revealed that winds blowing from the western and northern mountainous area of Shijiazhuang play a natural ventilation inlet role which can provide clean air. The SSHI and SHI were mainly distributed within the Second Ring Road, which has a large proportion of the low ventilation potential level. Thus, six first-class ventilation corridors and thirteen secondary corridors were recommended, which were set to be adapted to the dominant wind direction. Subsequently, an urban climate analysis map (UCAnMap) was developed considering climate sensitivity, and planning recommendations were provided for different climate zones. The relationship between architectural spatial structure and ventilation efficiency was analyzed; the results revealed that increasing the height of the buildings will decrease the proportion of comfortable wind zones, and the overall ventilation efficiency will weaken, so the average building height of a typical block should be controlled within 45 m, which matches ventilation performance requirements. The ventilation efficiency of the block has a certain negative correlation with the building density, and as the building density decreased by more than 10%, the proportion of the comfortable wind zones could increase by 4–5%.

(Re)envisioning inclusive futures: Applying narrative foresight to deconstruct the problem of urban flooding in the slums of Bengaluru, India

AbstractMotivationRecurring urban flooding in Bengaluru, India, has brought multiple intersecting development challenges to the forefront. While climate change is a catalyst for flooding, rapid urbanisation has aggravated the problem by neglecting its ecological history. Repeated floods have particularly affected migrants living in the slums, further worsening their already vulnerable conditions. Currently, only about 40% of slums are formally recognized by city authorities, leaving most slum dwellers with limited access to public benefits and basic infrastructure. Although the city offers piecemeal solutions, it currently lacks foresight for long‐term planning that includes marginalized voices.PurposeWe explore the multiple and intertwined development challenges faced by Bengaluru city, attempting to frame them from the perspective of migrant slum dwellers experiencing flooding. We try to bring to the forefront the everyday risks and vulnerabilities of the marginalized populations in Indian cities, which have received limited attention both in research and policy.The results of this exercise are intended to create sustainable collaborative processes to inform future decisions, particularly addressing the problem of urban flooding.Methods and approachOur proposed methodology integrates climate risk assessment—urban flood modelling and exposure mapping of slums across the city—with vulnerability assessments at the household level including analysis of life histories to capture the relative vulnerabilities of slum dwellers and the slums in which they live.FindingsWe deconstruct urban flooding, particularly from the perspective of migrant slum dwellers to identify some critical challenges, especially that of recognition, to foresight thinking. By incorporating marginalized voices, our methods aim to be inclusive and contextually relevant, while considering intersectional variations among those marginalized.A mixed‐methods approach allows climate risk assessment to be augmented by life histories of vulnerable slum populations to collaboratively reimagine a more inclusive future.Policy implicationsTo make policy more inclusive, more participatory processes are needed. The proposed methods will contextualize everyday vulnerabilities and risks of migrant slum dwellers to bring these perspectives into conventional climate risk assessment. Thus, a more inclusive future with lower impacts from urban floods can be envisaged.

Real-Time Urban Flood Depth Mapping: Convolutional Neural Networks for Pluvial and Fluvial Flood Emulation

Real-Time Urban Flood Depth Mapping: Convolutional Neural Networks for Pluvial and Fluvial Flood Emulation

GIS-based spatial approaches to refining urban catchment delineation that integrate stormwater network infrastructure

Rapid urbanization and escalating climate change impacts have heightened stormwater-related concerns (e.g., pluvial flooding) in cities. Understanding catchment dynamics and characteristics, including precise catchment mapping, is essential to accurate surface water monitoring and management. Traditionally, topography is the primary data set used to model surface water flow dynamics in undisturbed natural landscapes. However, urban systems also contain stormwater drainage infrastructure, which can alter catchment boundaries and runoff behavior. Acknowledging both natural and built environmental influences, this study introduces three GIS-based approaches to enhance urban catchment mapping: (1) Modifying DEM elevations at inlet locations; (2) Adjusting DEM elevations along pipeline paths; (3) Applying the QGRASS plug-in to systematically incorporate infrastructure data. Our evaluation using the geographical Friedman test (p > 0.05) and Dice Similarity Coefficient (DSC = 0.80) confirms the statistical and spatial consistency among the studying methods. Coupled with onsite flow direction validation, these results support the feasibility and reliability of integrating elements of nature and built infrastructure in urban catchment mapping. The refined mapping approaches explored in this study offer improved and more accurate and efficient urban drainage catchment zoning, beyond using elevation and topographic data alone. Likewise, these methods bolster predictive stormwater management at catchment scales, ultimately strengthening urban stormwater and flooding resilience.

Simultaneous Calibration of Multiple Cameras and Generation of Omnidirectional Images

Abstract. Omnidirectional images are increasingly being used in various areas, such as urban mapping, virtual reality, agriculture, and robotics. These images can be generated by different acquisition systems, including multi-camera systems, which can acquire higher-resolution images. Stitching techniques are often used and can be suitable for non-metric applications, but rigorous photogrammetric processing is recommended when having more accurate requirements. The main challenges related to this kind of product are the system calibration and the generation of the final omnidirectional images. When using multi-camera systems, the displacement of the cameras' perspective centres can affect the generation of the omnidirectional images and the resulting accuracy. A common approach to minimising the resulting parallax error is to establish a value for the projection cylinder radius as close as possible to the object's depth. This work proposes a highly accurate simultaneous calibration technique for multiple camera systems using self-calibrating bundle adjustment with constraints of stability of the relative orientation parameters. These parameters are later used to generate a projecting cylindrical surface, maintaining the original camera perspective centres and relative orientation angles. The experiments show that using constraints improved both the calibration results and the final omnidirectional images. Residual mismatches between points in overlapping areas are subpixel.

Spatio-Temporal Analysis of Carbon Storage in Urban Areas After Wildfires: The Case of Marmaris Fire

Cities and urban areas are the primary source of CO2 worldwide by using around 70% of global energy and emitting more than 71% of CO2. Urban vegetation, referring to all trees and shrubs, are important components of urban environments. They provide many ecosystem services to human beings both directly and indirectly. Especially, they play a key role in reducing carbon emissions in urban areas by storing and capturing the carbon. However, recently, an increase in the number and intensity of wildfires that occur within urban areas has been observed. It resulted in losing stored carbon, releasing GHG to the atmosphere. Hence, quantifying above-ground carbon stored by urban trees and its distribution is essential to better understanding urban vegetation's role in urban environments and to better urban vegetation management. This study aimed to examine how forest fire affects the amount and distribution of stored carbon in the urban environment for the case of the Marmaris fire in the Summer of 2021 in Türkiye. For the study, urban forest carbon storage maps were generated before and after the Marmaris forest fire using remote sensing-based methodology with freely available remote sensing (RS) data. The results indicated that using the existing methodology could be rapid and cost-effective in monitoring the carbon storage change after an anthropogenic and natural disaster. However, for precise and reliable estimation of total carbon storage and the change in total urban carbon storage, the methodology needs to be developed at a local scale using field sampling along with RS data.

Improving Urban Mapping Accuracy: Investigating the Role of Data Acquisition Methods and SfM Processing Modes in UAS-Based Survey Through Explainable AI Metrics

In this study, we investigated the accuracy of surface models and orthophoto mosaics generated from images acquired using different data acquisition methods at different processing levels in two urban study areas with different characteristics. Experimental investigations employed single- and double-grid flight directions with nadir and tilted (60°) camera angles, alongside the Perimeter 3D method. Three processing levels (low, medium, and high) were applied using SfM software, resulting in 42 models. Ground truth data from RTK GNSS points and aerial LiDAR surveys were used to assess horizontal and vertical accuracies. For the horizontal accuracy test, neither the oblique camera angle nor the double grid resulted in an improvement in accuracy. In contrast, when examining the vertical accuracy, it was concluded that for several processing levels, the tilted camera angle yielded better results, and in these cases, the double grid also improved accuracy. Feature importance analysis revealed that, among the four variables, the data acquisition method was the most important factor affecting accuracy in two out of three cases.

Urban flood susceptibility mapping using remote sensing, social sensing and an ensemble machine learning model

Flood susceptibility mapping is crucial for urban disaster management. However, the heterogeneity of urban land use and the complexity of terrain pose challenges to the accuracy and generalizability of flood models. In this paper, we propose a framework named the EMF model for urban flood mapping. Specifically, the social sensing and remote sensing were used for flooding information collection. The XGBoost, Support Vector Classifier (SVC), Multilayer Perceptron (MLP), and Multimodal Deep Learning (MDL), were used as the predictive models, and their results were ensembled using a Random Forest model to produce the final outcome. Results show that the EMF model outperforms the standalone models, with an accuracy of 0.942 on the training set and 0.940 on the testing set. The accuracy of the five models is ranked as EMF > MDL > XGBoost > SVC > MLP. The flood map indicates that flooding has a greater impact on the outskirts and suburbs of the city compared to its central urban areas. Farmland is the most affected land type, making up 54.8 % of the flooded area. Overall, the proposed framework enables rapid and accurate identification of flood-prone areas, providing technical support for managers in formulating effective flood prevention strategies.