Complex Urban Environments Research Articles

Building Change Detection Network Based on Multilevel Geometric Representation Optimization Using Frame Fields

To address the challenges of accurately segmenting irregular building boundaries in complex urban environments faced by existing remote sensing change detection methods, this paper proposes a building change detection network based on multilevel geometric representation optimization using frame fields called BuildingCDNet. The proposed method employs a multi-scale feature aggregation encoder–decoder architecture, leveraging contextual information to capture the characteristics of buildings of varying sizes in the imagery. Cross-attention mechanisms are incorporated to enhance the feature correlations between the change pairs. Additionally, the frame field is introduced into the network to model the complex geometric structure of the building target. By learning the local orientation information of the building structure, the frame field can effectively capture the geometric features of complex building features. During the training process, a multi-task learning strategy is used to align the predicted frame field with the real building outline, while learning the overall segmentation, edge outline, and corner point features of the building. This improves the accuracy of the building polygon representation. Furthermore, a discriminative loss function is constructed through multi-task learning to optimize the polygonal structured information of the building targets. The proposed method achieves state-of-the-art results on two commonly used datasets.

Mexico city’s decline in per capita domestic water use: a comprehensive spatial-temporal study

ABSTRACT Facing the growing challenges in water supply in urban areas, characterized by high demand and water scarcity, Mexico City, with its high population density and limited water resources, exemplifies the challenges in ensuring equitable management and water supply in complex urban environments. This study combines GIS tools, statistical analysis and spatial regression to analyze the spatiotemporal changes in per capita water consumption in Mexico City households between 2010 and 2019. The results show a 40% decrease in average consumption and a spatial reconfiguration that reflects an increase in inequalities in access to drinking water. The influence of five key factors in the reconfiguration is identified: intermittent supply, economic income, water feasibility, households without piped water, and an increase in dwellings. The findings are essential for developing equitable and effective water policies, emphasizing the need to address inequalities in water access in urban planning to achieve the Sustainable Development Goals.

Bridging Perceptual Gaps: Designers vs. Non-Designers in Urban Wayfinding Signage Preferences

As urban environments become increasingly complex and the costs and challenges of infrastructure upgrades continue to rise, wayfinding signage has become an effective solution to cope with urban dynamics due to its low cost and high flexibility. Although the functionality of wayfinding signage has been extensively studied, the perceptual differences between designers and non-designers have not been adequately explored. Ignoring these differences may lead to the overlooking of users’ real and diverse needs, resulting in suboptimal signage performance in practical applications and ultimately a reduction in the overall functionality and user experience of urban spaces. This study aims to bridge this perceptual gap. For this study, we conducted a questionnaire survey in China to compare the visual preferences of designers and non-designers regarding text, shape, color coding, and patterns. The results indicate that designers prioritize functionality and clarity to ensure the effective use of signage in complex urban environments, whereas non-designers prefer wayfinding signages that reflect local cultural symbols and characteristics. Our conclusions suggest that the public’s expectations for wayfinding signage extend beyond basic navigational functions, with an emphasis on cultural expression and visual appeal. Understanding these perceptual differences is crucial in developing design strategies that balance functionality, esthetics, and sustainability, thereby facilitating the sustainable integration of signage into urban landscapes.

Multi-class Object Detection in Urban Scenes Based on Deep Learning

Abstract. The rapid development of urbanization presents challenges and requirements for multi-class object detection in urban scenes. Accurately identifying buildings, vehicles, and trees in urban scenes can optimize urban planning, traffic management, monitoring environmental conditions, and promote the development of smart cities. Traditional target detection methods perform poorly in complex urban environments, while deep learning technology achieves accurate target recognition and positioning by automatically extracting high-level semantic features. In this study, we chose to use the YOLOv5s algorithm for multi-class target detection in urban scenes. YOLOv5s is a lightweight deep learning model with small storage space and efficient detection speed. In this paper, the Potsdam area data published by ISPRS is used to make the label data of buildings, vehicles and trees. The YOLOv5s algorithm is used to iteratively train the model. The results show that the mAP value detected by the YOLOv5s model can reach 82.83%. The experimental results show that the algorithm shows higher accuracy than SSD and Faster R-CNN in tree detection. Although it has a slight decline in building and vehicle detection, considering the factors such as detection accuracy, speed, and model size, the YOLOv5s algorithm has a better recognition and detection effect for the detection of multi-class targets in urban scenes.

Differential Analysis of Emergency Vehicle Detection in Urban Traffic : A Systematic Review

The differential analysis of emergency vehicle detection in urban traffic is crucial for improving response times and reducing traffic-related delays during emergencies. This systematic review aims to analyze various methods and technologies, such as acoustic, visual, and sensor-based systems, used for detecting emergency vehicles in complex urban environments. The motivation behind this study is the growing need for more efficient traffic management systems that prioritize emergency vehicles, minimizing delays caused by congestion. However, limitations include the inconsistent performance of detection systems in varying weather, lighting, and noise conditions, as well as integration challenges with existing infrastructure. The objective is to evaluate current detection methods, identify their limitations, and propose potential improvements to enhance the accuracy and reliability of emergency vehicle detection in urban traffic systems.

Delivery optimization for collaborative truck–drone routing problem considering vehicle obstacle avoidance

Drone participating in logistics delivery has gained much concern due to its potential superiority of operational efficiency and service costs. How to optimize the hybrid vehicle delivery trip is still a crucial issue. Besides, complex urban environment and regulatory no-through zones bring more rigorous challenges. The aim is to develop an efficient routing solution that considers obstacles encountered by the truck and drone, ensuring the timely delivery. This paper proposes an efficient deep reinforcement learning to optimize the collaborative truck–drone routing problem (C-TDRP) under vehicle obstacle avoidance trail. Specifically, the trucks deploy a fleet of drones to serve the random distributed consumers subject to minimum delivery cost. Homogeneous drones serve multiple demand nodes per trip with limited energy carrying capacity. We design the C-TDRP formulation with studying the feasibility of obstacle avoidance routing. Owing to the computational complexity of the proposed mathematical model, an intelligent optimization algorithm based on deep reinforcement learning is developed, named pointer network (Ptr-Net), which can capture the position weights associated with network sequence automatically. Through rigorous experimental validations, the results demonstrate that the vehicle energy consumption of final trajectory reduces by more than 42%, even for large-scale delivery scenarios. Our proposed method not only enhances the optimization performance but also lays the foundation for more intelligent and adaptable logistics delivery in complex urban environments.

An Improved Velocity-Aided Method for Smartphone Single-Frequency Code Positioning in Real-World Driving Scenarios

The availability of Global Navigation Satellite System (GNSS) raw observations in smartphones has driven research into low-cost GNSS solutions, especially in challenging urban environments, which have garnered significant attention from scholars in recent years. This study proposes an improved smartphone-based velocity-aided positioning method and conducts vehicle-mounted experiments in urban roads representing typical scenarios. The results show that when transitioning from low- to high-multipath environments, the number of visible satellites and carrier phase observations are highly sensitive to environmental factors, with frequent multipath effects. The introduction of robust pre-fit and post-fit residual algorithms has proven to be an effective quality control method. Additionally, using more refined observation models and appropriate parameter estimation algorithms led to a slight 6% improvement in velocity performance. The improved Kalman filter position estimation model (KFSPP-P) strategy, by incorporating velocity uncertainty into the state estimation process, overcomes the limitations of conventional velocity-aided smartphone positioning methods (KFSPP-V) in complex urban environments. In low-multipath environments, the accuracy of the KFSPP-P strategy is comparable to that of KFSPP-V, with an approximate 8% improvement in horizontal accuracy. However, in more challenging environments, such as tree-lined roads and urban environments, the KFSPP-P strategy shows significant improvements, particularly enhancing horizontal positioning accuracy by approximately 50%. These advancements demonstrate the potential of using smartphones to provide reliable positioning services in complex urban environments.

City Logistics Solutions for CO2 Emission Reduction and Energy Efficiency: A Comparative Study of Vitoria-Gasteiz, Tartu, and Sønderborg

Modern cities face the challenge of reconciling dynamic development with environmental protection, as well as ensuring a high quality of life for their residents. In a time of continuous urbanization, with more than half of the world’s population living in cities, city logistics plays a crucial role in managing complex urban environments. As part of the concept of sustainable development, city logistics aims to minimize the negative impact of transport on the environment, while increasing operational efficiency and improving the comfort of life of residents in urban agglomerations. This article presents the results of a comparative analysis of the intensity of sustainable urban logistics development in selected cities of the European Union. It examines various strategies that reduce CO2 emissions, improve air quality, and increase building energy efficiency. The analysis demonstrates that cities investing in sustainable urban logistics not only improve their environmental performance but also increase their attractiveness and competitiveness as desirable places to live and work.

Low-cost urban heat environment sensing device with Android platform for digital twin

The proper monitoring of heat and meteorological variables is essential for the well-being of residents of metropolitan areas. It is challenging to configure spatial heat variations in complex urban environments, even though the temporal variation of urban heat flux has been measured at several designated monitoring stations. Neither the budget nor existing techniques for efficient urban heat monitoring are sufficient for a digital twin of the urban heat environment. As a result, we have developed a low-cost monitoring system that can be easily integrated into a portable pedestrian device, kickboard, or electric bike. With this system, citizens can collect information about urban heat, such as air temperature, surface temperature, relative humidity, barometric pressure, light intensity, and micro-geophysical features including topological aspects and mobile information (e.g., three-dimensional accelerations). Citizens can participate in daily scientific activities using these devices, which facilitate data acquisition and information exchange in urban digital twin environments.

‘Grand designs?’ Investigating the cultural and spatial logics of Channel 4’s media hub workspaces in Leeds, Bristol and Glasgow

This article explores the evolving spatiality of media production through an analysis of recent developments in UK broadcaster Channel 4’s move to a multi-site operating model. Historically, media buildings have served as landmarks of power and influence, embodying the aspirations and identities of media organisations and, as such, offer a fruitful lens for the specific exploration of the spaces of contemporary media production. Through a detailed analysis of Channel 4’s decision-making process, site selections and the significance of the chosen buildings within areas with an urban regeneration focus, the study investigates the complex interplay between media industry dynamics, regional development policies, and wider political and economic forces. Drawing on a range of academic literature and evidence from media, industry and policy reporting, the article highlights the strategic motivations behind Channel 4’s decentralisation efforts, positioned by the organisation as an effort to address diversity in terms of nations and regions representation but significantly shaped by political factors. However, it also raises critical questions about the long-term sustainability, economic viability and cultural impact of these relocation decisions. The article discusses how Channel 4’s regional media spaces and decentralisation reflect the impermanence and crisis facing Public Service Media, emphasising the shifting power dynamics within the media landscape and the need for adaptive strategies in an increasingly volatile industry environment. By examining the evolving investment in media buildings, this research contributes to a growing body of research seeking to understand the complex dynamics shaping contemporary media landscapes and urban environments.

Sky-GVIO: Enhanced GNSS/INS/Vision Navigation with FCN-Based Sky Segmentation in Urban Canyon

Accurate, continuous, and reliable positioning is critical to achieving autonomous driving. However, in complex urban canyon environments, the vulnerability of stand-alone sensors and non-line-of-sight (NLOS) caused by high buildings, trees, and elevated structures seriously affect positioning results. To address these challenges, a sky-view image segmentation algorithm based on a fully convolutional network (FCN) is proposed for NLOS detection in global navigation satellite systems (GNSSs). Building upon this, a novel NLOS detection and mitigation algorithm (named S−NDM) uses a tightly coupled GNSS, inertial measurement units (IMUs), and a visual feature system called Sky−GVIO with the aim of achieving continuous and accurate positioning in urban canyon environments. Furthermore, the system combines single-point positioning (SPP) with real-time kinematic (RTK) methodologies to bolster its operational versatility and resilience. In urban canyon environments, the positioning performance of the S−NDM algorithm proposed in this paper is evaluated under different tightly coupled SPP−related and RTK−related models. The results exhibit that the Sky−GVIO system achieves meter-level accuracy under the SPP mode and sub-decimeter precision with RTK positioning, surpassing the performance of GNSS/INS/Vision frameworks devoid of S−NDM. Additionally, the sky-view image dataset, inclusive of training and evaluation subsets, has been made publicly accessible for scholarly exploration.

Road traffic noise assessment method for Hong Kong and associated GIS-based assessment tools

Hong Kong, known for its compact and complex urban environment, has long faced unique challenges in modeling road traffic noise for planning and assessment purposes. The Environmental Protection Department (EPD) of the Hong Kong Special Administrative Region Government (HKSARG) identified and established an enhanced prediction methodology called Road Traffic Noise Assessment Method - Hong Kong (RONOSS-HK). RONOSS-HK aims to provide better treatment on source geometry, source terms, noise propagation, considerations for new-energy vehicles and special noise reduction of the Innovative Noise Mitigation Designs (INMD) to cater for the complicated spatial noise situations in Hong Kong. To facilitate the implementation of RONOSS-HK, the EPD has also developed and introduced a GIS-based assessment tool which allows users to utilize GIS data readily available in HKSARG databases and other spatial information in the public domain for accurate road traffic noise prediction using RONOSS-HK methodology. Additionally, the EPD is in the process of further developing a web-based 3D software to serve as an alternative comprehensive assessment tool for applying RONOSS-HK in noise assessment. This paper introduces RONOSS-HK prediction methodology and the latest development of its associated GIS-based assessment tools.

The LIFE SILENT project's approach to sustainable noise mitigation

The main objective of the LIFE SILENT PROJECT is the development of sustainable and eco-friendly solutions to mitigate noise in complex urban environments, where multiple and diverse noise sources, mainly roads and railways, coexist across densely populated areas. Mitigating noise in such environments generally excludes the use of solutions that might interfere with the urban context, such as noise barriers. This is mainly due to the proximity of receivers to the noise source, which reduces the visibility of the surroundings and air circulation, leading to microclimatic modifications and social opposition. This is why noise mitigation measures acting directly on the source are recommended, such as low-noise pavements for roads, and dampers, rail grinding, and silent brakes for railways. However, these solutions suffer from either durability issues or high implementation costs. Thus, an improvement is necessary. In the LIFE SILENT project, innovative and sustainable low-noise and long-lasting pavements, as well as low-height noise barriers will be developed and demonstrated in a real test environment. Additionally, procedures will be established to facilitate their synergistic implementation, providing transport infrastructure owners and managers with solid information to support their widespread adoption. In this paper, a general overview of the LIFE SILENT project is given.

An experimental setup to investigate relevant validation parameters for the auralization of commercial aircraft flyovers in complex urban contexts

Auralization has a key role in the design of immersive virtual reality tools for the study of human environments and their evolution. In soundscape and multisensory research, the validation of auralization frameworks traditionally relies on the impressions engendered by the virtual acoustic environment on the human subjects, and whether those impressions match real-world experiences. It uses subjective surveys related to the perceptual and affective spheres of individuals. This may lead to unclear validation. In this paper, we present an experimental setup to search for a set of relevant validation parameters for the auralization of complex urban environments involving commercial aircraft flyovers. Our investigation is tailored to the study of working and learning activities in offices or universities neighboring the flight paths. The experimental setup focuses on the quantitative evaluation of cognitive performance instead of the classic perceptual or affective personal survey-based approach. In the experiment, subjects undergo distinct acoustic environments, synthesized from real-world binaural recordings. Simultaneously, subjects perform memory, fluency, or puzzle-like tasks. Different cognitive performance parameters are measured throughout the experiment. The parameters most strongly correlated to the environments' acoustic events and properties are considered meaningful validation parameters.

A WRF-UCM-SOLWEIG framework for mapping thermal comfort and quantifying urban climate drivers: Advancing spatial and temporal resolutions at city scale

The capability to evaluate city-scale outdoor thermal comfort is crucial for understanding the public's experience of heat stress, especially during heat waves. Nevertheless, there remains a methodological gap in accurately mapping thermal comfort with high spatial and temporal resolutions in complex urban environment and in quantifying the contributions of various urban climate drivers, such as sky view factors and tree canopy fraction. To bridge this gap, we propose an innovative WRF-UCM-SOLWEIG framework that couples a mesoscale model with an urban microclimate model. Specifically, it integrates the Weather Research and Forecasting model coupled with the urban canopy model (WRF-UCM) and the Solar and Longwave Environmental Irradiance Geometry model (SOLWEIG). This framework is then applied to a densely populated tropical city in China, to quantify the impact of urban climate drivers on the Universal Thermal Climate Index (UTCI). The results reveal a significant diurnal variation in the impact of urban morphology. Notably, the most significant drivers affecting daytime UTCI are the impervious surface fraction and the tree canopy fraction, with maximum Pearson's correlation coefficients of 0.80 and -0.70, respectively. These findings suggest that urban heat mitigation strategies should prioritize on reducing impervious surfaces and enhancing shade management, alongside expanding urban forestry measures.

On the Assessment of Wind Microclimate in a Complex Urban Environment Utilising Computational Fluid Dynamics

This paper presents an insight and key considerations for using Computation Fluid Dynamics (CFD) to simulate the Wind Microclimate in a Complex Urban Environment. The current study involved developing a local 10m height “reference” wind rose for the project site and then combining statistical meteorological data with aerodynamic information and wind comfort and wind safety criteria. Where wind speeds were found to be at undesirable wind levels at areas of interest (ground level, podium level, terraces, balconies, etc.), recommendations were made to reduce detrimental wind effects, e.g. using landscaping, porous windbreaks, canopies, etc. The criteria used in the evaluation of pedestrian-level winds surrounding the proposed development were based on the well-established “Lawson” criteria which couple the probability of exceeding winds at given statistical levels with wind speed magnitudes originally related to the Beaufort Land Scale. To take into account the influence of the immediate surrounding environment, all neighboring buildings and local topography within a diameter of almost 1,000 m around the site were included in the developed CFD model. Furthermore, all small canopies, balconies, and semi-open spaces were modeled in detail as per the provided architectural drawings. Based on a mesh sensitivity assessment, polyhedral elements were used for the entire computational domain. CFD analysis offers a comprehensive range of output including the velocity distribution in three directions and turbulence levels, allowing the identification of hot spot areas that have potentially unacceptable wind conditions for further assessment and mitigation treatments to reduce wind speed to acceptable levels. The baseline (no mitigation) scenario simulation results contributed to a better understanding of the environmental wind impact for the project at the site, enabling a targeted approach to the development of effective windbreak options This paper provides a comprehensive approach toward the establishment of a robust CFD assessment of human comfort to ensure that proposed building developments and their streetscapes create a comfortable wind environment to live and visit.

Moderate Red-Edge vegetation index for High-Resolution multispectral remote sensing images in urban areas

Urban green space (UGS) monitoring is significant in optimizing urban planning, protecting the ecological environment, and improving residents’ quality of life. However, in urban environments, shadow interference and the emergence of new construction materials pose challenges to monitoring green vegetation in high-resolution imagery. This study found that existing vegetation indices (VIs), such as normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI), perform inadequately in extracting vegetation in urban areas, resulting in significant omissions and errors. By conducting in-depth analysis and quantitative experiments on the reflectance of typical urban ground objects, this study developed a new vegetation extraction method, the moderate red-edge vegetation index (MREVI), to enhance the extraction accuracy of UGS vegetation from unmanned aerial vehicle (UAV) high-resolution multispectral remote sensing (RS) images. Experimental results demonstrate that MREVI performs exceptionally well in complex urban environments, significantly suppressing non-vegetation areas, achieving an overall accuracy (OA) of 98.6% and a Kappa coefficient of 0.97. This study supports for urban planning, UGS monitoring, and the evaluation of urban plant carbon sequestration capacity.

Evaluating urban biodiversity: Effectiveness of citizen science driven species distribution models in urban ecosystems

Citizen science (CS) and remote sensing (RS) approaches have become more reliable, thus providing higher resolution and generating a large amount of environmental data. When considering urban environments, where fragmented and highly diverse landscapes are predominant, the combination of citizen science data and remote sensing techniques with species distribution models (SDM) can play a vital role in comprehensively investigating and evaluating urban biodiversity. However, citizen science derived species distribution models for multiple avian species in dense and fragmented urban areas are rarely used. The study aims (I) to elaborate, whether CS driven SDMs can be effectively used in spatially complex urban environments; (II) to identify biodiversity hotspots and prioritize areas for nature conservation and (III) to examine, if existing protective areas correspond to species’ hotspots. Therefore, Citizen science-based datasets of 26 breeding bird species over three years were obtained for this analysis in Germany’s Ruhr Metropolis. Quality assurance, data thinning, and pseudo-absence simulations were performed. Spatial data from the ecosystem LiDAR project GEDI (Global Ecosystem Dynamics Investigation), climate data from the German Weather Service, and land use information from Copernicus were used as environmental predictors. Eleven different species distri-bution models (SDMs) were trained on species subselection by using Biomod2 for preliminary analysis. Overall model performance was evaluated via several metrics, including TSS (true skill statistics) and ROC (receiver operating characteristic). Finally, four species distribution models were used for ensemble modelling. Subsequently, a species richness analysis was performed with the aim of identifying spots with high avian biodiversity. Overall, the CS-derived SDMs performed well, with high predictive power for all of the investigated species. Within the Ruhr Metropolis, approximately 6% (250 km²) of the terrain was identified as being highly suitable for avian diversity, inhabiting at least 17 out of 26 species. Predominantly within the core urban areas, high species richness was predicted on preserved brownfields and revitalized mine sites, as well as in the remnants of formerly demarcated regional greenbelts. Additionally, regions outside of the core area, which are part of the overarching biotope network framework, proved to have high species richness capabilities for avian biodiversity. These findings aid in optimizing urban development concepts and (sub)urban green space management with respect to urban biodiversity conservation. Following the implications of the recently established Regional Biodiversity Strategy in the Ruhr Metropolis, this analysis demonstrates the importance of networked green spaces, their preservation and the need to close existing network gaps within the Ruhr Metropolis.

Development of an Intelligent Drone Management System for Integration into Smart City Transportation Networks

Drones have experienced rapid technological advancements, leading to the proliferation of small, low-cost, remotely controlled, and autonomous aerial vehicles with diverse applications, from package delivery to personal transportation. However, integrating these drones into the existing air traffic management (ATM) system poses significant challenges. The current ATM infrastructure, designed primarily for traditionally manned aircraft, requires enhanced capacity, workforce, and cost-effectiveness to coordinate the large number of drones expected to operate at low altitudes in complex urban environments. Therefore, this study aims to develop an intelligent, highly automated drone management system for integration into smart city transportation networks. The key objectives include the following: (i) developing a conceptual framework for an intelligent total transportation management system tailored for future smart cities, focusing on incorporating drone operations; (ii) designing an advanced air traffic management and flight control system capable of managing individual drones and drone swarms in complex urban environments; (iii) improving drone management methods by leveraging drone-following models and emerging technologies such as the Internet of Things (IoT) and the Internet of Drones (IoD); and (iv) investigating the landing processes and protocols for unmanned aerial vehicles (UAVs) to enable safe and efficient operations.

Combined BDS/5G seamless positioning scheme based on joint switching strategy of satellite elevation angle and CNR in complex urban environments

Abstract Satellite-based positioning has gained popularity, but in bustling urban areas, signals face challenges like serious attenuation, affecting the reliability of positioning. To overcome this, we propose a seamless positioning approach that combines the BeiDou navigation satellite system (BDS) and 5G, specifically designed for complex urban settings. Initially, we establish static and dynamic positioning solutions using real 5G data measured through the time difference of arrival method, resulting in accurate 5G indoor positioning. Following this, we develop a combined BDS/5G positioning model incorporating joint switching based on satellite elevation angle and carrier-to-noise ratio (CNR). We conduct positioning experiments in intricate environments to validate the effectiveness of our model. The experimental outcomes demonstrate that our combined BDS/5G seamless positioning model, employing the joint switching strategy of satellite elevation angle and CNR, achieves impressive positioning accuracies ranging from decimeters to meters. This approach markedly enhances accuracy and reliability of seamless positioning in challenging urban scenarios.