Search Results (54)

Building clustering is a key challenge in cartographic generalization, where the goal is to group spatially related buildings into semantically coherent clusters while preserving the true distribution patterns of urban structures. Existing methods often rely on either spatial distance or building feature similarity alone, leading to clusters that sacrifice either accuracy or spatial continuity. Moreover, most deep learning-based approaches, including graph attention networks (GATs), fail to explicitly incorporate spatial distance constraints and typically restrict message passing to first-order neighborhoods, limiting their ability to capture long-range structural dependencies. To address these issues, this paper proposes LA-GATs, a multi-feature constrained and spatially adaptive building clustering network. First, a Delaunay triangulation is constructed based on nearest-neighbor distances to represent spatial topology, and a heterogeneous feature matrix is built by integrating architectural spatial features, including compactness, orientation, color, and height. Then, a spatial distance-constrained attention mechanism is designed, where attention weights are adjusted using a distance decay function to enhance local spatial correlation. A second-order neighborhood aggregation strategy is further introduced to extend message propagation and mitigate the impact of triangulation errors. Finally, spectral clustering is performed on the learned similarity matrix. Comprehensive experimental validation on real-world datasets from Xi’an and Beijing, showing that LA-GATs outperforms existing clustering methods in both compactness, silhouette coefficient and adjusted rand index, with up to about 21% improvement in residential clustering accuracy. Full article

One of the sometimes-neglected fields is the landscape design of hospital premises. This study focuses on the perception and preferences of responders regarding hospital site design. The objective was to determine if people are aware of the benefits of restorative contact with nature and if there were preferences for any specific landscape type. The online questionnaire with color figures was distributed using emails and social media from 4 May to 2 August 2024. Some 110 respondents returned the questionnaire. Most of the respondents were women under 25. Most respondents declared that the surroundings of the healthcare building influence the health and well-being of patients (96%) and health personnel (86%). The results confirmed the awareness of the importance of contact with nature (89%). Moreover, this study demonstrated a preference for calm garden compositions, stimulating physical and mental recovery with trees, flowers, and water features, as well as stabilized paths and sheltered sitting places. The results confirm previous studies and demonstrate the importance of landscape architecture design of hospital premises for the well-being of patients. The findings may influence urban landscape planning and the design of hospital sites. Full article

This article presents an analysis of the architectural integration of two new buildings implemented on the Gdańsk University of Technology campus (Poland) as a case study of combining contemporary technologies with cultural continuity. The buildings, designed by the author of the article, who is the main designer, are a conscious response to the historical urban and architectural context of the campus, the development of which started at the beginning of the 20th century in the style of Dutch Neo-Renaissance. The new buildings refer to the architectural heritage of the university through their scale and colors, but their form, details and applied technological solutions clearly reflect modernity. A particularly important element of their modern character is the implementation of advanced pro-ecological systems for obtaining energy from renewable sources (RES), which fits into the current climate challenges and the role of the technical university as a promoter of sustainable development. The article discusses how architecture, materials and modern building systems were used to create a dialogue between tradition and innovation. The analysis is based on design documentation and planning conditions, and its background is a broader discourse on culturally sustainable architecture. Conscious of other, more conservative views, the author puts forward the thesis that cultural continuity does not require stylistic imitation, but conscious, contextual reinterpretation. The results of the article enrich the debate on the development of academic campuses, heritage-responsible design and the role of the architect in shaping a space that connects the future with the past. The main research contribution of the article is the presentation of an original method of designing architectural objects that integrates advanced pro-ecological technologies with a contextual reinterpretation of architectural heritage, which constitutes a new perspective in the discussion on culturally sustainable architecture. Full article

This paper introduces a novel approach to tree modeling architecture integrated with blockchain technology, aimed at enhancing landscape spatial planning and forest monitoring systems. The primary objective is to develop a low-cost, automated tree CAD modeling methodology combined with blockchain functionalities to support smart forest projects and collaborative design processes. The proposed method utilizes a parametric tree CAD model consisting of four 2D tree-frames with a 45° division angle, enriched with recorded tree-leaves’ texture and color. An “AI Text-by-Voice CAD Programming” technique is employed to create tangible tree-model NFT tokens, forming the basis of a thematic “Internet-of-Trees” blockchain. The main results demonstrate the effectiveness of the blockchain/Merkle hash tree in tracking tree geometry growth and texture changes through parametric transactions, enabling decentralized design, data validation, and planning intelligence. Comparative analysis highlights the advantages in cost, time efficiency, and flexibility over traditional 3D modeling techniques, while providing acceptable accuracy for metaverse projects in smart forests and landscape architecture. Core contributions include the integration of AI-based user voice interaction with blockchain and behavioral data for distributed and collaborative tree modeling, the introduction of a scalable and secure “Merkle hash tree” for smart forest monitoring, and the facilitation of fintech adoption in environmental projects. This framework offers significant potential for advancing metaverse-based landscape architecture, smart forest surveillance, sustainable urban planning, and the improvement of citizen involvement in sustainable forestry paving the way for a greener future. Full article

As part of contemporary urban culture, murals support place making and city identity. While much attention has been paid to their role in activating public space during daylight hours, their presence after dark remains largely unexamined. This paper analyzes how mural content interacts with night-time illumination. The research draws on case studies, photographs, luminance measurements, and lighting simulations. It evaluates how existing lighting systems support or undermine the legibility and impact of commercial murals in urban environments. It explores whether standardized architectural lighting guidelines suit murals, how color and surface affect visibility, and which practices improve night-time legibility. The study identifies a gap in existing lighting strategies, noting that uneven lighting distorts intent and reduces public engagement. In response, a new design tool—the Floodlighting Content Readability Map—is proposed to support artists and planners in creating night-visible murals. This paper situates mural illumination within broader debates on creative urbanism and argues that lighting is not just infrastructure, but a cultural and aesthetic tool that extends the reach and resonance of public art in the 24 h city. It further emphasizes the need for interdisciplinary collaboration and a multi-contextual perspective—encompassing visual, social, environmental, and regulatory dimensions—when designing murals in cities. Full article

Single image super-resolution is the inverse problem of reconstructing a high-resolution image from its low-resolution counterpart. Although recent Transformer-based architectures leverage global context integration to improve reconstruction quality, they often overlook frequency-specific characteristics, resulting in the loss of high-frequency information. To address this limitation, we propose the Dual Frequency Adaptive Network (DFAN). DFAN first decomposes the input into low- and high-frequency components via Stationary Wavelet Transform. In the low-frequency branch, Swin Transformer layers restore global structures and color consistency. In contrast, the high-frequency branch features a dedicated module that combines Directional Convolution with Residual Dense Blocks, precisely reinforcing edges and textures. A frequency fusion module then adaptively merges these complementary features using depthwise and pointwise convolutions, achieving a balanced reconstruction. During training, we introduce a frequency-aware multi-term loss alongside the standard pixel-wise loss to explicitly encourage high-frequency preservation. Extensive experiments on the Set5, Set14, BSD100, Urban100, and Manga109 benchmarks show that DFAN achieves up to +0.64 dBpeak signal-to-noise ratio, +0.01 structural similarity index measure, and −0.01learned perceptual image patch similarity over the strongest frequency-domain baselines, while also delivering visibly sharper textures and cleaner edges. By unifying spatial and frequency-domain advantages, DFAN effectively mitigates high-frequency degradation and enhances SISR performance. Full article

Radar echo extrapolation is a critical forecasting tool in the field of meteorology, playing an especially vital role in nowcasting and weather modification operations. In recent years, spatiotemporal sequence prediction models based on deep learning have garnered significant attention and achieved notable progress in radar echo extrapolation. However, most of these extrapolation network architectures are built upon convolutional neural networks, using radar echo images as input. Typically, radar echo intensity values ranging from −5 to 70 dBZ with a resolution of 5 dBZ are converted into 0–255 grayscale images from pseudo-color representations, which inevitably results in the loss of important echo details. Furthermore, as the extrapolation time increases, the smoothing effect inherent to convolution operations leads to increasingly blurred predictions. To address the algorithmic limitations of deep learning-based echo extrapolation models, this study introduces three major improvements: (1) A Deep Convolutional Generative Adversarial Network (DCGAN) is integrated into the ConvLSTM-based extrapolation model to construct a DCGAN-enhanced architecture, significantly improving the quality of radar echo extrapolation; (2) Considering that the evolution of radar echoes is closely related to the surrounding meteorological environment, the study incorporates specific physical variable products from the initial zero-hour field of RMAPS-NOW (the Rapid-update Multiscale Analysis and Prediction System—NOWcasting subsystem), developed by the Institute of Urban Meteorology, China. These variables are encoded jointly with high-resolution (0.5 dB) radar mosaic data to form multiple radar cells as input. A multi-channel radar echo extrapolation network architecture (MR-DCGAN) is then designed based on the DCGAN framework; (3) Since radar echo decay becomes more prominent over longer extrapolation horizons, this study departs from previous approaches that use a single model to extrapolate 120 min. Instead, it customizes time-specific loss functions for spatiotemporal attenuation correction and independently trains 20 separate models to achieve the full 120 min extrapolation. The dataset consists of radar composite reflectivity mosaics over North China within the range of 116.10–117.50°E and 37.77–38.77°N, collected from June to September during 2018–2022. A total of 39,000 data samples were matched with the initial zero-hour fields from RMAPS-NOW, with 80% (31,200 samples) used for training and 20% (7800 samples) for testing. Based on the ConvLSTM and the proposed MR-DCGAN architecture, 20 extrapolation models were trained using four different input encoding strategies. The models were evaluated using the Critical Success Index (CSI), Probability of Detection (POD), and False Alarm Ratio (FAR). Compared to the baseline ConvLSTM-based extrapolation model without physical variables, the models trained with the MR-DCGAN architecture achieved, on average, 18.59%, 8.76%, and 11.28% higher CSI values, 19.46%, 19.21%, and 19.18% higher POD values, and 19.85%, 11.48%, and 9.88% lower FAR values under the 20 dBZ, 30 dBZ, and 35 dBZ reflectivity thresholds, respectively. Among all tested configurations, the model that incorporated three physical variables—relative humidity (rh), u-wind, and v-wind—demonstrated the best overall performance across various thresholds, with CSI and POD values improving by an average of 16.75% and 24.75%, respectively, and FAR reduced by 15.36%. Moreover, the SSIM of the MR-DCGAN models demonstrates a more gradual decline and maintains higher overall values, indicating superior capability in preserving echo structural features. Meanwhile, the comparative experiments demonstrate that the MR-DCGAN (u, v + rh) model outperforms the MR-ConvLSTM (u, v + rh) model in terms of evaluation metrics. In summary, the model trained with the MR-DCGAN architecture effectively enhances the accuracy of radar echo extrapolation. Full article

In addition to architecture and infrastructure, urban outdoor advertising also shapes urban visual identity, serving as a prominent carrier of public information and visual stimuli. However, excessive or poorly designed advertisements disrupt the cityscape and contribute to visual pollution and cognitive overload. Leveraging computer-based eye tracking, this study examines the visual and cognitive effects of outdoor advertising designs within urban contexts. Key eye-tracking metrics, including total fixation duration, fixation count, time to first fixation, and first fixation duration, are measured to analyze the influence of various variables on visual attention and user experience, such as color contrast, text complexity, information hierarchy, and spatial layout. The findings reveal that high-contrast, text-heavy designs hinder visual flow and increase mental effort, while visually balanced layouts improve legibility and reduce cognitive burden. These results offer actionable insights for optimizing urban visual identity and enhancing the clarity, comfort, and coherence of outdoor advertising. By integrating perceptual data into urban design strategies, this research provides a data-driven approach to smarter, more human-centered advertising management and urban aesthetic governance. Full article

High-resolution holographic visualization of built environments remains largely inaccessible due to the complexity and technical demands of traditional 3D data acquisition processes. This study proposes a workflow for producing high-quality full-color digital holographic stereograms of architectural landmarks using Google Earth Studio. By leveraging photogrammetrically reconstructed three-dimensional (3D) city models and a controlled camera path, we generated perspective image sequences of two iconic monuments, that is, the Basílica de la Sagrada Família (Barcelona, Spain) and the Arc de Triomphe (Paris, France). A custom pipeline was implemented to compute keyframe coordinates, extract cinematic image sequences, and convert them into histogram data suitable for CHIMERA holographic printing. The holograms were recorded on Ultimate U04 silver halide plates and illuminated with RGB light-emitting diodes, yielding visually immersive reconstructions with strong parallax effects and color fidelity. This method circumvented the requirement for physical 3D scanning, thereby enabling scalable and cost-effective holography using publicly available 3D datasets. In conclusion, the findings indicate the potential of combining Earth Studio with digital holography for urban visualization, cultural heritage preservation, and educational displays. Full article

Historic and cultural heritage districts, as physical carriers of a city’s cultural identity, have become key issues in urban development. Architectural color, as a core visual element of district character, is an important symbol of regional identity recognition. However, further exploration is needed regarding how to integrate architectural color quantification metrics and evaluation techniques into the urban characteristics management framework. In this paper, taking Tianjin’s historic cultural heritage districts as a case study, street view data were utilized, and deep learning along with clustering analysis methods were employed to extract architectural colors. Based on the “point-line-surface” protection strategy, a multi-scale architectural color identification and evaluation method spanning “buildings-streets-districts” was established. This methodology enables the recognition of dominant building colors in heritage zones at the district scale and the assessment of street color harmony and richness at the street scale. By analyzing these two levels, this research interprets the role of architectural color as a visual attribute in defining urban character and enhancing urban distinctiveness. It provides technical support for refining urban characteristics management systems and achieving precise control over the preservation and development of distinctive urban features. Full article

Detecting fire and smoke is essential for maintaining safety in urban, industrial, and outdoor settings. This study suggests a unique concatenated convolutional neural network (CNN) model that combines deep learning with hybrid preprocessing methods, such as contour-based algorithms and color characteristics analysis, to provide reliable and accurate fire and smoke detection. A benchmark dataset with a variety of situations, including dynamic surroundings and changing illumination, the D-Fire dataset was used to assess the technique. Experiments show that the suggested model outperforms both conventional techniques and the most advanced YOLO-based methods, achieving accuracy (0.989) and recall (0.983). In order to reduce false positives and false negatives, the hybrid architecture uses preprocessing to enhance Regions of Interest (ROIs). Additionally, pooling and fully linked layers provide computational efficiency and generalization. In contrast to current approaches, which frequently concentrate only on fire detection, the model’s dual smoke and fire detection capabilities increase its adaptability. Although preprocessing adds a little computing expense, the methodology’s excellent accuracy and resilience make it a dependable option for safety-critical real-world applications. This study sets a new standard for smoke and fire detection and provides a route forward for future developments in this crucial area. Full article

Architectural images, experienced visually and spatially, embody urban culture, aesthetics, and identity, yet their suitability in urban communities remains underexplored. This study addresses this gap by evaluating the suitability of architectural images using the niche-fitness model, combined with residents’ perception assessments. Evaluation indicators focus on architectural form, color, features, and values to assess how well buildings align with residents and environmental contexts. The findings reveal significant variations in suitability across six studied buildings in a high-density community in Wuhan. One building showed high ecological adaptability and alignment with residents’ functional and aesthetic preferences, while others exhibited moderate to low suitability, reflecting mismatches with residents’ perceptions. The inharmonious adaptability of these buildings demonstrates the need to harmonize architectural images with residents’ psychological preferences to enhance community livability and identity. Combining Wuhan’s regional characteristics, suggestions for improving the governance of architectural images are proposed to address mismatches. This study analyzes the role of architectural image suitability in improving residents’ quality of life and shaping urban community characteristics. By offering a practical approach for guiding the renewal of architectural images in communities, this research contributes to creating livable and culturally resonant environments to support sustainable urban development. Full article

Automatic building change detection is essential for updating geospatial data, urban planning, and land use management. The objective of this study is to propose a transformer-based UNet-like framework for end-to-end building change detection, integrating multi-temporal and multi-source data to improve efficiency and accuracy. Unlike conventional methods that focus on either spectral imagery or digital surface models (DSMs), the proposed method combines RGB color imagery, DSMs, and building vector maps in a three-branch Siamese architecture to enhance spatial, spectral, and elevation-based feature extraction. We chose Hsinchu, Taiwan as the experimental site and used 1:1000 digital topographic maps and airborne imagery from 2017, 2020, and 2023. The experimental results demonstrated that the data fusion model significantly outperforms other data combinations, achieving higher accuracy and robustness in detecting building changes. The RGB images provide spectral and texture details, DSMs offer structural and elevation context, and the building vector map enhances semantic consistency. This research advances building change detection by introducing a fully transformer-based model for end-to-end change detection, incorporating diverse geospatial data sources, and improving accuracy over traditional CNN-based methods. The proposed framework offers a scalable and automated solution for modern mapping workflows, contributing to more efficient geospatial data updating and urban monitoring. Full article

From the color geography perspective, a field investigation was conducted in the Minjiang River Basin, constructing a color index system of traditional villages. In Python, a random forest model was constructed to screen out important color indexes for traditional village color classification and explore its influence mechanism. Among eight color indexes, the important indexes are wall form and building face form, accounting for 30.50% and 19.40%, respectively. Based on this, the basin was divided into four color zones presenting color characteristics and eight color subzones presenting architectural features. The influence mechanism concerns dialect divisions that have shaped traditional villages of different color types, and the interconnection of water systems has promoted the connections among them. The application of traditional village colors in the new urban and rural planning can enhance local characteristics. Integrating the color resources of traditional villages contributes to the regional protection of culture and economic development. Full article

Globalization has profoundly impacted architecture by promoting urban homogenization, where global styles and materials overshadow local character. This shift prioritizes standardized functionality and energy efficiency over cultural identity, erasing regional architectural distinctiveness. In historical urban centers, globalization-driven interventions—such as ventilated facades or external thermal insulation systems (ETISs)—often simplify original compositions and alter building materiality, texture, and color. The Ensanche of San Sebastián serves as a case study highlighting this issue. Despite its architectural richness, which includes neoclassical and modernist buildings primarily constructed with sandstone from the Igeldo quarry, unprotected buildings are at risk of unsympathetic renovations. Such changes can distort the identity of what is considered “everyday heritage”, encompassing the residential buildings and public spaces that shape the collective memory of cities. This study presents a replicable methodology for assessing the vulnerability of buildings to facade interventions. By utilizing tools like digital twins, point cloud modeling, and typological analysis, the research establishes criteria for interventions aimed at preserving architectural values. It emphasizes the importance of collaborative efforts with urban planning authorities and public awareness campaigns to safeguard heritage. Ultimately, protecting architectural identity requires balancing the goals of energy efficiency with cultural preservation. This approach ensures that urban landscapes maintain their historical and social significance amidst globalization pressures. Full article