Search Results (270)

Building height information plays an important role in many urban-related applications, such as urban planning, disaster management, and environmental studies. With the rapid development of real scene maps, street view images are becoming a new data source for building height estimation, considering their easy collection and low cost. However, existing studies on building height estimation primarily utilize remote sensing images, with little exploration of height estimation from street-view images. In this study, we proposed a deep learning-based method for estimating the height of a single building in Baidu panoramic street view imagery. Firstly, the Segment Anything Model was used to extract the region of interest image and location features of individual buildings from the panorama. Subsequently, a cross-view matching algorithm was proposed by combining Baidu panorama and building footprint data with height information to generate building height samples. Finally, a Two-Branch feature fusion model (TBFF) was constructed to combine building location features and visual features, enabling accurate height estimation for individual buildings. The experimental results showed that the TBFF model had the best performance, with an RMSE of 5.69 m, MAE of 3.97 m, and MAPE of 0.11. Compared with two state-of-the-art methods, the TBFF model exhibited robustness and higher accuracy. The Random Forest model had an RMSE of 11.83 m, MAE of 4.76 m, and MAPE of 0.32, and the Pano2Geo model had an RMSE of 10.51 m, MAE of 6.52 m, and MAPE of 0.22. The ablation analysis demonstrated that fusing building location and visual features can improve the accuracy of height estimation by 14.98% to 69.99%. Moreover, the accuracy of the proposed method meets the LOD1 level 3D modeling requirements defined by the OGC (height error ≤ 5 m), which can provide data support for urban research. Full article

Background/Objectives: Aging is often accompanied by physical and cognitive decline, affecting older adults’ mobility. Virtual reality (VR) offers innovative opportunities to safely practice everyday tasks, such as street crossing. This study was designed as a feasibility and pilot study to explore acceptance, usability, and preliminary effects of a VR-based road-crossing intervention for older adults. It investigates the use of virtual reality (VR) as an innovative training tool to support senior citizens in safely navigating everyday challenges such as crossing roads. By providing an immersive environment with realistic traffic scenarios, VR enables participants to practice in a safe and controlled setting, minimizing the risks associated with real-world road traffic. Methods: A VR training application called “Wegfest” was developed to facilitate targeted road-crossing practice. The application simulates various scenarios commonly encountered by older adults, such as crossing busy streets or waiting at traffic lights. The study applied a single-group pre-post design. Outcomes included the Timed Up and Go test (TUG), Falls Efficacy Scale-International (FES-I), and Montreal Cognitive Assessment (MoCA). Results: The development process of “Wegfest” demonstrates how a highly realistic street environment can be created for VR-based road-crossing training. Significant improvements were found in the Timed Up and Go test (p = 0.002, d = 0.784) and fall-related self-efficacy (FES-I, p = 0.005). No change was observed in cognitive function (MoCA, p = 0.56). Participants reported increased subjective safety (p < 0.001). Discussion: The development of the VR training application “Wegfest” highlights the feasibility of creating realistic virtual environments for skill development. By leveraging immersive technology, both physical and cognitive skills required for road-crossing can be effectively trained. The findings suggest that “Wegfest” has the potential to enhance the mobility and safety of older adults in road traffic through immersive experiences and targeted training interventions. Conclusions: As an innovative training tool, the VR application not only provides an engaging and enjoyable learning environment but also fosters self-confidence and independence among older adults in traffic settings. Regular training within the virtual world enables senior citizens to continuously refine their skills, ultimately improving their quality of life. Full article

In remote sensing building detection tasks, data acquisition remains a critical bottleneck that limits both model performance and large-scale deployment. Due to the high cost of manual annotation, limited geographic coverage, and constraints of image acquisition conditions, obtaining large-scale, high-quality labeled datasets remains a significant challenge. To address this issue, this study proposes an automatic semantic labeling framework for remote sensing imagery. The framework leverages geospatial vector data provided by OpenStreetMap, precisely aligns it with high-resolution satellite imagery from Bing Maps through projection transformation, and incorporates a quality-aware sample filtering strategy to automatically generate accurate annotations for building detection. The resulting dataset comprises 36,647 samples, covering buildings in both urban and suburban areas across multiple cities. To evaluate its effectiveness, we selected three publicly available datasets—WHU, INRIA, and DZU—and conducted three types of experiments using the following four representative object detection models: SSD, Faster R-CNN, DETR, and YOLOv11s. The experiments include benchmark performance evaluation, input perturbation robustness testing, and cross-dataset generalization analysis. Results show that our dataset achieved a mAP at 0.5 intersection over union of up to 93.2%, with a precision of 89.4% and a recall of 90.6%, outperforming the open-source benchmarks across all four models. Furthermore, when simulating real-world noise in satellite image acquisition—such as motion blur and brightness variation—our dataset maintained a mean average precision of 90.4% under the most severe perturbation, indicating strong robustness. In addition, it demonstrated superior cross-dataset stability compared to the benchmarks. Finally, comparative experiments conducted on public test areas further validated the effectiveness and reliability of the proposed annotation framework. Full article

Objectives: The aim of this systematic review is to analyze the research journals, sample characteristics and research methodology used in the studies about school neighborhood built environment (SNBE) and the physical health of children and adolescents. Methods: Using 124 key terms across four databases (Web of Science, PubMed, Sportdiscus and Transportation Research Board), 8837 studies were identified, and 55 were selected. The research question and evidence search were guided by the “Population, Intervention, Comparison, Outcomes” (PICO) framework. Results: Most studies were published in health-related research journals (67.3%) and conducted in 16 countries, primarily urban contexts (44.4%). Cross-sectional designs dominated (89.1%), with participation ranging from a minimum of 7 schools and 94 students to a maximum of 6362 schools and 979,119 students. Street network distances are often defined by 1000 or 800 m. The SNBE variables (135 total) were often measured via GIS (67.2%). In contrast, 70.6% of the 45 physical health measures relied on self-reports. Conclusions: This systematic review highlights the diverse approaches, gaps, and common patterns in studying the association between the SNBE and the physical health of children and adolescents. Therefore, this manuscript may serve as a valuable resource to examine the current landscape of knowledge and to guide future research on this topic. Full article

Despite the pivotal role of unmanned aerial vehicles (UAVs) in intelligent inspection tasks, existing video instance segmentation methods struggle with irregular deforming targets, leading to inconsistent segmentation results due to ineffective feature offset capture and temporal correlation modeling. To address this issue, we propose a hierarchical offset compensation and temporal memory update method for video instance segmentation (HT-VIS) with a high generalization ability. Firstly, a hierarchical offset compensation (HOC) module in the form of a sequential and parallel connection is designed to perform deformable offset for the same flexible target across frames, which benefits from compensating for spatial motion features at the time sequence. Next, the temporal memory update (TMU) module is developed by employing convolutional long-short-term memory (ConvLSTM) between the current and adjacent frames to establish the temporal dynamic context correlation and update the current frame feature effectively. Finally, extensive experimental results demonstrate the superiority of the proposed HDNet method when applied to the public YouTubeVIS-2019 dataset and a self-built UAV-Seg segmentation dataset. On four typical datasets (i.e., Zoo, Street, Vehicle, and Sport) extracted from YoutubeVIS-2019 according to category characteristics, the proposed HT-VIS outperforms the state-of-the-art CNN-based VIS methods CrossVIS by 3.9%, 2.0%, 0.3%, and 3.8% in average segmentation accuracy, respectively. On the self-built UAV-VIS dataset, our HT-VIS with PHOC surpasses the baseline SipMask by 2.1% and achieves the highest average segmentation accuracy of 37.4% in the CNN-based methods, demonstrating the effectiveness and robustness of our proposed framework. Full article

This study presents a systematic bibliometric review of wearable technologies aimed at vulnerable road user (VRU) safety, covering publications from 2000 to 2025. Guided by PRISMA procedures and a PICo-based search strategy, 58 records were extracted and analyzed in CiteSpace, yielding visualizations of collaboration networks, publication trajectories, and intellectual structures. The results indicate a clear evolution from single-purpose, stand-alone devices to integrated ecosystem solutions that address the needs of diverse VRU groups. Six dominant knowledge clusters emerged—street-crossing assistance, obstacle avoidance, human–computer interaction, cyclist safety, blind navigation, and smart glasses. Comparative analysis across pedestrians, cyclists and motorcyclists, and persons with disabilities shows three parallel transitions: single- to multisensory interfaces, reactive to predictive systems, and isolated devices to V2X-enabled ecosystems. Contemporary research emphasizes context-adaptive interfaces, seamless V2X integration, and user-centered design, and future work should focus on lightweight communication protocols, adaptive sensory algorithms, and personalized safety profiles. The review provides a consolidated knowledge map to inform researchers, practitioners, and policy-makers striving for inclusive and proactive road safety solutions. Full article

As cities globally prioritize sustainable transportation, understanding gender-differentiated responses to the urban built environment is critical for equitable mobility planning. This study combined the Social Ecological Model (SEM) with the theoretical perspective of Gendered Spatial Experience to explore the differentiated impacts of the Perceived Street Built Environment (PSBE) on the cycling behavior of men and women. Questionnaire data from 285 e-bike and traditional bicycle riders (236 e-bike riders and 49 traditional cyclists, 138 males and 147 females) from Gulou District, Nanjing, between May and October 2023, were used to investigate gender differences in cycling behavior and PSBE using the Mann–Whitney U-test and crossover analysis. Linear regression and logistic regression analyses examined the PSBE impact on gender differences in cycling probability and route choice. The cycling frequency of women was significantly higher than that of men, and their cycling behavior was obviously driven by family responsibilities. Greater gender differences were observed in the PSBE among e-bike riders. Women rated facility accessibility, road accessibility, sense of safety, and spatial comfort significantly lower than men. Clear traffic signals and zebra crossings positively influenced women’s cycling probability. Women were more sensitive to the width of bicycle lanes and street noise, while men’s detours were mainly driven by the convenience of bus connections. We recommend constructing a gender-inclusive cycling environment through intersection optimization, family-friendly routes, lane widening, and noise reduction. This study advances urban science by identifying gendered barriers in cycling infrastructure, providing actionable strategies for equitable transport planning and urban design. Full article

Accurate and detailed spatial data on wind energy infrastructure is essential for renewable energy planning, grid integration, and system analysis. However, publicly available datasets often suffer from limited spatial accuracy, missing attributes, and inconsistent metadata. To address these challenges, this study presents a harmonized and spatially refined dataset of wind turbines in South Africa, combining OpenStreetMap (OSM) data with high-resolution satellite imagery, deep learning-based coordinate correction, and manual curation. The dataset includes 1487 turbines across 42 wind farms, representing over 3.9 GW of installed capacity as of 2025. Of this, more than 3.6 GW is currently operational. The Geo-Coordinates were validated and corrected using a RetinaNet-based object detection model applied to both Google and Bing satellite imagery. Instead of relying solely on spatial precision, the curation process emphasized attribute completeness and consistency. Through systematic verification and cross-referencing with multiple public sources, the final dataset achieves a high level of attribute completeness and internal consistency across all turbines, including turbine type, rated capacity, and commissioning year. The resulting dataset is the most accurate and comprehensive publicly available dataset on wind turbines in South Africa to date. It provides a robust foundation for spatial analysis, energy modeling, and policy assessment related to wind energy development. The dataset is publicly available. Full article

This article addresses the issue of historical heritage revitalization using the example of a tavern. The concept presented in this study constitutes an attempt to establish a connection between the community’s tangible historical legacy and the green space that both highlights and reinforces its significance. The Tatary district in Lublin includes areas along Mełgiewska Street, Zadębie III, and the village of Hajdów. It is a residential and industrial district with landmarks such as the Graff Manor and the Krauze Brothers’ Mill. Since the Middle Ages, a crossing existed here at the narrowing of the Bystrzyca River valley, where major communication routes from Lithuania to Łęczna and from Ruthenia to Mełgiew intersected. Located in this area, the Red Inn has one of the oldest culinary traditions in Lublin, dating back to the 16th century. The building is listed in the register of monuments under number A/268. The revitalization of this currently non-operational inn should focus on restoring the building to preserve its original character and historical value while adapting it to modern standards. The inn and its surroundings have been subjected to field analyses on multiple research levels, culminating in a land development project. A key element of the plantings here are native species that support biodiversity. Full article

In the context of autonomous driving, predicting pedestrian behavior is a critical component for enhancing road safety. Currently, the focus of such predictions extends beyond accuracy and reliability, placing increasing emphasis on the explainability and interpretability of the models. This research presents a novel neuro-symbolic approach that integrates deep learning with fuzzy logic to develop a pedestrian behavior predictor. The proposed model leverages a set of explainable features and utilizes a fuzzy inference system to determine whether a pedestrian is likely to cross the street. The pipeline was trained and evaluated using both the Pedestrian Intention Estimation (PIE) and Joint Attention for Autonomous Driving (JAAD) datasets. The results provide experimental insights into achieving greater explainability in pedestrian behavior prediction. Additionally, the proposed method was applied to assess the data selection process through a series of experiments, leading to a set of guidelines and recommendations for data selection, feature engineering, and explainability. Full article

Parkinson’s disease (PD) causes attentional deficits and worse dual-task (DT) performance, which increases the risk of being run over. In addition to motor deficits, the decision-making ability and the response to external stimuli are impaired. The aim of this study was to evaluate the spatiotemporal parameters of gait during everyday tasks of individuals with PD, specifically during street crossing simulation, obstacle circumvention, and motor DT. People with PD (PG) and matched controls (CG) were distributed into two groups and were evaluated under six different gait and randomized conditions: without a concomitant task (NW); with obstacle circumvention (OC); and four other conditions under simulation of street crossing (without concomitant task (SC); with obstacle circumvention (SC_OC); carrying bags (SC_B); and carrying bags concomitant to obstacle circumvention (SC_OC+B)). The CG group had greater values for all parameters compared to PG, except for double support time. This study’s results found that individuals with PD took smaller, narrower, slower, and shorter steps when compared to neurologically healthy older people and that there was a change in the spatiotemporal gait parameters of all individuals, except for the step-duration parameter under the most difficult crossing conditions. Full article

While deep learning-based image matching methods excel at extracting high-level semantic features from remote sensing data, their performance degrades significantly under cross-daylight conditions and wide-baseline geometric distortions, particularly in multi-source street-view scenarios. This paper presents a novel illumination-invariant framework that synergistically integrates geometric topology and semantic consistency to achieve robust multi-view matching for cross-daylight urban perception. We first design a self-supervised learning paradigm to extract illumination-agnostic features by jointly optimizing local descriptors and global geometric structures across multi-view images. To address extreme perspective variations, a homography-aware transformation module is introduced to stabilize feature representation under large viewpoint changes. Leveraging a graph neural network with hierarchical attention mechanisms, our method dynamically aggregates contextual information from both local keypoints and semantic topology graphs, enabling precise matching in occluded regions and repetitive-textured urban scenes. A dual-branch learning strategy further refines similarity metrics through supervised patch alignment and unsupervised spatial consistency constraints derived from Delaunay triangulation. Finally, a topology-guided multi-plane expansion mechanism propagates initial matches by exploiting the inherent structural regularity of street scenes, effectively suppressing mismatches while expanding coverage. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods, achieving a 6.4% improvement in matching accuracy and a 30.5% reduction in mismatches under cross-daylight conditions. These advancements establish a new benchmark for reliable multi-source image retrieval and localization in dynamic urban environments, with direct applications in autonomous driving systems and large-scale 3D city reconstruction. Full article

Federated learning is a distributed machine learning framework that allows multiple clients to collaborate on training global models without sharing raw data, thereby protecting data privacy. However, it is still a challenge to construct an efficient federated learning method for the semantic segmentation task of automated driving street view. On the one hand, the complexity of the semantic segmentation model is high, resulting in huge computing and communication overhead of client local training. On the other hand, the client data distribution is significantly different and has Non-Independent and Identically Distributed (non-IID) characteristics, which easily leads to the difficulty of global model convergence or the deterioration of generalization performance. Therefore, this paper proposes a Federal Street View segmentation method, Federal Street View Segmentation (FedSS), which optimizes model training by improving the cross-entropy loss function and designing a gradient compensation strategy and a gradient sparse compression strategy to alleviate the high communication overhead in federation learning. Extensive experiments show that our approach can consume fewer computational resources and achieve higher communication efficiency while improving semantic segmentation performance. Full article

The aging population has posed significant challenges to the built environment (BE) in urban residential areas, particularly in addressing older adults’ activity and health needs. Understanding how the BE influences older adults’ activity and health is crucial for promoting active and healthy aging. This study explored the interactions among the BE, self-efficacy (SE), activity engagement (AE), and self-rated health (SH) for older adults in urban residential areas. A random sampling technique selected 372 older adults residing in urban residential areas to participate in the questionnaire survey. Spearman correlation and hierarchical regression analysis were used to develop the BE-SE-AE-SH model for older people based on social cognitive theory. Accessibility, land use mix, and street connectivity affect activity engagement by influencing older persons’ walking and self-care abilities. Land use mix discourages walking ability and activity engagement, while esthetics encourages activity engagement. Land use mix, street connectivity, transportation, walking ability, self-care ability, and activity engagement enhance older adults’ self-rated health. Practical recommendations for age-friendly urban residential areas include the following: (1) optimize elevators and footpaths; (2) decentralize small businesses and create multi-use parking; (3) shorten crossings and enhance pavements; (4) add natural and humanistic elements; (5) limit car speed and install traffic signals. Full article

In 21st-century American cities, urban crime remains a critical public safety concern influenced by complex social, political, and environmental structures. Crime is not randomly distributed and built-environment characteristics, such as street network configuration, impact criminal activity through spatial dependence effects at multiple scales. This study investigates the cross-sectional, multi-scale spatial effects of street network configuration on property crime across neighborhoods in Charlotte, North Carolina. Specifically, we examine whether the fundamental characteristics of a neighborhood’s street network contribute to variations in its property crime. Using a novel and granular spatial approach, incorporating spatial econometric models (SAR, CAR, and GWR), several street network characteristics, including density, connectivity, and centrality, within five nested buffer bands are measured to capture both local and non-local influences. The results provide strong and consistent evidence that certain characteristics of the neighborhood street network, such as connectivity and accessibility, significantly influence the occurrence of property crime. Impacts are also found to be spatially heterogenous, manifesting themselves at the mid-range scale rather than hyper-locally. The integration of comprehensive measures of street network configuration into spatially explicit models offers new opportunities for advancement in environmental criminology literature. Such spatial dynamics further contribute to urban safety policy by informing decision-makers so that they can ensure a defensively built environment design. Full article