Immersive virtual reality and computer vision for heritage: visual evaluation and perception of the industrial heritage sites along the Yunnan–Vietnam railway (Yunnan section)

Heritage Science, Год журнала: 2024, Номер 12(1)

Опубликована: Фев. 2, 2024

Abstract The visual composition and human perception are found to relate the reuse tourism of heritage railways. Previous studies have used either environmental audits on-site interviews that limitations in terms cost, time, measurement scale, or virtual base on two-dimension images but with gaps interactivity, immersion field view. This study developed an “objective + subjective” evaluation framework integrating Computer Vision (CV) Immersive Virtual Reality (IVR) assess quality industrial sites along Yunnan-Vietnam Railway (Yunnan Section). stepwise multiple linear regression models were carried out investigate relationship between objective subjective perception. results showed 16 landscape elements successfully segmented. According score bands, 120 classified as 39 high-score sites, 66 medium-score 15 low-score sites. In general, although sky hard ground accounted for a higher proportion, they had little effect sum scores, while vegetation, water, buildings played significant role quality. can help researchers, planners, government departments clarify scientifically specify bottom-up planning management solutions railway Moreover, simplicity, accuracy, effectiveness this make it suitable large-scale other

Язык: Английский

---

A Campus Landscape Visual Evaluation Method Integrating PixScape and UAV Remote Sensing Images

Buildings, Год журнала: 2025, Номер 15(1), С. 127 - 127

Опубликована: Янв. 3, 2025

Landscape, as an important component of environmental quality, is increasingly valued by scholars for its visual dimension. Unlike evaluating landscape quality through on-site observation or using digital photos, the visualization modeling method supported unmanned aerial vehicle (UAV) photography, geographic information System (GIS), and PixScape has advantage systematically scanning space. The data acquisition convenient fast, resolution high, providing a new attempt analysis. In order to explore application visibility based on high-resolution UAV remote sensing images in evaluation, this study takes campus example uses basic source analyze differences between planar tangent provided 1.2 software modeling. Six evaluation factors, including Naturalness (N), Normalized Shannon Diversity Index (S), Contagion (CONTAG), depth (SD), Depth Line (DL), Skyline (SL), are selected evaluate vision four viewpoints analytic hierarchy process (AHP) method. results indicate that considers impact vertical amplitude distance viewpoints, which more line with real perception human eyes. addition, objective quantitative metrics can reflect landscapes from different have good applicability evaluation. It expected research enrich system provide technical references it.

Язык: Английский

---

Assessing the landscape visual quality of urban green spaces with multidimensional visual indicators

Urban forestry & urban greening, Год журнала: 2025, Номер unknown, С. 128727 - 128727

Опубликована: Фев. 1, 2025

Язык: Английский

---

Evaluation of Thermal Comfort in Urban Commercial Space with Vision–Language-Model-Based Agent Model

Land, Год журнала: 2025, Номер 14(4), С. 786 - 786

Опубликована: Апрель 6, 2025

Thermal comfort in urban commercial spaces significantly impacts both business performance and public well-being. Traditional evaluation methods relying on field surveys expert assessments are often time-consuming labor-intensive. This study proposes a novel vision–language model (VLM)-based agent system for thermal assessment spaces, simulating eight distinct heat-sensitive roles with varied demographic backgrounds through prompt engineering using ChatGPT-4o. Taking Harbin Central Street, China as case study, we first validated accuracy ASHRAE scale evaluations of 30% samples (167 images) by 50 experts, then conducted simulations followed spatial interpretability analyses. Key findings include (1) significant correlation between VLM (r = 0.815, p < 0.001), confirming method feasibility; (2) notable heterogeneity across agents, demonstrating the VLMs’ capacity to capture perceptual differences among social groups; (3) analysis revealing higher eastern regions compared western central areas despite inter-role variations, consistency agents; (4) shade vegetation being identified primary influencing factors that contribute agent’s decision making. research validates VLM-based agents’ effectiveness evaluation, showcasing their dual capability replicating traditional while capturing group differences. The proposed approach establishes paradigm efficient, comprehensive, multi-perspective environments.

Язык: Английский

---

Scaling up natural experimental studies: harnessing emerging technologies to transform physical activity and built environment research

International Journal of Behavioral Nutrition and Physical Activity, Год журнала: 2025, Номер 22(1)

Опубликована: Апрель 11, 2025

Язык: Английский

---

Understanding the visual perception and environmental impressions of tourists’ experiences in Suzhou’s modern gardens in China

Cogent Arts and Humanities, Год журнала: 2025, Номер 12(1)

Опубликована: Апрель 23, 2025

Язык: Английский

---

Assessing the relationship between urban park spatial features and physical activity levels in Residents: A spatial analysis Utilizing drone remote sensing

Ecological Indicators, Год журнала: 2024, Номер 166, С. 112520 - 112520

Опубликована: Авг. 28, 2024

The park environment is crucial for promoting physical activity (PA). While numerous studies show that environments influence PA behavior, inconsistencies remain, likely due to varing research methods and parks types. This study employs a fixed spatial grid method systematically sample four representative in Tianjin, China. High-precision orthophoto map (DOM) data from drones provided detailed environmental attributes (like tree canopy area, lawn paved area) characteristics (number of participants, intensity, diversity). results show: 1) Cluster analysis grouped 1839 grids into 12 attribute integrations, each correlating with different characteristics. "Tree-lined jogging corridors" "Large sports field areas" exhibit the highest while "Entrance plazas", "Central plazas," "Open spaces" have number participants diversity. 2) Correlation shows various attributes, including Lawn Area, Paved are significantly correlated 3)Random Forest indicates key area diversity, specialized facilities intensity. These findings support urban green space planning highlight importance better public health.

Язык: Английский

---

Real-Time Sensor-Based and Self-Reported Emotional Perceptions of Urban Green-Blue Spaces: Exploring Gender Differences with FER and SAM

Sensors, Год журнала: 2025, Номер 25(3), С. 748 - 748

Опубликована: Янв. 26, 2025

Urban green-blue spaces (UGBS) are increasingly recognized for their benefits to physical and mental well-being. However, research on real-time gender-specific emotional responses UGBS remains limited. To address this gap, a dual-method approach combining facial expression recognition (FER) self-reported measures investigate gender differences in evaluations of was developed. Using static images from Google Street View as stimuli, self-reporting experiment involving 108 participants provided insights into subjective experiences. Subsequently, FER experiment, utilizing 360-degree video captured over two million data points, validating the feasibility advantages emotion monitoring. The findings revealed distinct patterns: women experienced stronger pleasant emotions preferred scenes evoking higher arousal, while men demonstrated sharper rated with peak valence more favorably. Grass elicited relaxation delight arousal men, whereas blue induced calmness across genders, reporting greater water content increased. study underscores potential technology assessing responses, providing actionable inclusive urban planning. By integrating advanced tools participatory design approaches, planners can develop strategies that enhance well-being create livable cities support diverse user needs.

Язык: Английский

---

Designing effective image-based surveys for urban visual perception

Landscape and Urban Planning, Год журнала: 2025, Номер 260, С. 105368 - 105368

Опубликована: Апрель 17, 2025

Язык: Английский

---

A comparative study of the perception of traditional villages between different media

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 8, 2025

Nowadays, more and people choose to go the traditional villages with beautiful scenery relaxing atmosphere relax relieve stress due unique cultural background environmental of villages, which well met public's aesthetic value landscape environment. Previous research has primarily focuses on villages' history, background, rural land planning, ancient architecture other directions. However, relatively few studies have explored public perception village landscape. Existing are usually limited a single-field study or laboratory study, medium used show remain simple. Therefore, this investigates perceptions space using an experimental approach. It examines how subjects perceive landscapes two-dimensional (2D) displays, three-dimensional (3D) VR five media representing landscapes: real scenes, photographs, videos, 2D panoramas, 3D panoramas. The advantages, limitations, feasibilities various combinations representations analyzed determine optimal methods for evaluation. results demonstrate that combination significantly influences evaluations by affecting subjects' perceptions. degree is highly significant mediating factor. displays 720° panoramas provides best agreement between laboratory-based findings real-world environments, regardless type. This paper summarizes data under media, compares analyzes results, aim provide most suitable reference scheme future in related fields.

Язык: Английский

---