Evaluating human perception of building exteriors using street view imagery

Building and Environment, Год журнала: 2024, Номер 263, С. 111875 - 111875

Опубликована: Июль 28, 2024

Язык: Английский

---

Coverage and bias of street view imagery in mapping the urban environment

Computers Environment and Urban Systems, Год журнала: 2025, Номер 117, С. 102253 - 102253

Опубликована: Янв. 23, 2025

Язык: Английский

---

A 360-degree imagery-multisensor system for visualizing environmental parameters in architecture and urban spaces

HardwareX, Год журнала: 2025, Номер unknown, С. e00643 - e00643

Опубликована: Март 1, 2025

Язык: Английский

---

Quantifying seasonal bias in street view imagery for urban form assessment: A global analysis of 40 cities

Computers Environment and Urban Systems, Год журнала: 2025, Номер 120, С. 102302 - 102302

Опубликована: Май 9, 2025

Язык: Английский

---

Translating street view imagery to correct perspectives to enhance bikeability and walkability studies

International Journal of Geographical Information Science, Год журнала: 2024, Номер 38(12), С. 2514 - 2544

Опубликована: Авг. 27, 2024

Street view imagery (SVI), an emerging geospatial dataset, is useful for evaluating active transportation infrastructure, but it faces potential biases from its vehicle-based capture method, diverging pedestrians' and cyclists' perspectives. Existing literature lacks both examination of these a solution. This study identifies quantifies by comparing conventional SVI with views the road shoulder/sidewalk. To mitigate such perspective biases, we introduce novel framework generative adversarial network (GAN)-based image generation models (Pix2Pix CycleGAN), regression model (ResNet-50), tabular (LightGBM). Experiments assessed effectiveness in translating car-centric to those pedestrian cyclist Results show significant differences semantic indicators (e.g. green index) between center shoulder/sidewalk SVI, low Pearson's correlation coefficients r (0.35–0.55 shoulders 0.45–0.47 sidewalks) indicating bias. The succeeded creating realistic images aligning pixel ratios perspectives, achieving strong (0.81 0.83 sidewalks), thus reducing work contributes providing scalable model-agnostic approach produce accurate SVIs urban planning sustainability, setting foundation improving bikeability walkability assessments promoting transportation.

Язык: Английский

---

StreetSurfaceVis: a dataset of crowdsourced street-level imagery annotated by road surface type and quality

Scientific Data, Год журнала: 2025, Номер 12(1)

Опубликована: Янв. 16, 2025

Road unevenness significantly impacts the safety and comfort of traffic participants, especially vulnerable groups such as cyclists wheelchair users. To train models for comprehensive road surface assessments, we introduce StreetSurfaceVis, a novel dataset comprising 9,122 street-level images mostly from Germany collected crowdsourcing platform manually annotated by type quality. By crafting heterogeneous dataset, aim to enable robust that maintain high accuracy across diverse image sources. As frequency distribution types qualities is highly imbalanced, propose sampling strategy incorporating various external label prediction resources ensure sufficient per class while reducing manual annotation. More precisely, estimate impact (1) enriching data with OpenStreetMap tags, (2) iterative training application custom classification model, (3) amplifying underrepresented classes through prompt-based GPT-4o (4) similarity search using embeddings. Combining these strategies effectively reduces annotation workload ensuring representation.

Язык: Английский

---

Cross-view geolocalization and disaster mapping with street-view and VHR satellite imagery: A case study of Hurricane IAN

ISPRS Journal of Photogrammetry and Remote Sensing, Год журнала: 2025, Номер 220, С. 841 - 854

Опубликована: Фев. 1, 2025

Язык: Английский

---

Nighttime Street View Imagery: A new perspective for sensing urban lighting landscape

Sustainable Cities and Society, Год журнала: 2024, Номер 116, С. 105862 - 105862

Опубликована: Окт. 16, 2024

Язык: Английский

---

A perception-powered urban digital twin to support human-centered urban planning and sustainable city development

Cities, Год журнала: 2024, Номер 156, С. 105473 - 105473

Опубликована: Окт. 21, 2024

Язык: Английский

---

Examining the causal impacts of the built environment on cycling activities using time-series street view imagery

Transportation Research Part A Policy and Practice, Год журнала: 2024, Номер 190, С. 104286 - 104286

Опубликована: Окт. 21, 2024

Язык: Английский

---