Treffer: Assessment of tourist sun exposure using computer vision technology: A micro-scale analysis with 3D modeling and surveillance image data.

• Developed a novel method for identifying and assessing tourist sun exposure in complex surveillance environments. • Introduced an inverted pyramid slicing-assisted object detection technique for high-accuracy tourist recognition. • Achieved spatial mapping of tourist sun exposure and identified significant patterns of direct sunlight exposure throughout the day. • Provided management recommendations for optimizing shading facilities and improving tourist experience in high-temperature weather. With increases in extreme heat events, precise assessment of tourist sun exposure is crucial for enhancing destination resilience and visitor experience. However, research has focused predominantly on macro-scale climate suitability or localized thermal comfort, and fine-grained quantitative analyses are lacking. Leveraging advances in computer vision and ubiquitous surveillance infrastructure, this study develops a novel framework integrating 3D modeling and visual perception to dynamically evaluate tourist sun exposure in outdoor settings. The method introduces: (1) an inverted pyramid-based object detection technique to address variation in accuracy in complex monitoring scenarios; (2) a dynamic shaded area extraction approach using detailed 3D modeling; and (3) a non-sun exposure index linking image coordinates to geographic coordinates to reveal spatiotemporal patterns. The framework was validated in a scenic area, demonstrating superior detection accuracy to those of existing methods, while revealing that over 60 % of tourists were sun-exposed during peak periods, with 65 % neglecting physical protection. This research bridges the gap between static macro-assessments and dynamic micro-perception, enabling data-driven optimization of shading infrastructure and visitor management. The framework can be extended to heat exposure analyses in other public spaces, offering a scalable tool for climate-resilient urban planning. [ABSTRACT FROM AUTHOR]

Copyright of Building & Environment is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)