Scholarlink

<p>Understanding how environmental conditions and policy interventions jointly shape pedestrian mobility is essential for designing resilient, adaptive, and human-centered urban spaces. This study presents a computer-vision framework that extracts pedestrian trajectories from a year-long video dataset recorded by a fixed camera system in a high-traffic shopping district in Fukuoka, Japan. The framework combines a real-time object-detection model with a multi-object tracking algorithm to analyze walking speeds across four daily time slots—morning, afternoon, evening, and night—under varying temperatures and during three coronavirus disease 2019 State of Emergency periods. The results reveal that pedestrian responses are strongly moderated by walking purpose: morning commuters walked faster and were more sensitive to temperature, whereas nighttime pedestrians exhibited greater behavioral variability and responded more to emergency-period restrictions than to thermal conditions. Demographic analysis further indicated a shift toward a younger nighttime population during emergency periods. These findings show that the relative influence of environmental versus policy factors is time- and purpose-dependent, an effect obscured by conventional daily-aggregate analyses. Beyond these behavioral insights, the framework demonstrates that low-cost camera infrastructure can support scalable, real-time monitoring and evidence-based evaluation of urban policies, providing practical tools for adaptive planning and more resilient smart cities.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Monitoring pedestrian walking dynamics under environmental and policy influences in urban spaces

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月31日

查看全文
  • Mohamed A. Abdelwahab,
  • Shizuo Kaji,
  • Maiya Hori,
  • Shigeru Takano

摘要

Understanding how environmental conditions and policy interventions jointly shape pedestrian mobility is essential for designing resilient, adaptive, and human-centered urban spaces. This study presents a computer-vision framework that extracts pedestrian trajectories from a year-long video dataset recorded by a fixed camera system in a high-traffic shopping district in Fukuoka, Japan. The framework combines a real-time object-detection model with a multi-object tracking algorithm to analyze walking speeds across four daily time slots—morning, afternoon, evening, and night—under varying temperatures and during three coronavirus disease 2019 State of Emergency periods. The results reveal that pedestrian responses are strongly moderated by walking purpose: morning commuters walked faster and were more sensitive to temperature, whereas nighttime pedestrians exhibited greater behavioral variability and responded more to emergency-period restrictions than to thermal conditions. Demographic analysis further indicated a shift toward a younger nighttime population during emergency periods. These findings show that the relative influence of environmental versus policy factors is time- and purpose-dependent, an effect obscured by conventional daily-aggregate analyses. Beyond these behavioral insights, the framework demonstrates that low-cost camera infrastructure can support scalable, real-time monitoring and evidence-based evaluation of urban policies, providing practical tools for adaptive planning and more resilient smart cities.