{
  "paper_id": "f633428bfe16ab55f6e5c9fb6c249faf",
  "paper_title": "Lidar-Based Detection and Analysis of Serendipitous Collisions in Shared Indoor Spaces",
  "paper_authors": [
    "Addison H. Flack",
    "Thomas J. Pingel",
    "Timothy D. Baird",
    "Shashank Karki",
    "Nicole Abaid"
  ],
  "publication_date": "2025-09-18",
  "publication_venue": "Remote Sensing",
  "abstract": "Indoor environments significantly influence human interaction, collaboration, and well-being, yet evaluating how architectural designs actually perform in fostering social connections remains challenging. This study demonstrates the use of 11 static-mounted lidar sensors to detect serendipitous encounters—collisions—between people in a shared common space of a mixed academic-residential university building. A novel collision detection algorithm achieved 86.1% precision and detected 14,022 interactions over 115 days (67 million person-seconds) of an academic semester. While occupancy strongly predicted collision frequency overall ( $R^2 \\geq 0.74$), significant spatiotemporal variations revealed the complex relationship between co-presence and social interaction. Key findings include the following: (1) collision frequency peaked early in the semester then declined by ~25% by mid-semester; (2) temporal lags between occupancy and collision peaks of 2–3 h in the afternoon indicate that social interaction differs from physical presence; (3) collisions per occupancy peaked on the weekend, with Saturday showing 52% higher rates than the weekly average; and (4) collisions clustered at key transition zones (elevator areas, stair bases), with an additional “friction effect”, where proximity to seating increased interaction rates (>30%) compared to open corridors. This methodology establishes a scalable framework for post-occupancy evaluation, enabling evidence-based assessment of design effectiveness in fostering the spontaneous interactions essential for creativity, innovation, and place-making in built environments.\n",
  "keywords": [
    "indoor geography",
    "lidar",
    "movement tracking",
    "post-occupancy evaluation"
  ],
  "paper_institutions": [
    "Virginia Polytechnic Institute and State University",
    "Binghamton University"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "deepseek-v4-flash",
  "prompt_template": "simple",
  "extracted_at": "2026-08-18T10:30:40.096194Z",
  "template_tag": "simple",
  "summary": "### 摘要\n\n本文针对室内建筑环境如何促进自发性社会互动难以量化评估的问题，提出并验证了一种基于静态激光雷达网络的“偶然碰撞”检测与分析方法。研究背景涉及室内地理学、激光雷达感知、弱联系与场所营造等方向；作者在弗吉尼亚理工大学一栋混合学术-居住建筑（CID）的公共空间中部署了11台顶置Blickfeld Cube 1激光雷达，连续采集115天共6700万人秒的匿名轨迹数据。该空间被设计为促进协作，包含多个走廊、电梯和中央楼梯，适合验证碰撞检测算法。检测算法以Percept生成的时空轨迹为基础，采用六重过滤机制：位移过滤（总位移≥4 m）、运动过滤（速度<0.3 m/s且减速）、时空邻近过滤（1.5 m内同时出现）、航向过滤（航向差≥90°）、事件过滤和去重过滤（2 m/5 s内合并），从而识别两人或多人从不同方向相遇并停留的偶然互动。算法在人工验证中达到86.1%的精确率，共检测到14,022次碰撞；占用率与碰撞次数在小时、日、周尺度上均呈强相关（R²≥0.74），但碰撞峰值比占用峰值滞后2–3小时，周六单位占用碰撞率比周均值高52%，且碰撞聚集在电梯、楼梯底部和“运动-停留”边界等摩擦区域，靠近座位的走廊比开放走廊互动率提高30%以上。碰撞频次在学期初最高，到期中下降约25%，感恩节到寒假前回升。研究还指出未来可结合视觉语言模型、声学传感器和跨建筑部署来改进检测，并用于建筑后评估与设计干预实验；当前局限包括静止人员易丢失、高密度活动期间验证困难以及电梯附近可能将单纯共处误判为互动。\n\n### 关键要点\n\n- 研究使用11台静态安装的Blickfeld Cube 1激光雷达，以72°×30°视场、230扫描线和2.4 Hz输出频率，连续监测弗吉尼亚理工大学CID建筑底层公共空间。\n- 数据采集持续2023年8月21日至12月13日共115天，累计获得约6700万人秒的Percept匿名轨迹数据，并检测出14,022次碰撞。\n- 碰撞检测算法包含位移、运动、时空邻近、航向、事件和去重六重过滤；其中位移过滤要求总位移≥4 m，运动过滤要求速度<0.3 m/s且减速，时空邻近过滤要求1.5 m内同时出现，航向过滤要求航向差≥90°，去重过滤合并2 m/5 s内的重复碰撞。\n- 算法性能通过3小时（10,800帧）低、中、高占用场景的人工动画复核验证，127次检测中68.5%为真阳性、11.0%为假阳性、20.5%不明确，按明确案例计算精确率为86.1%。\n- 占用率与碰撞次数在小时（R²=0.76）、日（R²=0.74）和周（R²=0.92）尺度上均显著相关，但小时尺度上碰撞峰值比占用峰值晚2–3小时，表明社交互动时间不同于单纯在场时间。\n- 按星期分析显示，周五和周六的单位占用碰撞率分别比周均值高24.53%和51.90%，而周一、周二、周三分别低17.13%、32.37%和12.07%，且该模式在整个学期保持一致。\n- 空间上，碰撞高发于电梯区域（超过2000次）、楼梯底部和社区集会空间中心；广义线性回归（R²=0.598）和地理加权回归（R²=0.84）显示走廊和部分高占用座位区碰撞低于预期，而电梯和楼梯底部高于预期。\n- 在走廊细尺度分析中，速度与占用在通道中心最高，碰撞呈双峰分布并偏向有座位的一侧，表明“摩擦效应”使运动-停留边界比开放走廊产生更多互动。\n- 碰撞次数在学期初达到峰值，随后至期中下降约25%，感恩节到寒假前回升；作者认为这可能与弱联系减少、碰撞更细微或互动转移到其他空间有关。\n- 当前局限包括Percept对长时间静止者会丢失跟踪、高密度活动期间算法表现和验证更困难、电梯附近可能将单纯共处误判为碰撞；未来计划引入视觉语言模型、声学传感器和跨建筑短期部署。"
}