{
  "paper_id": "e48c9ad1d4b97bfb4eec20fc10eabf67",
  "paper_title": "Using Lidar to Examine Human Occupancy and Collisions within a Shared Indoor Environment",
  "paper_authors": [
    "Addison Harris Flack"
  ],
  "publication_date": "2024-05-08",
  "publication_venue": "Virginia Polytechnic Institute and State University",
  "abstract": "Indoor spaces, where we spend the majority of our lives, greatly impact our work, social interactions, and well-being. In recognition of the central role that buildings play in our lives, architects and designers have increasingly focused on creating spaces that intentionally promote interaction and collaboration between building occupants. One challenge arising from this trend is evaluating the efficacy of new designs. This study used object tracking data for the Fall 2023 semester from a collection of lidar sensors installed in a portion of a mixed-use academic building on a university campus to algorithmically detect occupancy and serendipitous collisions between people - patterns of simultaneous movement and pause that indicate that two or more individuals have stopped and had a meaningful interaction. The algorithm detected over 14,000 collisions throughout the semester with high spatial and temporal precision. Occupancy and collisions were highly related over several scales of temporal and spatial analysis. Furthermore, several interesting patterns emerged, including (a) collisions peaked early in the semester, then declined before leveling off, (b) occupancy peaked in mid-afternoon, while collisions peaked in the late afternoon and early evening, (c) collisions peaked later in the week than did occupancy, and (d) specific hotspots were apparent at important nodes such as the bottom of stairs and near elevators. The patterns found in this study can provide insight as to how interactions can be measured using remote sensing data, and can aid designers in attempting to increase collaboration in shared indoor environments.\n",
  "keywords": [
    "indoor geography",
    "lidar",
    "remote sensing",
    "placemaking",
    "interaction"
  ],
  "paper_institutions": [
    "Virginia Polytechnic Institute and State University"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "deepseek-v4-flash",
  "prompt_template": "simple",
  "extracted_at": "2026-08-18T10:30:48.292553Z",
  "template_tag": "simple",
  "summary": "### 摘要\n\n本论文针对室内共享空间中人们偶然相遇（碰撞）难以量化评估的问题，结合室内地理学、激光雷达遥感、行为地理学以及空间-地方动态等研究背景，提出了一种基于固定式激光雷达网络和Percept目标跟踪数据的碰撞检测方法。研究在弗吉尼亚理工大学布莱克斯堡校区创意与创新区生活学习社区（CID）的Community Assembly空间开展，该空间因设计上包含电梯、楼梯、走廊和座位区等多重交汇点而被选为理想研究地点；使用11台Blickfeld Cube 1激光雷达采集2023年秋季学期（8月21日至12月13日）共115天的匿名轨迹数据，约6700万人秒；由于原始数据约18GB，算法将数据分为20个等份并行处理。核心机制是依次通过位移过滤（总位移≥4 m）、运动过滤（速度<0.3 m/s且减速）、时空过滤（两人距离≤1.5 m）、航向过滤（来向夹角>90°）和去重过滤（2 m/5 s内合并）来识别碰撞。算法共检测到14,022次碰撞，人工验证显示68.5%为确定真阳性、11.0%为确定假阳性、20.5%不确定，估计准确率78.7%，双向碰撞假阴性率约46%。时间上，碰撞在学期初最高、之后下降并趋稳，下午傍晚和周五周六更频繁；占用与碰撞在小时、天、周尺度上R²分别为0.76、0.74、0.92，空间上GLR R²=0.598、GWR R²=0.84，电梯、楼梯底部和座位区是热点。进一步研究可改进算法并行化与参数优化、区分活动与非活动碰撞、加入声学传感器验证，并通过实验性布局改变探索设计影响；实际应用中需注意隐私保护、Percept丢失静止目标、传感器中断、计划性活动干扰以及MAUP/MTUP等尺度效应。\n\n### 关键要点\n\n- 研究在弗吉尼亚理工大学“创意与创新区生活学习社区”（CID）的Community Assembly公共空间进行，使用11台Blickfeld Cube 1激光雷达，覆盖2023年秋季学期（8月21日至12月13日）共115天。\n- 数据由Percept目标跟踪软件生成匿名轨迹，共约6700万人秒；原始数据约18GB，被分成20个等份并行处理，总处理时间约5.5小时。\n- 碰撞检测算法依次使用位移过滤（总位移≥4 m）、运动过滤（速度<0.3 m/s且减速）、时空过滤（两人距离≤1.5 m）、航向过滤（来向夹角>90°）和去重过滤（2 m/5 s内合并）来识别偶然互动。\n- 算法在学期内共检测到14,022次碰撞，平均每天121.9次、每小时5.1次；人工验证3小时数据中127次检测，68.5%为确定真阳性，11.0%为确定假阳性，20.5%不明确，估计准确率78.7%。\n- 12小时现场观察记录到11次双向碰撞和6次汇合碰撞；算法检测到其中6次双向碰撞，双向碰撞假阴性率约46%，且未能检测到汇合碰撞。\n- 时间分析显示，碰撞在学期前几周最高，之后下降并趋于平稳；感恩节后到期末出现反弹；占用在工作日最高，而碰撞在周五和周六更多。\n- 小时尺度上，占用在9:00–20:00较高并在15:00达到峰值，碰撞则在17:00–20:00达到峰值，存在约2–3小时的时间滞后。\n- 占用与碰撞在小时、天、周聚合尺度上均强相关（R²分别为0.76、0.74、0.92）；对数-对数斜率显示日/周略超线性（n≈1.15–1.17），小时略次线性（n=0.78）。\n- 空间上，电梯周围（超过2000次碰撞，占14.2%）、楼梯底部和主要座位区是碰撞热点；走廊和靠墙边缘碰撞少于按占用预期；GLR R²=0.598，GWR R²=0.84。\n- 在走廊横断面分析中，有座位一侧的碰撞/占用比高于无座位一侧，碰撞在通道两侧呈双峰分布，支持“移动-暂停边界摩擦”假设（H3）。\n- 局限性包括：Percept会丢失静止约15秒的人并重新分配ID，传感器有4次中断，计划性活动会抬高碰撞计数，且算法未检测远距离打招呼、静止碰撞和部分汇合碰撞。\n- 未来工作可改进算法并行化与参数优化、区分活动期间/非活动期间碰撞、加入声学传感器验证，并通过实验性摆放视觉/物理障碍物来研究空间设计对碰撞的影响。"
}