{
  "paper_id": "9533c6f4465cdf1bf89174c99315ee7d",
  "paper_title": "Cost-effective Stationary Human Detection Using 2D LiDAR for Security Robots",
  "paper_authors": [
    "Haruki Mochizuki",
    "Ryozo Kiyohara"
  ],
  "publication_date": "",
  "publication_venue": "2025 19th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI-Winter)",
  "abstract": "Since the COVID-19 pandemic, Japanese industries have been facing labor shortages across various sectors. In particular, the security industry has been affected due to an aging workforce and a lack of younger employees. This shortage has also impacted university security operations, where wide-area patrols place a considerable burden on security guards. Meanwhile, advancements in robotics have enabled not only the automation of simple tasks but also those involving human interaction. As a result, the development and deployment of patrol robots have been actively pursued, with high-precision situational recognition being a critical requirement for their practical implementation. However, existing robots are typically equipped with various sensors such as LiDAR and cameras, leading to high costs that hinder their adoption in university security. In this paper, we propose a cost-effective human detection method using multiple 2D LiDAR sensors. The proposed method focuses on the detection of stationary humans, an aspect that has not been sufficiently addressed in previous research. In addition, this paper outlines the key technical components necessary for the practical deployment of patrol robots in university security operations.\n",
  "keywords": [
    "patrol robot",
    "human detection",
    "2D LiDAR",
    "cost-effective sensing",
    "campus security"
  ],
  "paper_institutions": [
    "Graduate School of Kanagawa Institute of Technology",
    "Kanagawa Institute of Technology"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "deepseek-v4-flash",
  "prompt_template": "simple",
  "extracted_at": "2026-08-18T10:30:14.238966Z",
  "template_tag": "simple",
  "summary": "### 摘要\n\n针对日本安保行业因疫情、老龄化和年轻劳动力不足造成的人力短缺，以及大学校园夜间巡逻负担重的问题，本文提出一种使用多个2D LiDAR的低成本静止人体检测方法。与依赖相机和3D LiDAR的现有方案相比，该方法避免了校园光照变化带来的识别困难，也降低了点云数据量和计算成本；此前基于2D LiDAR的方法多要求人体位于正前方，本文通过提取躯干和腿部特征、在90cm和45cm高度安装LiDAR，并聚合多次扫描来提升点密度，从而支持多角度和远距离检测。实验使用VLP-16 LiDAR的单个光束模拟2D LiDAR，在约5m处采集6名不同体型受试者的正面和侧面点云作为训练数据，类别包括人、树和标志牌，测试覆盖0°到180°每30°的朝向以及5m、10m、15m、20m的距离；PointNet分类器训练100轮、batch size为32。结果表明，人在所有朝向和距离下的F值均接近或等于1.00，并能与树和标志牌正确区分，验证了仅用正面和侧面训练即可实现方向无关的静止人体识别。个人空间实验显示，夜间行人希望机器人保持约2–3m距离，因此检测应在进入个人空间前完成。未来工作将评估非人类障碍物以及坐姿、躺姿等非直立姿态。核心机制是使用PointNet对点云进行与顺序无关的特征压缩与重建，并以F值（F=2PR/(P+R)）评估分类性能。\n\n### 关键要点\n\n- 日本安保行业因疫情、老龄化和年轻劳动力不足面临人力短缺，大学夜间巡逻负担重，需要巡逻机器人。\n- 现有巡逻机器人常配备LiDAR、相机、红外等多类传感器，成本高，难以在大学安保中推广；本文提出仅用多个2D LiDAR的低成本方案。\n- 与基于图像的方法相比，2D LiDAR在校园明暗变化环境下更稳定；与3D LiDAR相比，点云数据量小、计算成本低。\n- 方法聚焦躯干和腿部，将两个2D LiDAR分别安装在约90cm和45cm高度，以适应145–170cm的老年人身高范围。\n- 由于单次扫描点密度低且随距离下降，机器人靠近目标并聚合5次扫描（<1秒）提高点密度，改善分类精度。\n- 分类采用PointNet（Classify Point Clouds Using PointNet），训练数据包含6名不同体型的受试者的正面和侧面点云，类别包括人、树和标志牌。\n- 在5m距离采集数据，测试从0°到180°每30°间隔的朝向，人的F值在所有朝向上均为1.00，且能与树和标志牌区分。\n- 在5m、10m、15m、20m距离实验中，即使点云密度下降，聚合多次扫描后仍保持接近或等于1.00的F值，说明训练正面和侧面即可泛化到不同距离。\n- 个人空间实验显示，受试者不希望机器人靠近的距离约为2–3m，闭眼时距离增大；夜间巡逻应在进入个人空间前完成可疑人员检测。\n- 背景差分实验通过参考地图与当前点云比较提取差异点，用于识别环境中的物体；蓝牙定向接收实验表明可通过RSSI方向性估计多个已认证手机的位置。\n- 未来工作包括评估非人类障碍物的分类性能，以及坐姿、躺姿等非直立姿态的人员分类。"
}