{
  "paper_id": "01ecf6781e3e07b1539c74d3f9bf6594",
  "paper_title": "Reliable People Detection Using Range and Intensity Data from Multiple Layers of Laser Range Finders on a Mobile Robot",
  "paper_authors": [
    "Alexander Carballo",
    "Akihisa Ohya",
    "Shin'ichi Yuta"
  ],
  "publication_date": "2011-01-07",
  "publication_venue": "International Journal of Social Robotics",
  "abstract": "Reliable people detection is an important task in several areas like security, intelligent environments and human robot interaction. People detection does not depend only upon separation of static environment objects from those showing motion (hopefully humans), a reliable system should be able to detect static people even in cluttered environments.\n\nThis work presents a reliable approach for people detection and position estimation using multiple layers of Laser Range Finders (LRF) on a mobile robot. Each layer combines two LRF sensors to scan around the robot's surroundings and are vertically separated to detect distinct parts of the human body. By using AdaBoost we create strong classifiers to detect body parts, candidate segments in each layer are fused for people detection, and we use simple data association to estimate their positions. Additionally, this work introduces laser reflection intensity as a novel property for people detection. First, we present a study of laser intensity and textiles, then introduce new intensity-based features for detection, and propose a method for segment separation using laser intensity. We provide a thorough evaluation of our multi-layered system through several experiments on a mobile robot.",
  "keywords": [
    "Multi-layered laser range finder",
    "Laser reflection intensity",
    "People detection",
    "AdaBoost",
    "Sensor fusion"
  ],
  "paper_institutions": [
    "University of Tsukuba"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:46:32.242913Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本论文针对移动机器人可靠人员检测问题，提出利用多层激光测距仪（LRF）的方案。系统由两层LRF组成，每层两个传感器分别面向前后，实现360°扫描，垂直间隔约70cm，以检测人体的胸部和腿部。采用AdaBoost训练强分类器，基于多种范围和强度特征对段进行分类。创新性地引入激光反射强度作为新特征，并提出了基于Gompertz函数的强度校准方法，以减小距离对强度的影响。同时，利用强度差异的方差来检测和分离合并段（例如人和物体靠近时），通过期望最大化算法估计高斯混合的参数以确定分割点。实验在四个不同环境（杂乱区域、人群、走廊、办公室）中进行，结果表明，融合强度特征后，多层检测系统的真检测率从77.4%-89.2%提升至88.2%-92.6%，假阳性率显著下降，单层检测率也明显提升。系统处理时间平均52ms，低于传感器扫描周期100ms，满足实时性要求。未来工作包括动态选择分类器、利用强度进行人员识别以及群体跟踪等。\n\n### 关键要点\n- 系统采用两层激光测距仪，每层两个传感器，分别面向前后，实现360度扫描，垂直间隔约70cm以检测胸部和腿部。\n- 使用AdaBoost训练强分类器，基于12种范围特征（包括新增的尺寸比和归一化点数）和4种强度特征。\n- 引入激光反射强度作为新特征，提出基于Gompertz函数的强度校准方法，以减小距离影响。\n- 强度特征包括平均强度、强度方差、强度差异平均和强度均匀性，用于改善段分类。\n- 利用强度差异的方差检测合并段，采用期望最大化算法分离高斯混合，确定分割点。\n- 实验在四个环境（clutter, crowd, hallway, office）进行，包含不同人数和遮挡情况。\n- 使用多传感器融合和多层融合，基于步行模型（步长、腿部间距）关联胸部和腿部段。\n- 实验结果：仅范围特征时，多层系统检测率77.4%-89.2%；加入强度特征后提升至88.2%-92.6%，且假阳性率下降。\n- 单层检测率远低于多层，加入强度后有所提升但仍明显不足。\n- 简化分类器（只使用3个范围特征+4个强度特征）也获得较好检测率，说明强度特征有效。\n- 限制：同时获取范围和强度时角分辨率减半，影响小物体检测；黑色低反射织物在远距离无法获取数据。\n- 未来工作：基于环境动态选择分类器、用强度进行人员识别、群组跟踪和社会力模型。"
}