{
  "paper_id": "92e3a4602c393e033102780832c188d2",
  "paper_title": "People detection and tracking with multiple stereo cameras using particle filters",
  "paper_authors": [
    "Rafael Muñoz-Salinas",
    "R. Medina-Carnicer",
    "F.J. Madrid-Cuevas",
    "A. Carmona-Poyato"
  ],
  "publication_date": "2009-03-24",
  "publication_venue": "Not specified",
  "abstract": "In this work, a novel approach for people detection and tracking using multiple stereo cameras is proposed. Our proposal consists in combining information from all the available cameras using three different plan-view maps. Occupancy and height maps register the volume and height of the objects that are visible in the stereo cameras, respectively. We also propose the use of a novel map, named confidence map, which registers the confidence of the information projected in each cell. The proposed confidence map is employed to fuse the information captured by each camera so that the most reliable information is kept in each cell. We then propose a particle filter algorithm for tracking people in the fused plan-view maps. The observation model employed considers height, occupancy and confidence information so that information from the most reliable camera is employed at each time instant. The experiments conducted show the validity of our proposal.",
  "keywords": [
    "Plan-view maps",
    "Stereo vision",
    "Person tracking",
    "Particle filtering",
    "Colour processing",
    "Condensation algorithm",
    "Person detection",
    "Gesture recognition"
  ],
  "paper_institutions": [
    "Department of Computing and Numerical Analysis, University of Córdoba"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:06.379803Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文提出了一种使用多个立体相机进行人员检测与跟踪的新方法。目标是在多相机环境下解决单相机视野受限和遮挡问题，利用立体视觉提供深度信息以增强鲁棒性。该方法为每个相机生成三种平面视图地图：占用图、高度图和一种新颖的置信度图，其中置信度图记录每个单元投影信息的可靠性。通过置信度图将来自各相机的信息融合，保留每个单元最可靠的信息，从而构建全局地图。跟踪阶段采用多个粒子滤波器，每个目标一个独立的跟踪器，融合占用、高度和置信度信息构建观测模型，并结合交互因子避免粒子凝聚问题，同时设计遮挡检测与恢复机制。实验在三个真实场景（PEIS房间、第二场景、走廊）中进行，摄像头数量分别为2、3、2，帧率分别为7fps和15fps，分辨率320×240，共10人参与，序列人数2-4人。结果显示，使用40个粒子时跟踪误差约为0.15m，背景去除、地图创建和每个跟踪器分别耗时30ms、9ms和2.5ms。置信度地图的引入有效减少了立体误差造成的虚假模式，显著降低了跟踪误差。未来可改进背景去除效率，并扩展颜色地图。\n\n### 关键要点\n- 提出使用占用图、高度图和置信度图三种平面视图地图，用于融合多个立体相机的信息。\n- 置信度图基于立体误差模型，使用高斯函数定义，距离越远置信度越低，用于选择最可靠信息。\n- 地图融合时，每个单元选取置信度最高的相机的数据，确保全局地图包含最可靠信息。\n- 采用多个独立粒子滤波器，每个目标一个跟踪器，避免标准粒子滤波器的凝聚问题。\n- 粒子权重由占用概率、高度概率和置信度概率的乘积组成，置信度概率采用逆巴特沃斯分布。\n- 随机游走运动模型，噪声标准差根据帧率计算（σ_m = 1/fps），以适应人类行走速度。\n- 交互因子基于高斯函数，防止多个跟踪器粒子相互吸引而融合。\n- 遮挡检测通过估计位置的似然值低于阈值触发，此时增加粒子数和扩散程度，恢复后恢复默认值。\n- 实验在三个场景中验证：PEIS房间（2个相机，7fps）、第二场景（3个相机，15fps）、15米走廊（2个相机，7fps）。\n- 跟踪误差随粒子数增加而降低，40个粒子时达到0.15m RMSE，继续增加无明显改进。\n- 置信度地图的移除导致虚假模式（幻影）出现，尤其在走廊两端，误差增加近1米，证明了其重要性。\n- 背景去除是最耗时部分（30ms），未来工作将致力于优化。"
}