{
  "paper_id": "73f15e27bc5ce0127ca8c19e6ac3bb94",
  "paper_title": "People tracking with range cameras using density maps and 2D blob splitting",
  "paper_authors": [
    "Izaak Van Crombrugge",
    "Rudi Penne",
    "Steve Vanlanduit"
  ],
  "publication_date": "",
  "publication_venue": "Integrated Computer-Aided Engineering",
  "abstract": "A robust method is proposed for people tracking using range cameras: Density Map Tracking with Blob Splitting (DMT-BS). It was designed primarily for worker safety in industrial environments, but can be used in other applications as well. Multiple cameras can easily be added to resolve occlusions and to enlarge the observed area. The method could be used to track any moving object in an otherwise static environment as the detection does not rely on a specific human model. Its strength lies in its simplicity, making the behavior predictable and opening possibilities to be implemented on low-cost hardware. From the point cloud delivered by the depth sensor, a 2D density map is formed in floor coordinates followed by basic 2D-tracking. Robustness of this tracking is enhanced using a simple but effective blob splitting technique. Tests show that the camera position, depth noise, and extrinsic calibration errors have little influence on the tracker's performance. The proposed method was tested on three depth tracking datasets, reaching significantly better MOTA (Multiple Object Tracking Accuracy) scores when compared to two state-of-the-art depth-based trackers.",
  "keywords": [
    "Human tracking",
    "depth camera",
    "time-of-flight",
    "RGB-D",
    "industrial safety"
  ],
  "paper_institutions": [
    "Faculty of Applied Engineering, University of Antwerp",
    "Department of Mathematics, University of Antwerp"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:27.448995Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文提出了一种基于距离相机的鲁棒人员跟踪方法——密度图跟踪与斑点分割（DMT-BS），主要面向工业环境中的工人安全应用，也可推广至其他场景。该方法通过深度传感器获取的点云在地面坐标系中构建二维密度图，并采用简单的二维跟踪策略，结合有效的斑点分割技术增强鲁棒性。其核心在于利用背景差分、点云变换、分箱投影、高斯模糊、阈值分割及形态学操作生成候选斑点，再通过匈牙利算法和卡尔曼滤波实现跟踪。方法不依赖特定人体模型，可跟踪静态环境中的任何移动物体，且多相机可方便地集成以解决遮挡并扩大观测区域。实验使用两个真实数据集（KTP和EPFL）以及基于V-REP的仿真场景，评估了相机高度与角度、多相机组合、深度噪声和外部标定误差的影响，并采用CLEAR MOT指标（如MOTA、MOTP）进行比较。结果显示，DMT-BS在三个数据集上均优于DPOM和Kinect SDK等两种先进方法，且对相机角度、深度噪声（高达50mm）和标定误差（高达1°）具有良好容忍性。该方法的简单性使其行为可预测，并可在低成本的硬件上实现，同时无需识别个体身份，有利于在工业现场被工人和工会接受。未来工作将解决场景中遗留大型物体被误标为静态人员的问题。\n\n### 关键要点\n- DMT-BS方法的检测不依赖特定人体模型，可跟踪静态环境中的任何移动物体，适用于工业安全场景。\n- 背景差分采用两阶段更新：对有效像素使用加权平均（小权重a）和快速更新（权重b），对无效像素推回背景；初始化时使用最大深度值。\n- 点云通过外部标定变换到世界坐标系，投影到地面平面（xz平面）生成密度图，每个点贡献其深度的平方以补偿距离导致的密度衰减。\n- 密度图归一化公式为map_norm = map · K · S²/f²，其中K为经验常数，使阈值可设为1.0。\n- 多相机合并采用像素级最大值，可解决单个相机遮挡问题，但必须保持视野重叠因为算法不进行重识别。\n- 斑点分割利用未匹配轨迹的预测位置与斑点的接近度判断合并，并通过欧氏Voronoi划分将合并斑点分配给各轨迹，最小轨迹年龄为1秒（20帧）。\n- 跟踪在二维世界坐标中进行，使用恒速卡尔曼滤波预测，并通过匈牙利算法以欧氏距离作为成本进行匹配。\n- 方法隐含过滤大多数非人类物体：静止物体融入背景、低于1米高度的物体被排除、小物体密度不足以超过阈值。\n- 在KTP、EPFL-LAB和EPFL-CORRIDOR三个数据集上，DMT-BS的MOTA分数均高于DPOM和Kinect SDK，且保持高召回率和高精度。\n- 仿真实验表明，相机角度从10°到80°性能稳定，低于10°时性能下降但仍能处理；增加第二相机显著提升MOTA，第三、四相机增益不大。\n- 深度噪声容忍度达50mm（约为Kinect噪声的10倍），超过后需更换背景差分器（如GMM）才能维持性能。\n- 外部标定旋转误差在1°以内对性能无影响，实际可采用精度优于2mm和0.6°的标定方法。"
}