{
  "paper_id": "78dfd8aea569f4929e800e50c0a6980a",
  "paper_title": "Tracking people within groups with RGB-D data",
  "paper_authors": [
    "Matteo Munaro",
    "Filippo Basso",
    "Emanuele Menegatti"
  ],
  "publication_date": "",
  "publication_venue": "2012 IEEE/RSJ International Conference on Intelligent Robots and Systems",
  "abstract": "This paper proposes a very fast and robust multi-people tracking algorithm suitable for mobile platforms equipped with a RGB-D sensor. Our approach features a novel depth-based sub-clustering method explicitly designed for detecting people within groups or near the background and a three-term joint likelihood for limiting drifts and ID switches. Moreover, an online learned appearance classifier is proposed, that robustly specializes on a track while using the other detections as negative examples. Tests have been performed with data acquired from a mobile robot in indoor environments and on a publicly available dataset acquired with three RGB-D sensors and results have been evaluated with the CLEAR MOT metrics. Our method reaches near state of the art performance and very high frame rates in our distributed ROS-based CPU implementation.",
  "keywords": [
    "multi-people tracking",
    "RGB-D",
    "sub-clustering",
    "joint likelihood",
    "online learning",
    "CLEAR MOT"
  ],
  "paper_institutions": [
    "Department of Information Engineering, University of Padova"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:01.724094Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文提出了一种适用于配备RGB-D传感器的移动平台的快速鲁棒多目标跟踪算法。该算法针对群组内或靠近背景的行人检测问题，引入了一种新颖的基于深度的子聚类方法，并设计了三项联合似然函数以减少跟踪漂移和身份切换。此外，提出了一种在线学习的表观分类器，该分类器针对每个轨迹进行鲁棒特化，同时将其他检测用作负样本。实验在移动机器人采集的室内数据和公开的三传感器RGB-D数据集上进行，采用CLEAR MOT指标评估。方法达到了接近当前最优的性能，在分布式ROS CPU实现中获得了较高的帧率。\n\n### 关键要点\n- 提出了一种基于深度子聚类的方法，有效解决了行人密集或靠近背景时的检测问题。\n- 利用高度图检测头部位置，将包含多人的三维簇分割为子簇。\n- 采用三项联合似然（运动、颜色、检测器置信度）进行数据关联，降低漂移和ID切换。\n- 在线Adaboost分类器基于RGB颜色直方图中的随机平行六面体特征，并利用其他检测作为负样本。\n- 使用RANSAC估计地面平面，并实时更新以应对相机运动。\n- 实验采用CLEAR MOT指标（MOTP、MOTA）评估，在移动机器人测试中MOTA达到90.9%以上。\n- 在RGB-D People Dataset上，所提方法MOTA为71.8%，ID切换次数19，低于对比方法的32次。\n- 若不使用子聚类，MOTA下降10%，ID切换增加17次，验证了该方法的有效性。\n- 系统在Intel Xeon处理器上以26fps运行，在Intel i5上以19fps运行，无需GPU。\n- 实际局限：深度传感器有效距离约8米，户外受阳光影响；算法假设行人在地面平面运动。"
}