{
  "paper_id": "91da7a279ec1f1d079b135448fb999e5",
  "paper_title": "Privacy-preserving Pedestrian Tracking using Distributed 3D LiDARs",
  "paper_authors": [
    "Masakazu Ohno",
    "Riki Ukyo",
    "Hamada Rizk",
    "Tatsuya Amano",
    "Hirozumi Yamaguchi"
  ],
  "publication_date": "",
  "publication_venue": "unknown",
  "abstract": "The growing demand for intelligent environments unleashes an extraordinary cycle of privacy-aware applications that makes individuals' life more comfortable and safe. Examples of these applications include pedestrian tracking systems in large areas. Although the ubiquity of camera-based systems, they are not a preferable solution due to the vulnerability of leaking the privacy of pedestrians. In this paper, we introduce a novel privacy-preserving system for pedestrian tracking in smart environments using multiple distributed LiDARs of non-overlapping views. The system is designed to leverage LiDAR devices to track pedestrians in partially covered areas due to practical constraints, e.g., occlusion or cost. Therefore, the system uses the point cloud captured by different LiDARs to extract discriminative features that are used to train a metric learning model for pedestrian matching purposes. To boost the system's robustness, we leverage a probabilistic approach to model and adapt the dynamic mobility patterns of individuals and thus connect their sub-trajectories. We deployed the system in a large-scale testbed with 70 colorless LiDARs and conducted three different experiments. The evaluation result at the entrance hall confirms the system's ability to accurately track the pedestrians with a 0.98 F-measure even with zero-covered areas. This result highlights the promise of the proposed system as the next generation of privacy-preserving tracking means in smart environments.",
  "keywords": [
    "Point cloud-based recognition",
    "LiDAR",
    "Privacy-preserving",
    "Re-ID",
    "Pedestrian tracking"
  ],
  "paper_institutions": [
    "Osaka University",
    "Tanta University"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:13.728762Z",
  "template_tag": "simple",
  "summary": "### 摘要\n该论文针对大型智能环境中利用分布式3D LiDAR进行隐私保护的行人跟踪问题。传统基于RGB摄像头的多摄像头跟踪系统存在泄露行人生物特征（如人脸、肤色、年龄等）的风险，且易受模型反演等攻击。作者提出了一种利用多个非重叠视野的LiDAR传感器进行隐私保护的行人跟踪系统，通过提取点云特征（Fisher Vector）训练深度度量学习模型进行行人再识别，并结合空间（转移矩阵）和时间（旅行时间）特征，采用贝叶斯更新动态调整概率分布。系统部署于一座6层楼建筑内70个无色LiDAR的大型测试平台，进行了三个实验：受控场景（32人）、入口大厅（与RGB方法对比）和长廊（低密度LiDAR）。实验结果表明，在无覆盖区域的情况下，系统在入口大厅达到0.98的F值，在受控场景中特征组合后F值为0.89，验证了系统在隐私与准确率之间的良好权衡。\n\n### 关键要点\n- 该研究首次利用多个分布式3D LiDAR的无色点云进行行人再识别，解决了部分覆盖区域（由于遮挡或成本）导致的多LiDAR行人跟踪难题。\n- 系统采用Fisher Vector将无序、大小不一的点云转换为固定尺寸的判别特征，结合深度度量学习（Triplet loss）计算行人间相似度。\n- 亲和度计算融合三个特征：点云相似度（P1）、空间转移概率（P2）、旅行时间概率（P3），通过匈牙利算法求解全局最优匹配。\n- 空间转移矩阵通过历史直方图更新，旅行时间分布采用贝叶斯公式（逆伽马分布）进行在线更新，以适应移动模式变化。\n- 实验部署在70个LiDAR覆盖6层楼的测试平台，包括Livox Avia和Hokuyo YVT-35LX两种传感器，覆盖不同密度和视野。\n- Experiment-1中，32名受试者行走于4m×7m区域，评估了不同人数（2至32人）和不同时间间隔（5至20秒）下的F值，更新后可达0.89。\n- 单一特征贡献实验中，点云特征P1、空间特征P2、时间特征P3的F值分别为0.74、0.71、0.80，三者组合达到0.89，证明特征融合的有效性。\n- 深度度量学习在测试集上AUC为0.71，同人相似度均值为0.57（标准差0.14），不同人均值为0.02（标准差0.41），区分性较好。\n- Experiment-2中，入口大厅的实测数据（2356条轨迹）达到0.98 F值，优于RGB方法（0.943），且保护隐私。\n- Experiment-3中使用低密度LiDAR（Hokuyo），无法用FV点云特征，改用身高作为替代特征，五天内F值最高达0.80。\n- 系统在部分覆盖（零覆盖）区域仍能保持高准确率，展示了对遮挡和成本约束的鲁棒性，适合大规模智能环境部署。"
}