{
  "paper_id": "56cea03fa708a18669688858842e8920",
  "paper_title": "Enhancing Digital Twins with Human Movement Data: A Comparative Study of Lidar-Based Tracking Methods",
  "paper_authors": [
    "Shashank Karki",
    "Thomas J. Pingel",
    "Timothy D. Baird",
    "Addison Flack",
    "Todd Ogle"
  ],
  "publication_date": "2024-09-18",
  "publication_venue": "Remote Sensing",
  "abstract": "Digitals twins, used to represent dynamic environments, require accurate tracking of human movement to enhance their real-world application. This paper contributes to the field by systematically evaluating and comparing pre-existing tracking methods to identify strengths, weaknesses and practical applications within digital twin frameworks. The purpose of this study is to assess the efficacy of existing human movement tracking techniques for digital twins in real world environments, with the goal of improving spatial analysis and interaction within these virtual modes. We compare three approaches using indoor-mounted lidar sensors: (1) a frame-by-frame method deep learning model with convolutional neural networks (CNNs), (2) custom algorithms developed using OpenCV, and (3) the off-the-shelf lidar perception software package Percept version 1.6.3. Of these, the deep learning method performed best (F1 = 0.88), followed by Percept (F1 = 0.61), and finally the custom algorithms using OpenCV (F1 = 0.58). Each method had particular strengths and weaknesses, with OpenCV-based approaches that use frame comparison vulnerable to signal instability that is manifested as \"flickering\" in the dataset. Subsequent analysis of the spatial distribution of error revealed that both the custom algorithms and Percept took longer to acquire an identification, resulting in increased error near doorways. Percept software excelled in scenarios involving stationary individuals. These findings highlight the importance of selecting appropriate tracking methods for specific use. Future work will focus on model optimization, alternative data logging techniques, and innovative approaches to mitigate computational challenges, paving the way for more sophisticated and accessible spatial analysis tools. Integrating complementary sensor types and strategies, such as radar, audio levels, indoor positioning systems (IPSs), and wi-fi data, could further improve detection accuracy and validation while maintaining privacy.",
  "keywords": [
    "terrestrial lidar",
    "indoor geography",
    "deep learning",
    "dynamic digital twins",
    "computer vision",
    "lidar perception",
    "occupancy and movement"
  ],
  "paper_institutions": [
    "Virginia Polytechnic Institute and State University",
    "Binghamton University"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:46:46.364672Z",
  "template_tag": "simple",
  "summary": "### 摘要\n\n本研究旨在评估基于激光雷达（lidar）的人类运动追踪方法在数字孪生框架内的效能，以增强动态环境的空间分析能力。针对室内复杂环境，论文比较了三种方法：基于卷积神经网络（CNN）的逐帧深度学习模型（YOLOv5）、基于OpenCV的自定义算法（背景减除和帧差分）以及商用激光雷达感知软件Percept 1.6.3。实验在新建的混合用途建筑X的一楼公共区域进行，部署11个Blickfeld Cube 1激光雷达传感器，将点云投影为二维光栅图像（同时包含最大高程和强度信息）作为深度学习与OpenCV的输入，而Percept直接处理三维点云。结果表明，深度学习模型在F1分数（0.879）、精确率（0.843）和召回率（0.930）上均表现最佳，其次是Percept（F1=0.606），OpenCV方法表现最差（背景减除F1=0.575，帧差分F1=0.438）。深度学习在准确追踪移动人员方面表现出色，但难以检测静止在家具上的人员；OpenCV受激光雷达光栅化产生的边缘闪烁噪声影响较大；Percept能较好检测静止个体和楼梯上的人员，但误报率较高且计算资源消耗大。各方法的空间误差分布显示，较慢的识别速度导致门口附近误差增加。未来的工作将集中于模型优化、替代数据记录技术以及集成雷达、音频、室内定位系统和Wi-Fi等互补传感器以提升准确性和隐私保护。\n\n### 关键要点\n\n- 论文针对数字孪生中人类运动数据的需求，系统比较了三种基于激光雷达的追踪方法：深度学习（YOLOv5）、OpenCV自定义算法和商用软件Percept。\n- 深度学习模型在三个数据模态（DSM、强度、双波段组合）上表现相近，其中DSM的F1最高（0.879），表明几何信息对检测有利。\n- OpenCV的背景减除方法精确率高（0.858）但召回率低（0.433），帧差分方法两者均较低，整体性能最差。\n- Percept软件在检测静止个体和楼梯上的人员时优于其他方法，但误报率较高，调整后其F1可提升至0.690。\n- 激光雷达数据光栅化产生的边缘闪烁噪声是OpenCV方法性能受限的主要原因，增大光栅网格尺寸或形态学处理无法根本解决。\n- 深度学习方法仅依赖单帧图像，无法利用时间上下文，对静止或部分遮挡目标的检测能力有限。\n- 实验数据来自11个激光雷达传感器，融合为单一三维点云后投影为二维光栅图像，分辨率为5厘米，点密度平均为578点/平方米。\n- 准确性评估使用匈牙利算法匹配检测点与人工标注的地面真值（共3600帧，80%训练20%验证），距离阈值为2米。\n- 各方法在空间热点分布上大致相似，深度学习与Percept显示东北走廊为次要热点，而OpenCV低估了入口附近的活动。\n- 时间模式上，各方法的日均检测趋势一致，但Percept在9月12-13日及下午4-5点存在差异，劳动节周末明显活跃度最低。\n- 未来的混合模型可结合深度学习的帧检测、OpenCV的简单性和Percept的静止目标检测能力，并考虑集成雷达、Wi-Fi等传感器以提高鲁棒性。"
}