{
  "paper_id": "61bb410e8bb4e383042c97cece61f9bd",
  "paper_title": "A Radar-Based Human Activity Recognition Using a Novel 3-D Point Cloud Classifier",
  "paper_authors": [
    "Zheqi Yu",
    "Ahmad Taha",
    "William Taylor",
    "Adnan Zahid",
    "Khalid Rajab",
    "Hadi Heidari",
    "Muhammad Ali Imran",
    "Qammer H. Abbasi"
  ],
  "publication_date": "",
  "publication_venue": "IEEE Sensors Journal",
  "abstract": "This article provides a new benchmark dataset for 3-D point cloud classification in which the manually labeled human activity data exceeds 100 point clouds per frame and is capable of meeting the training needs for data-intensive learning approaches. In this study, a case study is considered for evaluating the benchmark using a deep long short-term memory (LSTM) neural network, which demonstrated a significant performance improvement over the state-of-the-art human activity recognition (HAR) area. To date, numerous types of collection devices have been used in the recognition of human activities. However, due to the scarcity of training data, the task of 3-D point cloud labeling has not yet made significant progress. To overcome this challenge, it is aimed to deduce this data requirements gap, allowing deep-learning methods to reach their full potential in 3-D point cloud tasks. The dataset used for this process is comprised of dense point clouds acquired with the static ground sensor by the NodeNs company-supported multiple input multiple output (MIMO) radar (NodeNs ZERO 60 GHz IQ radar). It contains multiple types of human being data ranging from one to four individuals and encompasses a range of human action scenarios, including standing, sitting, picking up, falling, and walking. Furthermore, it also investigated sensor locations and requirements for human being data collection that is from a single subject to multiple subjects, as well as identified and analyzed various sensing devices and applications that collect activity data. In this regard, a thorough study is conducted on several benchmark datasets, examining sensors, characteristics, activity categories, and other data. Finally, it compares and analyzes the activity recognition methods used in several benchmark datasets based on the current study. Unlike existing devices, the new NodeNs sensor provides more accessible and straightforward point cloud data to capture human movement information. Depending on an advanced detection algorithm to process point cloud data, it achieved more than 95% accuracy on the benchmark dataset.",
  "keywords": [
    "Benchmark dataset",
    "density-based spatial clustering of applications with noise (DBSCAN)",
    "human activity recognition (HAR)",
    "long short-term memory (LSTM)",
    "NodeNs sensor"
  ],
  "paper_institutions": [
    "University of Glasgow",
    "Queen Mary University of London",
    "NodeNs Medical Ltd."
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:51.090512Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文提出一个用于3D点云分类的新基准数据集，手动标记的人类活动数据超过每帧100个点云，满足数据密集型学习训练需求。该数据集由NodeNs ZERO 60 GHz IQ雷达（MIMO雷达）采集，包含1至4名被试的多种活动（站立、坐下、拾起、跌倒、行走等），样本总数1011个，每个样本时长为5秒。研究采用DBSCAN算法对点云数据进行预处理和聚类，然后使用深度LSTM神经网络进行活动分类，在训练集（80%）和测试集（20%）上评估。实验结果表明，在单人到多人的不同场景下，分类准确率均超过95%，优于现有方法。与已有基准数据集相比，本数据集在规模、类别和分辨率上具有优势，更适用于深度学习算法训练。未来研究可考虑硬件资源消耗（如内存、CPU、传感器数量和电池）以及识别精度与资源使用之间的权衡。该工作为雷达点云HAR提供了新的基准和基线结果。\n\n### 关键要点\n- 提出一个新的3D点云基准数据集，手动标记超过100点云/帧，满足深度学习训练需求。\n- 数据集由NodeNs ZERO 60 GHz IQ雷达（MIMO雷达）采集，包含1-4个被试的多种活动：站立、坐下、拾起、跌倒、行走。\n- 数据分为15个文件夹，共1011个数据文件，每个文件代表一个样本，活动时长固定5秒。\n- 使用DBSCAN进行点云预处理和聚类，参数设置epsilon=0.4，minPoints=1。\n- 使用LSTM神经网络进行活动分类，训练集80%，测试集20%，确保训练和测试来自不同场景。\n- 单人五种活动准确率95.75%，两人三种活动准确率97.59%，三人三种活动准确率98.01%，四人四种活动准确率96.90%。\n- 与现有基准数据集相比，本方法准确率高于基于USRP的92.47%、基于Kinect V2的90.89%等。\n- 讨论了HAR的多种传感技术（可穿戴、雷达、RF、摄像头），本工作聚焦雷达点云。\n- 分析了活动分类中的难点，如静态活动与动态活动，相似姿态转换（坐与站）容易混淆。\n- 文章综述了相关点云处理技术，如PointNet等。\n- 结论：该基准数据集比传统传感器数据更适合深度学习训练，比Lidar设备更高效。\n- 未来研究方向：考虑硬件资源消耗（内存、CPU、传感器数量、电池），以及识别精度与资源使用的权衡。"
}