{
  "paper_id": "9fa57a53cb21192067a3b820d850cdf6",
  "paper_title": "RADHAR: Human Activity Recognition from Point Clouds Generated through a Millimeter-wave Radar",
  "paper_authors": [
    "Akash Deep Singh",
    "Sandeep Singh Sandha",
    "Luis Garcia",
    "Mani Srivastava"
  ],
  "publication_date": "2019-10-25",
  "publication_venue": "3rd ACM Workshop on Millimeter-wave Networks and Sensing Systems (mm-Nets'19)",
  "abstract": "Accurate human activity recognition (HAR) is the key to enable emerging context-aware applications that require an understanding and identification of human behavior, e.g., monitoring disabled or elderly people who live alone. Traditionally, HAR has been implemented either through ambient sensors, e.g., cameras, or through wearable devices, e.g., a smartwatch, with an inertial measurement unit (IMU). The ambient sensing approach is typically more generalizable for different environments as this does not require every user to have a wearable device. However, utilizing a camera in privacy-sensitive areas such as a home may capture superfluous ambient information that a user may not feel comfortable sharing. Radars have been proposed as an alternative modality for coarse-grained activity recognition that captures a minimal subset of the ambient information using micro-Doppler spectrograms. However, training fine-grained, accurate activity classifiers is a challenge as low-cost millimeter-wave (mmWave) radar systems produce sparse and non-uniform point clouds. In this paper, we propose RADHAR, a framework that performs accurate HAR using sparse and non-uniform point clouds. RADHAR utilizes a sliding time window to accumulate point clouds from a mmWave radar and generate a voxelized representation that acts as input to our classifiers. We evaluate RADHAR using a low-cost, commercial, off-the-shelf radar to get sparse point clouds which are less visually compromising. We evaluate and demonstrate our system on a collected human activity dataset with 5 different activities. We compare the accuracy of various classifiers on the dataset and find that the best performing deep learning classifier achieves an accuracy of 90.47%. Our evaluation shows the efficacy of using mmWave radar for accurate HAR detection and we enumerate future research directions in this space.",
  "keywords": [
    "millimeter-wave",
    "mmWave",
    "radar",
    "human activity recognition",
    "machine learning",
    "neural networks",
    "point-clouds",
    "voxelization",
    "RF"
  ],
  "paper_institutions": [
    "University of California, Los Angeles"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:35.670571Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文提出了RADHAR框架，用于基于毫米波雷达产生的稀疏非均匀点云进行人体活动识别（HAR）。传统的环境感知（如摄像头）和可穿戴设备（如智能手表带有IMU）方法存在隐私或不便问题，而雷达作为替代方案，虽然能减少环境信息暴露，但低成本毫米波雷达产生的点云稀疏且不均匀，给精确分类带来挑战。RADHAR采用滑动时间窗口累积点云，并通过体素化处理生成恒定大小的输入表示，以支持后续分类器。我们使用TI的IWR1443BOOST商用雷达收集了包含5种活动的新数据集MMActivity（步行、跳跃、开合跳、深蹲和拳击），共93分钟数据，并按71.6分钟训练/21.4分钟测试划分。在相同的训练测试划分下，评估了SVM、MLP、双向LSTM和时域分布式CNN+双向LSTM等分类器。结果显示，深度学习方法显著优于传统SVM，其中时域分布式CNN+双向LSTM取得了最佳测试准确率90.47%。该结果验证了毫米波雷达用于精确HAR的可行性。未来研究方向包括处理体素表示的高计算开销，以及探索能直接处理点云的神经网络（如PointNet）以改善效率。本工作适用于对隐私敏感的场所（如独居老人监控）等活动识别场景。核心机制涉及体素化处理和滑动时间窗口，以及雷达距离分辨率公式 d_res = c/(2B)，其中带宽越大，距离分辨率越高。\n\n### 关键要点\n- RADHAR框架使用毫米波雷达产生的点云进行人体活动识别，解决了低成本雷达点云稀疏和非均匀的问题。\n- 该方法通过26秒的滑动时间窗口（60帧）累积点云，并将每个点云体素化为 10×32×32 的三维网格，从而生成恒定大小的输入。\n- 收集的新MMActivity数据集包含5种活动（步行、跳跃、开合跳、深蹲、拳击），由2名受试者执行，总计93分钟数据。\n- 实验使用TI IWR1443BOOST雷达，采样率30帧/秒，通过ROS和rosbag记录数据，再转换为体素表示。\n- 输入样本形状为 60×10×32×32（时间×深度×高度×宽度），训练集12097个样本，测试集3538个样本。\n- 比较了SVM、MLP、双向LSTM和时域分布式CNN+双向LSTM，其中SVM需先用PCA降维至6000维（保留80%方差）。\n- 时域分布式CNN+双向LSTM取得了90.47%的测试准确率，优于双向LSTM（88.42%）、MLP（80.34%）和SVM（63.74%）。\n- 深度学习架构中，专门处理空间（CNN）和时间（LSTM）依赖的模型表现更好，表明点云数据中的时空关联对识别至关重要。\n- 体素化表示存在内存和计算开销大的缺点，每个样本需要处理614400维数据，未来可考虑直接处理点云的网络（如PointNet）。\n- 混淆矩阵显示“跳跃”和“拳击”容易与“步行”混淆，可能是由于这些活动在点云特征上的相似性。\n- 使用速度作为体素值（求和）的表示与使用点数计数的表示性能接近，表明两种编码均可用于分类。\n- 该研究为隐私敏感场景（如独居老人监控）提供了可行的活动识别方案，同时为毫米波雷达点云数据在HAR中的应用提供了开源数据集和代码。"
}