{
  "paper_id": "317d3cc81ac42e10420a76ebf8fc81e4",
  "paper_title": "Human Movement Recognition Based on 3D Point Cloud Spatiotemporal Information from Millimeter-Wave Radar",
  "paper_authors": [
    "Xiaochao Dang",
    "Peng Jin",
    "Zhanjun Hao",
    "Wenze Ke",
    "Han Deng",
    "Li Wang"
  ],
  "publication_date": "2023-11-27",
  "publication_venue": "Sensors",
  "abstract": "Human movement recognition is the use of perceptual technology to collect some of the limb or body movements presented. This practice involves the use of wireless signals, processing, and classification to identify some of the regular movements of the human body. It has a wide range of application prospects, including in intelligent pensions, remote health monitoring, and child supervision. Among the traditional human movement recognition methods, the widely used ones are video image-based recognition technology and Wi-Fi-based recognition technology. However, in some dim and imperfect weather environments, it is not easy to maintain a high performance and recognition rate for human movement recognition using video images. There is the problem of a low recognition degree for Wi-Fi recognition of human movement in the case of a complex environment. Most of the previous research on human movement recognition is based on LiDAR perception technology. LiDAR scanning using a three-dimensional static point cloud can only present the point cloud characteristics of static objects; it struggles to reflect all the characteristics of moving objects. In addition, due to its consideration of privacy and security issues, the dynamic millimeter-wave radar point cloud used in the previous study on the existing problems of human body movement recognition performance is better, with the recognition of human movement characteristics in non-line-of-sight situations as well as better protection of people's privacy. In this paper, we propose a human motion feature recognition system (PNHM) based on spatiotemporal information of the 3D point cloud of millimeter-wave radar, design a neural network based on the network PointNet++ in order to effectively recognize human motion features, and study four human motions based on the threshold method. The data set of the four movements of the human body at two angles in two experimental environments was constructed. This paper compares four standard mainstream 3D point cloud human action recognition models for the system. The experimental results show that the recognition accuracy of the human body's when walking upright can reach 94%, the recognition accuracy when moving from squatting to standing can reach 84%, that when moving from standing to sitting can reach 87%, and the recognition accuracy of falling can reach 93%.",
  "keywords": [
    "3D point cloud",
    "millimeter-wave radar",
    "human movement",
    "neural network"
  ],
  "paper_institutions": [
    "College of Computer Science & Engineering, Northwest Normal University"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:46:22.775314Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本文针对传统视频图像识别在昏暗或恶劣天气下性能下降、Wi-Fi感知受距离和多径干扰限制、LiDAR仅能获取静态点云等问题，提出一种基于毫米波雷达三维点云时空信息的人体动作识别系统PNHM。该系统采用IWR6843毫米波雷达收集动态三维点云，通过DBSCAN聚类去噪，利用PointNet++神经网络融合局部与全局特征，并引入高度和速度阈值以区分相似动作。在实验室和走廊两种环境、0°和30°两个角度下构建了包含直立行走、站立到坐下、站立到下蹲和跌倒四种动作的数据集，采集了不同身高、体重、年龄的8名受试者的900组点云数据，按30帧切片输入网络，以3:1划分训练集和测试集。实验结果表明，PNHM在实验室0°场景下对行走、站立到坐下、站立到下蹲和跌倒的识别准确率分别为94%、87%、84%和93%，平均准确率89.5%，优于CNN、LSTM、PointNet+LSTM等主流方法。系统在非视距条件下仍能有效识别，具备较好的隐私保护性和鲁棒性，未来可扩展至多人共存的复杂场景及更多角度。\n\n### 关键要点\n- 本文提出PNHM（PointNet++ Human Motion）方法，基于PointNet++神经网络设计，用于处理毫米波雷达动态三维点云，实现人体动作分类识别。\n- 系统流程包括五步：3D点云数据采集（IWR6843雷达）、DBSCAN聚类去噪、点云聚类、数据切片（每30帧作为输入）以及特征提取与分类。\n- 毫米波雷达具有4 GHz带宽、3.75 cm距离分辨率，可全天候工作，穿透力强，相比视觉和LiDAR更保护隐私。\n- 实验采用IWR6843ISK与DCA1000EVM设备，设置60 GHz频率，每帧最多64个点，共采集1000帧。\n- 在实验室和走廊两种环境下，实验者运动轨迹与雷达信号中心分别成0°和30°角度，采集四种动作：直立行走、站立到坐下、站立到下蹲、跌倒。\n- 数据来自8名受试者（4男4女），身高155-181 cm，体重45-70 kg，年龄22-28岁，保证多样性。\n- 通过速度与高度阈值辅助区分相似动作（如坐下和下蹲），雷达离地2.5 m时，跌倒识别率可达97%，但坐下和下蹲准确率较低。\n- 不同动作设置不同帧率：行走5帧/秒、坐下/站起10帧/秒、下蹲/站起15帧/秒、跌倒20帧/秒。\n- 点云被切片为15、30、45、60、75、90帧进行实验，30帧时分类效果最佳，最终确定30帧作为统一输入。\n- 在实验室0°场景下，PNHM对行走、坐下、下蹲、跌倒的准确率分别为94%、87%、84%、93%，平均89.5%。\n- 与CNN、LSTM、PointNet+LSTM对比，PNHM在实验室0°、走廊0°、实验室30°、走廊30°四个场景的准确率均最高，分别为90.4%、88.6%、85.7%、86.2%。\n- 未知受试者（未参与训练）的识别准确率约87%，表明PNHM具备较强的泛化能力和鲁棒性。",
  "available_templates": [
    "deep_read",
    "simple"
  ]
}