{
  "paper_id": "0d59ae49005533118b0dd94a2b9a7ed0",
  "paper_title": "Mobility Assessment of Demented People Using Pose Estimation and Movement Detection An Experimental Study in the Field of Ambient Assisted Living",
  "paper_authors": [
    "Julia Richter",
    "Christian Wiede",
    "Gangolf Hirtz"
  ],
  "publication_date": "",
  "publication_venue": "Proceedings of the International Conference on Pattern Recognition Applications and Methods",
  "abstract": "The European population will steadily be growing older in the following decades. At the same time, the risk of getting dementia increases with higher age. Both these factors are apt to cause serious problems for the society, especially with regard to the caring sector, which also suffers from the lack of qualified personnel. As technical support systems can be of assistance to medical staff and patients, a mobility assessment system for demented people is presented in this paper. The grade of mobility is measured by means of the person's pose and movements in a monitored area. For this purpose, pose estimation and movement detection algorithms have been developed. These process 3-D data, which are provided by an optical stereo sensor installed in a living environment. In order to train and test a discriminative classifier a variety of labelled training and test data was recorded. Moreover, we designed a discriminative and universal feature vector for pose estimation. The experiments demonstrated that the algorithms work robustly. In connection with a human machine interface, the system facilitates a mobilisation as well as a more valid assessment of the patient's medical condition than it is presently the case.",
  "keywords": [
    "Pose Estimation",
    "Stereo Vision",
    "Image Understanding",
    "Video Analysis",
    "3-D Image Processing",
    "Machine Learning",
    "Support Vector Machine",
    "Ambient Assisted Living"
  ],
  "paper_institutions": [
    "Chemnitz University of Technology"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:47:14.161515Z",
  "template_tag": "simple",
  "summary": "### 摘要\n本论文针对痴呆症患者活动能力评估问题，提出一种基于姿态估计和运动检测的辅助生活系统。欧洲人口老龄化加剧，痴呆症患者增多，护理人员短缺，而传统评估依赖不定期检查，结果受患者当日状态影响且不可靠。相关工作包括ADL检测、跌倒检测等，但缺少对姿态和运动的综合评估。本方案采用安装在天花板的宽视角立体相机，获取3D点云，首先通过混合高斯背景建模和前景投影定位人物，然后利用滑动窗口和阈值（如距离阈值X=500mm）检测运动，并通过状态机抑制抖动。姿态估计方面，提取人物点云，设计基于20个垂直bin的特征向量（每个bin高度110mm），使用线性支持向量机（SVM）进行分类（站立、坐、躺）。实验在实验室公寓和不同环境设置下进行，训练数据包含约3000张标注图像，测试共2958个样本。结果表明，姿态分类准确率较高（站立、坐、躺的多数类别达97%以上），运动检测的真阳性率为96.6%。系统通过人机界面（平板、电视等）提供提醒和统计，帮助医护人员评估护理需求。未来工作包括动作识别、长期现场试验和优化界面。核心机制为：通过立体相机获取3D世界坐标，利用高斯混合模型提取前景，再通过特征向量和SVM进行姿态分类。\n### 关键要点\n- 本系统利用单个立体相机（非Kinect）以避免视野、分辨率和相互干扰问题，适合AAL环境。\n- 人物定位采用混合高斯背景建模于世界z-map，并投影到虚拟俯视图确定中心点和包围盒。\n- 运动检测基于滑动窗口（5帧），累加帧间距离，设置高阈值600mm和低阈值400mm形成迟滞，防止振荡。\n- 姿态估计第一步从点云中提取属于人物的点，通过包围盒和前景掩码过滤，并利用坐标变换提高效率。\n- 特征向量由点云按z轴分成20个垂直bin（每个110mm），统计各bin点数并归一化。\n- 选用线性SVM原因：在训练数据有限时性能优异，且是判别式最大间隔分类器。\n- 训练数据来自3人（P3、P4、P7）在实验室公寓录制的约3000张标注图像。\n- 测试场景一为实验室公寓的两名老年人（P1、P2），场景二为不同环境下的4人（P3-P6），其中P3、P4参与过训练。\n- 姿态分类结果：在实验室场景中站立和坐的准确率100%，躺为93.5%；在场景二中除一处躺误判为站（2.4%）和一处躺误判为坐（1%）外，其余均高。\n- 躺的误判率高因点云稀疏和噪声，源于人物位置离传感器较远，立体匹配达到极限。\n- 运动检测TPR=96.6%（288/298），表明能可靠检测跨房间等显著移动。\n- 系统通过人机界面（平板、电视）在检测到长时间不活动时显示提醒，并可查看月度姿势和运动图表。",
  "available_templates": [
    "deep_read",
    "simple"
  ]
}