• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Pattern Recognition Applications and Methods >Activity Recognition for Elderly Care by Evaluating Proximity to Objects and Human Skeleton Data
【24h】

Activity Recognition for Elderly Care by Evaluating Proximity to Objects and Human Skeleton Data

机译：通过评估对象和人体骨架数据的邻近来认识老年人护理

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recently, researchers have shown an increased interest in the detection of activities of daily living (ADLs) for ambient assisted living (AAL) applications. In this study, we present an algorithm that detects activities related to personal hygiene. The approach is based on the evaluation of pose information and a person's proximity to objects belonging to the typical equipment of bathrooms, such as sink, toilet and shower. In addition to this high-level reasoning, we developed a skeleton-based algorithm that recognises actions using a supervised learning model. Therefore, we analysed several feature vectors, especially with regard to the representation of joint trajectories in the frequency domain. The results gave evidence that this high-level reasoning algorithm can reliably recognise hygiene-related activities. An evaluation of the skeleton-based algorithm shows that the defined actions were successfully classified with a rate of 96.66%.
机译：最近，研究人员对对环境辅助生活（AAL）应用的日常生活（ADL）的活动进行了增加的兴趣。在这项研究中，我们提出了一种检测与个人卫生有关的活动的算法。该方法基于对姿势信息的评估和一个人对属于浴室典型设备的物体的邻近的物体，例如水槽，卫生间和淋浴。除了这种高级推理之外，我们还开发了一种基于骨架的算法，可以使用监督学习模型识别动作。因此，我们分析了几个特征向量，特别是关于频域的关节轨迹的表示。结果提出了证据表明这种高级推理算法可以可靠地识别卫生相关的活动。基于骨架的算法的评估表明，定义的动作成功分类，速率为96.66％。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号