• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >WiFi and Vision Multimodal Learning for Accurate and Robust Device-Free Human Activity Recognition
【24h】

WiFi and Vision Multimodal Learning for Accurate and Robust Device-Free Human Activity Recognition

机译：WiFi和Vision多模态学习准确和坚固的无设备的人类活动识别

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

摘要

Human activity recognition plays an indispensable role in a myriad of emerging applications in context-aware services. Accurate activity recognition systems usually require the user to carry mobile or wearable devices, which is inconvenient for long term usage. In this paper, we design WiVi, a novel human activity recognition scheme that is able to identify common human activities in an accurate and device-free manner via multimodal machine learning using only commercial WiFi-enabled IoT devices and camera. For sensing using WiFi, a new platform is developed to extract fine-grained WiFi channel information and transform them into WiFi frames. A tailored convolutional neural network model is designed to extract high-level representative features among the WiFi frames in order to provide human activity estimation. We utilized a variant of C3D model for activity sensing using vision. Following this, WiVi performs multimodal fusion at the decision level to combine the strength of WiFi and vision by constructing an ensembled DNN model. Extensive experiments are conducted in an indoor environment, demonstrating that WiVi achieves 97.5% activity recognition accuracy and is robust under unfavorable situations, as each modality provides the complementary sensing when the other faces its limiting conditions.
机译：人类活动识别在情绪感知服务中的无数申请中起着不可或缺的作用。准确的活动识别系统通常要求用户携带移动或可穿戴设备，这对于长期使用不方便。在本文中，我们设计WIVI，一种新颖的人类活动识别方案，可以通过仅使用商业WiFi的物流设备和相机通过多式联机学习以准确和无设备的方式识别普通人类活动。为了使用WiFi进行感测，开发了一个新平台以提取细粒度的WiFi频道信息并将其转换为WiFi帧。定制的卷积神经网络模型旨在提取WiFi帧中的高级代表特征，以提供人类活动估计。我们利用了使用视觉的活性感测的C3D模型的变体。在此之后，WIVI在决策级别执行多模峰融合，以通过构建集成的DNN模型来结合WiFi和视觉的强度。广泛的实验在室内环境进行了广泛的实验，证明WIVI在不利情况下实现了97.5％的活动识别准确性，并且在不利的情况下是强大的，因为每种方式都提供了相互作用的感测，当另一个面临其限制条件时。

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