Towards 3D human pose construction using wifi
Towards 3D human pose construction using wifi
复制标题
DOI：
10.1145/3372224.3380900
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Wenjun Jiang;Hongfei Xue;Chenglin Miao;Shiyang Wang;Sen Lin;Chong Tian;Srinivasan Murali;Haochen Hu;Zhi Sun;Lu Su
中科院分区：
文献类型：
--
作者：
Wenjun Jiang;Hongfei Xue;Chenglin Miao;Shiyang Wang;Sen Lin;Chong Tian;Srinivasan Murali;Haochen Hu;Zhi Sun;Lu Su
本文介绍了首个使用商用WiFi设备的三维人体姿态构建框架WiPose。通过无处不在的WiFi信号，WiPose可以重建由人体四肢和躯干关节组成的3D骨骼。通过克服传统的基于摄像头的人类感知解决方案所面临的技术挑战，如照明和遮挡，提出的WiFi人类感知技术展示了实现新一代应用的潜力，如医疗保健、辅助生活、游戏和虚拟现实。WiPose基于一种新颖的深度学习模型，可以解决一系列技术挑战。首先，WiPose可以将人体骨骼的先验知识编码到姿态构建过程中，以确保估计的关节满足人体骨骼结构。其次，为了实现跨环境泛化，WiPose将捕获整个三维空间运动的三维速度轮廓作为输入，从而将姿态特定特征与周围环境中的静态物体分离开来。最后，WiPose采用递归神经网络（RNN）和平滑损失来强制生成骨架的平滑运动。我们在具有分布式天线的真实WiFi传感测试平台上的评估结果表明，WiPose可以定位人体骨骼上的每个关节，平均误差为2.83cm，与为专用雷达传感器设计的最先进的姿势构建模型相比，精度提高了35%。
This paper presents WiPose, the first 3D human pose construction framework using commercial WiFi devices. From the pervasive WiFi signals, WiPose can reconstruct 3D skeletons composed of the joints on both limbs and torso of the human body. By overcoming the technical challenges faced by traditional camera-based human perception solutions, such as lighting and occlusion, the proposed WiFi human sensing technique demonstrates the potential to enable a new generation of applications such as health care, assisted living, gaming, and virtual reality. WiPose is based on a novel deep learning model that addresses a series of technical challenges. First, WiPose can encode the prior knowledge of human skeleton into the posture construction process to ensure the estimated joints satisfy the skeletal structure of the human body. Second, to achieve cross environment generalization, WiPose takes as input a 3D velocity profile which can capture the movements of the whole 3D space, and thus separate posture-specific features from the static objects in the ambient environment. Finally, WiPose employs a recurrent neural network (RNN) and a smooth loss to enforce smooth movements of the generated skeletons. Our evaluation results on a real-world WiFi sensing testbed with distributed antennas show that WiPose can localize each joint on the human skeleton with an average error of 2.83cm, achieving a 35% improvement in accuracy over the state-of-the-art posture construction model designed for dedicated radar sensors.