[PDF] Enhancing Vital Sign Estimation Performance of FMCW MIMO Radar by Prior Human Shape Recognition-论文阅读讨论-ReadPaper

摘要

Radio technology enabled contact-free human posture and vital sign estimationis promising for health monitoring. Radio systems at millimeter-wave (mmWave)frequencies advantageously bring large bandwidth, multi-antenna array and beamsteering capability. \textit{However}, the human point cloud obtained by mmWaveradar and utilized for posture estimation is likely to be sparse andincomplete. Additionally, human's random body movements deteriorate theestimation of breathing and heart rates, therefore the information of the chestlocation and a narrow radar beam toward the chest are demanded for moreaccurate vital sign estimation. In this paper, we propose a pipeline aiming to enhance the vital signestimation performance of mmWave FMCW MIMO radar. The first step is torecognize human body part and posture, where we exploit a trained ConvolutionalNeural Networks (CNN) to efficiently process the imperfect human form pointcloud. The CNN framework outputs the key point of different body parts, and wastrained by using RGB image reference and Augmentative Ellipse Fitting Algorithm(AEFA). The next step is to utilize the chest information of the priorestimated human posture for vital sign estimation. While CNN is initiallytrained based on the frame-by-frame point clouds of human for postureestimation, the vital signs are extracted through beamforming toward the humanchest. The numerical results show that this spatial filtering improves theestimation of the vital signs in regard to lowering the level of side harmonicsand detecting the harmonics of vital signs efficiently, i.e., peak-to-averagepower ratio in the harmonics of vital signal is improved up to 0.02 and 0.07dBfor the studied cases.

展开全部

图表提取

论文十问

参考文献

被引用

提问与回答

暂无人提供速读十问回答