Capturing Human Pose Using mmWave Radar

Li，Guangzheng; Zhang，Ze; Yang，Hanmei; Pan，Jin; Chen，Dayin; Zhang，Jin

10.1109/PerComWorkshops48775.2020.9156151

2020-03-01

978-1-7281-4717-8

2020 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2020

1-6

23-27 March 2020

Austin, TX, USA

Human pose estimation is an important task. Traditional human pose capturing systems are based on images or videos, which may suffer from bad light and raise the concerns of privacy. In this paper, we proposed an accurate human pose estimation system using the 77GHz millimeter wave radar. It is the first time that people use off-the-shelf millimeter wave radar to complete such a task. Our system requires no camera or specific sensors on the body to estimate the human skeleton. The system first uses two radar data to generate heatmaps and then adopts CNN to transform two-dimensional heatmaps into human pose. We use coordinated heatmaps from radar and visual inputs extracting from camera together to train the designed network. Based on our dataset and system, the proposed method achieves an average OKS value of 0.705 and 0.877 in AP 50.

mmwave radar neural network sensing skeleton

第一

英语

EI

20204109314257

Millimeter waves ; Cameras ; Musculoskeletal system

Biomechanics, Bionics and Biomimetics:461.3 ; Electromagnetic Waves:711 ; Radar Systems and Equipment:716.2 ; Photographic Equipment:742.2

2-s2.0-85092007648

Scopus

Southern University of Science and Technology,China

Li，Guangzheng,Zhang，Ze,Yang，Hanmei,et al. Capturing Human Pose Using mmWave Radar[C],2020:1-6.