Human pose estimation using commodity WiFi has been successfully achieved for both 2D and 3D pose reconstruction. However, existing approaches focus on people at a fixed point and are thus inconvenient for daily use, where people move continuously and freely.
Image credit: Mohammed Hassan via Pxhere, CC0 Public Domain
A recent study proposes a system that can capture fine-grained 3D moving human poses with commodity WiFi devices. The processed amplitude and phase are firstly converted into channel state information images. It lets to extract features that contain more pose information but less position component.
A specifically constructed neural network then converts WiFi signals into human poses. A prototype system confirms a significant advantage in accuracy over state-of-the-art methods. The suggested approach uses only six antennas and therefore surpasses existing approaches in both cost and weight.
In this paper, we present Wi-Mose, the first 3D moving human pose estimation system using commodity WiFi. Previous WiFi-based works have achieved 2D and 3D pose estimation. These solutions either capture poses from one perspective or construct poses of people who are at a fixed point, preventing their wide adoption in daily scenarios. To reconstruct 3D poses of people who move throughout the space rather than a fixed point, we fuse the amplitude and phase into Channel State Information (CSI) images which can provide both pose and position information. Besides, we design a neural network to extract features that are only associated with poses from CSI images and then convert the features into key-point coordinates. Experimental results show that Wi-Mose can localize key-point with 29.7mm and 37.8mm Procrustes analysis Mean Per Joint Position Error (P-MPJPE) in the Line of Sight (LoS) and Non-Line of Sight (NLoS) scenarios, respectively, achieving higher performance than the state-of-the-art method. The results indicate that Wi-Mose can capture high-precision 3D human poses throughout the space.