Capturing the human figure through a wall

By Fadel M. Adib, Chen-Yu Hsu, Hongzi Mao, Dina Katabi, Frédo Durand. ACM Transactions on Graphics, 2015

457 citations recorded by the source corpus.

We present RF-Capture, a system that captures the human figure -- i.e., a coarse skeleton -- through a wall. RF-Capture tracks the 3D positions of a person's limbs and body parts even when the person is fully occluded from its sensor, and does so without placing any markers on the subject's body. In designing RF-Capture, we built on recent advances in wireless research, which have shown that certain radio frequency (RF) signals can traverse walls and reflect off the human body, allowing for the detection of human motion through walls. In contrast to these past systems which abstract the entire human body as a single point and find the overall location of that point through walls, we show how we can reconstruct various human body parts and stitch them together to capture the human figure. We built a prototype of RF-Capture and tested it on 15 subjects. Our results show that the system can capture a representative human figure through walls and use it to distinguish between various users.

Subfields: Biomedical Engineering, Electrical and Electronic Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2b2d03f8b96aa1e306fb941e0318d403efbde4be

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Electrical and Electronic Engineering

In Signal Processing

Citations in the corpus

Wireless Sensing for Human Activity: A Survey (2020, unknown): “For instance, the researchers utilize FMCW signals generated by USRP software radio with directional antennas to capture human figure through a wall [103], track user’s 3D motion [28], estimate gait velocity and stride length [104], detect vital signs [56], monitor sleep and insomnia [105], and reco”
Widar3.0: Zero-Effort Cross-Domain Gesture Recognition With Wi-Fi (2021, methodology): “[28], velocity [17], [20], gait [30], [31] and figure [24], [32].”
Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi (2019, methodology): “…existing approaches extract various parameters of signals reflected or shadowed by human, including DFS [26, 32, 44], ToF [2–4, 21], AoA / AoD [2 , On the human side, existing model-based works only tracks coarse human motion status, such as location [4, 41], velocity [26, 32], gait [43, 49]…”
Gait recognition using wifi signals (2016, methodology): “used FMCW Radar to capture a human figure behind the wall and to identify the user with an accuracy of 88% over 15 human subjects [1].”
An Introduction to Deep Learning for the Physical Layer (2017, background): “New applications outside the traditional scope of communications, such as tracking and identification of humans (through walls) [65] as well as gesture and emotion recognition [66], could be achieved using ML on radio signals.”
mm-Pose: Real-Time Human Skeletal Posture Estimation Using mmWave Radars and CNNs (2019, unknown): “stitching the identified parts to reconstruct a human figure [27].”
RF-based 3D skeletons (2018, methodology): “RF-Pose3D uses a multi-antenna FMCW radio similar to the one used in [1].”
Towards 3D human pose construction using wifi (2020, background): “Among them, RFCapture [4] demonstrates that by using RF signal, a coarse description of human body can be generated even through a wall.”
Through-Wall Human Pose Estimation Using Radio Signals (2018, methodology): “The resolution is typically tens of centimeters [5, 2, 4], and is defined by the bandwidth of the FMCW signal and the aperture of the antenna array.”
Gesture recognition for human-robot collaboration: A review (2017, methodology): “A recent discovery from MIT introduced WiTrack and RF-Capture system that captures user motion by radio frequency signals re ﬂ ected from human body (Adib et al., 2014, 2015; Adib and Katabi, 2013).”
Interacting with Soli: Exploring Fine-Grained Dynamic Gesture Recognition in the Radio-Frequency Spectrum (2016, background): “While we have not explored this in-depth we would like to highlight the similarities to recent work exploiting FMCW RF technology to coarsely ‘image’ users through a wall [1].”