3D Tracking via Body Radio Reflections

By Fadel M. Adib, Zachary Kabelac, Dina Katabi, Rob Miller. Symposium on Networked Systems Design and Implementation, 2014

799 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/052b36fd8bde6035c11eb316c3f9a3665c0110f0

How researchers see this paper

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

Citations in the corpus

Widar3.0: Zero-Effort Cross-Domain Gesture Recognition With Wi-Fi (2021, methodology): “On the human side, existing model-based works only tracks coarse human motion status, such as location [21], [28], velocity [17], [20], gait [30], [31] and ﬁgure [24], [32].”
A Survey on Behavior Recognition Using WiFi Channel State Information (2017, methodology): “[7] F.”
Emotion recognition using wireless signals (2016, methodology): “The FMCW radio connects to a computer over Ethernet.”
Wireless Sensing for Human Activity: A Survey (2020, methodology): “…[67]–[71], [84]–[91] FMCW-based Frequency shift associated with human body depth Fine-grained Yes [28], [42]–[44], [55]–[57] [29], [30], [45], [98], [99] Doppler Shift-based Frequency shift associated with human body moving speed Fine-grained Yes [28]–[30], [45], [58]–[66], [92]–[95] WiFi device”
Precise Power Delay Profiling with Commodity Wi-Fi (2015, background): “For example, to detect the existence of human beings [5], to count the number of people moving around [4], to detect human falling down in [3] and recognize different human activities [2], [49], [50], [51].”
Capturing the human figure through a wall (2015, methodology): “Speciﬁcally, either they abstract the whole human body as a single-point reﬂector, which they track [Adib et al. 2014; Adib and Katabi 2013; Seifeldin et al. 2013; Nannuru et al. 2013], or they classify a handful of forward-backward gestures by matching them against prior training examples [Pu et…”
RF-based 3D skeletons (2018, methodology): “Our neural network takes as input the RF signal captured by an FMCW radio similar to the radio used in past work on localization [2].”
Multi-Person Localization via RF Body Reflections (2015, methodology): “Specifically, they either require covering the entire space with a dense, surveyed grid of sensors [18, 7] or they fail in the presence of multiple users in the environment [3].”
Widar: Decimeter-Level Passive Tracking via Velocity Monitoring with Commodity Wi-Fi (2017, background): “Isolating certain reflections can be done in either time domain [9] or frequency domain [1, 2].”
Device-Free Human Activity Recognition Using Commercial WiFi Devices (2017, background): “…much higher bandwidth, e.g. , Frequency Modulated Carrier Wave (FMCW) radar can take up to 1.79 GHz bandwidth [4] while WiFi usually only uses 20 MHz bandwidth, Radar-based systems can extract the micro-Doppler information [25] and have higher distance resolution of approximately 20 cm [4], [5].”
Widar2.0: Passive Human Tracking with a Single Wi-Fi Link (2018, methodology): “To achieve localization in complicated multipath environments indoors, previous works either rely on specialized hardware or software-defined radios [2, 3, 13], rendering them not ubiquitously applicable, or”
Keystroke Recognition Using WiFi Signals (2015, methodology): “proposed WiTrack that uses a specially designed frequency modulated carrier wave radio frontend to track human movements behind a wall [20].”
Cross-Domain WiFi Sensing with Channel State Information: A Survey (2022, methodology): “The former is based on the geometric properties to formulate the trilateration [2] and Fresnel zone models [85], or on the empirical measurements and probability functions of wireless channels to formulate a statistical model [106].”
Smart Homes that Monitor Breathing and Heart Rate (2015, methodology): “Hardware: We reproduced a state-of-the-art FMCW radio designed by past work on wireless localization [6].”
Decimeter-Level Localization with a Single WiFi Access Point (2016, background): “166 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI ’16) USENIX Association ized ultra wideband radios that span multiple GHz [5, 41].”
We Can Hear You with Wi-Fi! (2014, methodology): “(2) How to analyze the tiny radio reflections without any change on current Wi-Fi signals? Recent advances harness customized modulation like Frequency-Modulated Carrier Waves (FMCW) [8].”
WiFall: Device-free fall detection by wireless networks (2017, background): “In [15], the authors introduce WiTrack which can track the 3D motion of a target person.”
Through-Wall Human Pose Estimation Using Radio Signals (2018, background): “Different papers either localize the whole body [5, 23], monitor the person’s walking speed [43, 19], track the chest motion to extract breathing and heartbeats [6, 51, 52], or track the arm motion to identify a particular gesture [32, 26].”
Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi (2019, methodology): “On the signal side, 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],…”