Whole-home gesture recognition using wireless signals

@article{Pu2013WholehomeGR,
  title={Whole-home gesture recognition using wireless signals},
  author={Qifan Pu and Sidhant Gupta and Shyamnath Gollakota and Shwetak N. Patel},
  journal={Proceedings of the 19th annual international conference on Mobile computing \& networking},
  year={2013}
}
This paper presents WiSee, a novel gesture recognition system that leverages wireless signals (e.g., Wi-Fi) to enable whole-home sensing and recognition of human gestures. Since wireless signals do not require line-of-sight and can traverse through walls, WiSee can enable whole-home gesture recognition using few wireless sources. Further, it achieves this goal without requiring instrumentation of the human body with sensing devices. We implement a proof-of-concept prototype of WiSee using USRP… 
View on ACM
wisee.cs.washington.edu
914 Citations
Highly Influential Citations
82
Background Citations
485
Methods Citations
195
Results Citations
4

914 Citations

Citation Type

Citation Type

Whole-home gesture recognition using wireless signals (demo)
TLDR
This demo will allow SIGCOMM attendees to control a music player and a lighting control device using gestures and integrate WiSee with applications and demonstrate how WiSee enables users to use gestures and control applications including music players and gaming systems.
Wi-Fi Gesture Recognition on Existing Devices
TLDR
The first wireless gesture recognition system that operates using existing Wi-Fi signals and devices is introduced, and can achieve a classification accuracy of 91% while classifying four gestures across six participants, without the need for per-participant training.
Towards ubiquitous human gestures recognition using wireless networks
TLDR
New preprocessing and filtering techniques are used, new features to be extracted from the data and new classification method that have not been used in this field before are proposed and proved to work well for different humans and different gestures.
Time Reversal Based Robust Gesture Recognition Using Wifi
TLDR
WiGRep is proposed, a time reversal based gesture recognition approach using Wi-Fi, which can recognize different gestures by counting the number of repeating gesture segments, built upon the time reversal phenomenon in RF transmission.
Gesture Recognition Using Wireless Signals
TLDR
Unlike previous works which show the feasibility of wireless systems on detecting coarse motions such as walking or running, WiSee can perform fine-grained gesture classification anywhere in an environment and open up a new viewpoint on how wireless infrastructure today is leveraged.
WiGest: A ubiquitous WiFi-based gesture recognition system
TLDR
This work presents WiGest: a system that leverages changes in WiFi signal strength to sense in-air hand gestures around the user's mobile device, using standard WiFi equipment, with no modifications, and no training for gesture recognition.
A Ubiquitous WiFi-Based Fine-Grained Gesture Recognition System
TLDR
WiGest is a system that leverages changes in WiFi signal strength to sense in-air hand gestures around the user's mobile device, and is robust to the presence of other interfering humans, highlighting WiGest's ability to enable future ubiquitous hands-free gesture-based interaction with mobile devices.
PWiG: A Phase-based Wireless Gesture Recognition System
TLDR
A Phase-based Wireless Gesture recognition system PWiG, an accurate device-free gesture recognition approach that reduces the hardware cost and greatly simplifies the process of the gesture extraction only by calculating the variance values and meets the standard of gesture recognition.
WiGest demo: A ubiquitous WiFi-based gesture recognition system
TLDR
This demo presents WiGest: a system that leverages changes in WiFi signal strength to sense in-air hand gestures around the user's mobile device and builds mutually independent gesture families that can be mapped to distinguishable application actions.
Dynamic gesture recognition using wireless signals with less disturbance
TLDR
A gesture recognition system, which adopts off-the-shelf Wi-Fi devices to collect fine-grained wireless Channel State Information (CSI) and can keep high accuracy even with effects of moving objects.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 38 REFERENCES
SoundWave: using the doppler effect to sense gestures
TLDR
This work presents SoundWave, a technique that leverages the speaker and microphone already embedded in most commodity devices to sense in-air gestures around the device, and describes the phenomena and detection algorithm.
Humantenna: using the body as an antenna for real-time whole-body interaction
TLDR
This paper uses the human body as an antenna for sensing whole-body gestures and shows robust gesture recognition with an average accuracy of 93% across 12 whole- body gestures, and promising results for robust location classification within a building.
Challenges for device-free radio-based activity recognition
TLDR
An overview over the most important works investigating device-free localization and activity recognition and how radio-based activity recognition may profit from the current state of research and which challenges need to be addressed to enable the radio based recognition of activities is given.
Skinput: appropriating the body as an input surface
We present Skinput, a technology that appropriates the human body for acoustic transmission, allowing the skin to be used as an input surface. In particular, we resolve the location of finger taps on…
Through-the-Wall Sensing of Personnel Using Passive Bistatic WiFi Radar at Standoff Distances
TLDR
The results presented show the first through-the-wall (TTW) detections of moving personnel using passive WiFi radar, and it is shown that a new interference suppression technique based on the CLEAN algorithm can improve the SIR by approximately 19 dB.
Human Activity Classification Based on Micro-Doppler Signatures Using a Support Vector Machine
TLDR
The feasibility of classifying different human activities based on micro-Doppler signatures is investigated and the potentials of classify human activities over extended time duration, through wall, and at oblique angles with respect to the radar are investigated and discussed.
Digits: freehand 3D interactions anywhere using a wrist-worn gloveless sensor
TLDR
Digits is a wrist-worn sensor that recovers the full 3D pose of the user's hand, which enables a variety of freehand interactions on the move and is specifically designed to be low-power and easily reproducible using only off-the-shelf hardware.
Indoor localization without the pain
TLDR
Despite the absence of any explicit pre-deployment calibration, EZ yields a median localization error of 2m and 7m in a small building and a large building, which is only somewhat worse than the 0.7m and 4m yielded by the best-performing but calibration-intensive Horus scheme from prior work.
Spot Localization using PHY Layer Information
TLDR
Evidence that channel responses from multiple OFDM subcarriers can be a promising location signature in WiFi systems is found, and PinLoc, a functional system implemented on off-the-shelf Intel 5300 cards, is evaluated.
The magic carpet: physical sensing for immersive environments
TLDR
An interactive environment that uses a pair of Doppler radars to measure upper-body kinematics and a grid of piezoelectric wires hidden under a 6 x 10 foot carpet to monitor dynamic foot position and pressure is developed.
...
1
2
3
4
...