We can hear you with wi fi

We Can Hear You with Wi-Fi!

WiHear is presented, which enables Wi-Fi signals to “hear” people talks within the radio range without deploying any devices and can simultaneously “ hear’ multiple people’s talks leveraging MIMO technology. Expand

Figures from this paper

412 Citations

We Can «See» You via Wi-Fi — WiFi Action Recognition via Vision-based Methods

A novel de-noising method based on Singular Value Decomposition (SVD) to eliminate the background energy and effectively extract the channel information of signals reflected by human bodies and to minimize the effect of location dependency embedded in CSI. Expand

We Can «See» You via Wi-Fi — An Overview and Beyond

A novel de-noising method based on Singular Value Decomposition (SVD) to eliminate the background energy and effectively extract the channel information of signals reflected by human bodies is proposed. Expand

Wi-Fi Radar: Recognizing Human Behavior with Commodity Wi-Fi

This article provides a guide to and introduces the impressive landscape of this new realm of Wi-Fi, which is tremendously expanding the boundaries ofWi-Fi to a new realm and triggering revolutionary applications in the context of the Internet of Things. Expand

Investigation on Unauthorized Human Activity Watching Through Leveraging Wi-Fi Signals

This paper studies the study of watching human activities through leveraging Wi-Fi signals and discusses a few application prototypes used to detect, track, and identify any moving objects, including those behind obstacles using multiple-input Multiple-output (MIMO) technology. Expand

WiRIM: Resolution Improving Mechanism for Human Sensing With Commodity Wi-Fi

This paper designs a channel switching and aggregation algorithm to extend the effective bandwidth of commodity Wi-Fi signals and improve the performance and efficiency of human sensing applications and proposes a cross-location human activity recognition scenario. Expand

Device-Free Passive Human Detection Using Wi-Fi Technology: Current State and Future Trend

This paper describes the Wi-Fi signal features that are frequently used for device-free detection of human mobility in indoor environments, including RSSI, CSI and TOF, and separates existing work according to these wireless signal features. Expand

Wi-Run: Multi-Runner Step Estimation Using Commodity Wi-Fi

Wi-Run is a multi-runner step estimation system with only one pair of commodity Wi-Fi devices, which has limited number of antennas and bandwidth and the peak detection method is adopted to estimate steps for each runner without introducing extra overhead. Expand

WiFinger: talk to your smart devices with finger-grained gesture

WiFinger is deigned to recognize a set of finger-grained gestures, which are further used to realize continuous text input in off-the-shelf WiFi devices, and achieves up to 90.4% average classification accuracy for recognizing 9 digits finger- grained gestures from American Sign Language (ASL). Expand

Context-Free Fine-Grained Motion Sensing Using WiFi

WiTalk is proposed, a new fine-grained human motion sensing technique with the distinct context-free character that can be used to profile human motion using CSI, which generates CSI spectrograms using signal processing techniques and extracts features by calculating the contours of the CSISpectrograms. Expand

FreeSense: human-behavior understanding using Wi-Fi signals

A new method for human detection with high robustness and a novel approach for indoor human identification based on Wi-Fi Channel State Information (CSI) signals are proposed, using a combination of Principal Component Analysis, Discrete Wavelet Transform and Dynamic Time Warping techniques. Expand

71 References

See through walls with WiFi!

This paper shows how one can track a human by treating the motion of a human body as an antenna array and tracking the resulting RF beam, and shows how to use MIMO interference nulling to eliminate reflections off static objects and focus the receiver on a moving target. Expand

FIMD: Fine-grained Device-free Motion Detection

This paper presents an Indoor device-free Motion Detection system (FIMD), designed based on the insight that CSI maintains temporal stability in static environment, while exhibits burst patterns when motion takes place and uses a novel feature extracted from CSI to leverage its temporal stability and frequency diversity. Expand

Источник

WiHear — We Can Hear You with Wi-Fi!

The impact of wink (as denoted in the dashed red box).

• Filtering Out-Band Interference

• Partial Multipath Removal

•Mouth Motion Profile Construction

• Discrete Wavelet Packet Decomposition

Partial Multipath Removal•Mouth movement: Non-rigid

• Covert CSI (Channel State Information) from frequency domain to time domain via IFFT

•Multipath removal threshold: >500 ns

The multipath threshold value can be adjusted to achieve better performance

• Filtering Out-Band Interference

• Partial Multipath Removal

•Mouth Motion Profile Construction

• Discrete Wavelet Packet Decomposition

• Filtering Out-Band Interference

• Partial Multipath Removal

•Mouth Motion Profile Construction

• Discrete Wavelet Packet Decomposition

Discrete Wavelet Packet Decomposition• A Symlet wavelet filter of order 4 is selected

Classification & Error Correction

Learning-based Lip Reading

Vows and consonants Filtering

Partial Multipath Removal

• Context-based Error Correction

• Context-based Error Correction

• Inter word segmentationSilent interval between words

• Inner word segmentation Words are divided into phonetic events

• Context-based Error Correction

Feature Extraction• Multi-Cluster/Class Feature Selection (MCFS) scheme

• Context-based Error Correction

• Context-based Error Correction

Extending To Multiple Targets

•MIMO: Spatial diversity via multiple Rx antennas

• ZigZag decoding: a single Rx antenna

Floor plan of the testing environment. Experimental scenarios layouts. (a) line of sight; (b) non-line-of-sight; (c) through wall Tx side; (d) through wall Rx side; (e) multiple Rx; (f) multiple link pairs.

• Syllables: [æ], [e], [i], [u], [s], [l], [m], [h], [v], [ɔ], [w], [b], [j], [ ʃ ].

•Words: see, good, how, are, you, fine, look, open, is, the, door,

thank, boy, any, show, dog, bird, cat, zoo, yes, meet, some, watch, horse, sing, play, dance, lady, ride, today, like, he, she.

Automatic Segmentation Accuracy

Automatic segmentation accuracy for (a) Inner-word segmentation

on commercial devices (b) Inter-word segmentation on commercial devices (c) Inner-word segmentation on USRP(d) Inter-word segmentation on USRP

Impact of Context-based Error Correction

Performance with Multiple Receivers

Example of different views for pronouncing words

Performance for Multiple Targets

Performance of multiple users with multiple link pairs.

Performance of zigzag decoding for multiple users.

Performance of two through wall scenarios. Performance of through wall with multiple Rx.

Resistance to Environmental Dynamics

Waveform of a 4-word sentence without interference of ISM band signals or irrelevant human motions

Impact of irrelevant human movements interference

Impact of ISM band interference

• WiHear is the 1st prototype in the world, trying to use Wi-Fi signal to sense and recognize human talks.

• WiHear takes the 1st step to bridge communication between human speaking and wireless signals.

• WiHear introduces a new way so that machine can sense more complicated human behaviors (e.g. mood).

Thank you for your listening !

WiHearWe Can Hear You With Wi-Fi !

Источник

We Can Hear You with Wi-Fi!

WiHear is presented, which enables Wi-Fi signals to “hear” people talks within the radio range without deploying any devices and can simultaneously “ hear’ multiple people’s talks leveraging MIMO technology. Expand

Figures from this paper

412 Citations

We Can «See» You via Wi-Fi — WiFi Action Recognition via Vision-based Methods

A novel de-noising method based on Singular Value Decomposition (SVD) to eliminate the background energy and effectively extract the channel information of signals reflected by human bodies and to minimize the effect of location dependency embedded in CSI. Expand

We Can «See» You via Wi-Fi — An Overview and Beyond

A novel de-noising method based on Singular Value Decomposition (SVD) to eliminate the background energy and effectively extract the channel information of signals reflected by human bodies is proposed. Expand

Wi-Fi Radar: Recognizing Human Behavior with Commodity Wi-Fi

This article provides a guide to and introduces the impressive landscape of this new realm of Wi-Fi, which is tremendously expanding the boundaries ofWi-Fi to a new realm and triggering revolutionary applications in the context of the Internet of Things. Expand

Investigation on Unauthorized Human Activity Watching Through Leveraging Wi-Fi Signals

This paper studies the study of watching human activities through leveraging Wi-Fi signals and discusses a few application prototypes used to detect, track, and identify any moving objects, including those behind obstacles using multiple-input Multiple-output (MIMO) technology. Expand

WiRIM: Resolution Improving Mechanism for Human Sensing With Commodity Wi-Fi

This paper designs a channel switching and aggregation algorithm to extend the effective bandwidth of commodity Wi-Fi signals and improve the performance and efficiency of human sensing applications and proposes a cross-location human activity recognition scenario. Expand

Device-Free Passive Human Detection Using Wi-Fi Technology: Current State and Future Trend

This paper describes the Wi-Fi signal features that are frequently used for device-free detection of human mobility in indoor environments, including RSSI, CSI and TOF, and separates existing work according to these wireless signal features. Expand

Wi-Run: Multi-Runner Step Estimation Using Commodity Wi-Fi

Wi-Run is a multi-runner step estimation system with only one pair of commodity Wi-Fi devices, which has limited number of antennas and bandwidth and the peak detection method is adopted to estimate steps for each runner without introducing extra overhead. Expand

WiFinger: talk to your smart devices with finger-grained gesture

WiFinger is deigned to recognize a set of finger-grained gestures, which are further used to realize continuous text input in off-the-shelf WiFi devices, and achieves up to 90.4% average classification accuracy for recognizing 9 digits finger- grained gestures from American Sign Language (ASL). Expand

Context-Free Fine-Grained Motion Sensing Using WiFi

WiTalk is proposed, a new fine-grained human motion sensing technique with the distinct context-free character that can be used to profile human motion using CSI, which generates CSI spectrograms using signal processing techniques and extracts features by calculating the contours of the CSISpectrograms. Expand

FreeSense: human-behavior understanding using Wi-Fi signals

A new method for human detection with high robustness and a novel approach for indoor human identification based on Wi-Fi Channel State Information (CSI) signals are proposed, using a combination of Principal Component Analysis, Discrete Wavelet Transform and Dynamic Time Warping techniques. Expand

71 References

See through walls with WiFi!

This paper shows how one can track a human by treating the motion of a human body as an antenna array and tracking the resulting RF beam, and shows how to use MIMO interference nulling to eliminate reflections off static objects and focus the receiver on a moving target. Expand

FIMD: Fine-grained Device-free Motion Detection

This paper presents an Indoor device-free Motion Detection system (FIMD), designed based on the insight that CSI maintains temporal stability in static environment, while exhibits burst patterns when motion takes place and uses a novel feature extracted from CSI to leverage its temporal stability and frequency diversity. Expand

Источник