前言
这篇是无线感知领域必看的经典论文
《WiFi Sensing with Channel State Information:》 A Survey. ACM Comput. Surv. 52, 3
William 之前的SignFi 论文也是非常经典,里面实验细节是见过做的最好的之一。
随着无线数据流量的高需求增长,WiFi网络因其提供高吞吐量和易于部署的特性而迅速发展。最近,WiFi网络测量的信道状态信息(CSI)被广泛用于不同的感知目的。为了更深入地了解现有的WiFi感知技术以及未来的WiFi感知趋势,本调查全面回顾了基于CSI的WiFi感知的信号处理技术、算法、应用和性能结果。不同的WiFi感知算法和信号处理技术各有优缺点,适用于不同的WiFi感知应用
根据输出: 二分类,多分类,数值
本调查将基于CSI的WiFi感知应用分为三类:检测、识别 和 估计。
随着新WiFi技术的发展和部署,WiFi感知将拥有更多机会,其目标可能从人类扩展到环境、动物和物体。本调查强调了WiFi感知面临的三大挑战:鲁棒性和泛化性、隐私和安全以及WiFi感知与网络的共存。最后,本调查提出了三个未来的WiFi感知趋势,即整合跨层网络信息、多设备合作和不同传感器的融合,以增强现有的WiFi感知能力并开启新的WiFi感知机会。
目录:
- 简介
- 相关工作
- 信号处理(
- Python 实现Signal Transform
- 感知算法
- 感知应用
- 挑战和感知趋势
- 结论
一 简介
随着无线设备的日益普及,WiFi迎来了迅猛发展。WiFi成功的一项关键技术是多输入多输出(MIMO),该技术提供高吞吐量,以满足无线数据流量不断增长的需求。MIMO与正交频分复用(OFDM)相结合,在每个载波频率上为每个发射和接收天线对提供信道状态信息(CSI)。最近,来自WiFi系统的CSI测量被用于不同的感知目的。WiFi感知复用无线通信所用的基础设施,因此易于部署且成本低廉。此外,与基于传感器和基于视频的解决方案不同,WiFi感知不具有侵入性,并且对光照条件不敏感。
信道状态信息(CSI)表示在特定载波频率上,无线信号从发射器沿多条路径传播到接收器的过程。对于采用多输入多输出正交频分复用(MIMO-OFDM)技术的WiFi系统而言,CSI是一个由复数构成的3D矩阵,代表了多径WiFi信道的幅度衰减和相位偏移。
一系列CSI测量值捕捉了无线信号在时间、频率和空间域内穿越周围物体和人体的过程,因此可用于不同的无线感知应用。例如,时域中的CSI幅度变化对于不同人类、活动、手势等具有不同的模式,这些模式可用于
1 人类出现侦测
人类出现侦测 |
See ThroughWalls with WiFi |
An Adaptive Wireless Passive Human Detection via Fine-Grained Physical Layer Information |
Channel State Information Based Human Presence Detection Using Non-linear Techniques. |
Enabling Contactless Detection of Moving Humans with Dynamic Speeds Using CSI. |
PADS: Passive Detection of Moving Targets with Dynamic Speed Using PHY Layer Information |
Peripheral【pəˈrɪfərəl】 WiFi Vision: ExploitingMultipath Reflections for More Sensitive Human Sensing |
Non-Invasive Detection of Moving and Stationary Human With WiFi. |
Device-free WiFi Human Sensing: From Pattern-based to Model-based Approaches |
Invisible Cloak Fails: CSI-based Passive Human Detection |
Device-free Presence Detection and Localization With SVM and CSI Fingerprinting |
Omnidirectional Coverage for Device-free Passive Human Detection |
Robust Device-free Through-The- Wall Detection of Moving Human With WiFi |
2 跌倒检测
跌倒检测 |
WiFall: Device-free Fall Detection by Wireless Networks. |
FallDeFi: Ubiquitous Fall Detection Using Commodity Wi-Fi Devices. |
RT-Fall: A Real-Time and Contactless Fall Detection System with Commodity WiFi Devices |
A Statistical Electromagnetic Approach for Device-Free Indoor Speed Estimation. |
A Non-intrusive and Real-Time Fall Detector Leveraging CSI from Commodity WiFi Devices |
3 运动检测
运动检测 |
WiFi-based Real-Time Calibration-Free Passive Human Motion Detection. |
MoSense: An RF-based Motion Detection System via Off-the-Shelf WiFi Devices |
AR-Alarm: An Adaptive and Robust Intrusion Detection System Leveraging CSI from Commodity Wi-Fi. |
A Research on CSI-based Human Motion Detection in Complex Scenarios |
WiStep: Device-free Step Counting with WiFi Signals. |
4 活动识别
活动识别 |
A WiFi based Human Activity Recognition System for Sensorless Environments |
WIBECAM: Device Free Human Activity Recognition Through WiFi Beacon-Enabled Camera. |
WiDriver: Driver Activity Recognition System Based on WiFi CSI. |
BodyScan: Enabling Radio-based Sensing on Wearable Devices for Contactless Activity and Vital Sign Monitoring |
HeadScan: A Wearable System for Radio-based Sensing of Head and Mouth-Related Activities |
MAIS: Multiple Activity Identification System Using Channel State Information of WiFi Signals. |
HuAc: Human Activity Recognition Using Crowdsourced WiFi Signals and Skeleton Data |
< |