Widar 3.0: WiFi-based Activity Recognition Dataset

The Widar3.0 project is a large dataset designed for use in WiFi-based hand gesture recognition. The RF data are collected from commodity WiFi NICs in the form of Received Signal Strength Indicator (RSSI) and Channel State Information (CSI). The dataset consists of 258K instances of hand gestures with a duration of totally 8,620 minutes and from 75 domains. In addition, two sophisticated features from raw RF signal, including Doppler Frequency Shift (DFS) and a new feature Body-coordinate Velocity Profile (BVP) are included. More kinds of RF-based activity recognition data (e.g., gait identification, fall detection) are going to come. Please stay tuned for further updates.More details are available at http://tns.thss.tsinghua.edu.cn/widar3.0/. To cite this dataset, the best reference is the paper "Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi" in ACM MobiSys 2019.Widar3.0项目是一款专为基于WiFi的手势识别任务打造的大型数据集。其射频（Radio Frequency, RF）数据采集自商用WiFi网卡，格式为接收信号强度指示（Received Signal Strength Indicator, RSSI）与信道状态信息（Channel State Information, CSI）。该数据集包含25.8万个手势样本，总时长达8620分钟，涵盖75个采集域。此外，数据集还包含两种从原始射频信号中提取的精制特征：多普勒频移（Doppler Frequency Shift, DFS）以及一种全新特征——体坐标速度剖面（Body-coordinate Velocity Profile, BVP）。未来还将推出更多基于射频的行为识别数据（例如步态识别、跌倒检测），敬请关注后续更新。更多详情可访问http://tns.thss.tsinghua.edu.cn/widar3.0/。若需引用该数据集，最佳参考文献为发表于ACM MobiSys 2019的论文《Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi》。

搜集汇总

背景与挑战

背景概述

Widar 3.0是一个大规模基于WiFi的手势识别数据集，包含来自商用WiFi网卡的RSSI和CSI信号，总计258,000个手势实例，覆盖75个域，总时长约8,620分钟。数据集提供了从原始RF信号提取的Doppler Frequency Shift（DFS）和Body-coordinate Velocity Profile（BVP）等高级特征，旨在支持手势识别及其他RF活动识别研究。