[论文解读] DeepCount: Crowd Counting with WiFi via Deep Learning

Shangqing Liu, Yanchao Zhao+3 more|arXiv (Cornell University)|Mar 13, 2019

Indoor and Outdoor Localization Technologies参考文献 30被引用 42

一句话总结

DeepCount 在室内多人与环境中对人群进行计数，使用 WiFi CSI 数据的 CNN-LSTM，并通过在线学习达到约 90% 的准确率。

ABSTRACT

Recently, the research of wireless sensing has achieved more intelligent results, and the intelligent sensing of human location and activity can be realized by means of WiFi devices. However, most of the current human environment perception work is limited to a single person's environment, because the environment in which multiple people exist is more complicated than the environment in which a single person exists. In order to solve the problem of human behavior perception in a multi-human environment, we first proposed a solution to achieve crowd counting (inferred population) using deep learning in a closed environment with WIFI signals - DeepCout, which is the first in a multi-human environment. step. Since the use of WiFi to directly count the crowd is too complicated, we use deep learning to solve this problem, use Convolutional Neural Network(CNN) to automatically extract the relationship between the number of people and the channel, and use Long Short Term Memory(LSTM) to resolve the dependencies of number of people and Channel State Information(CSI) . To overcome the massive labelled data required by deep learning method, we add an online learning mechanism to determine whether or not someone is entering/leaving the room by activity recognition model, so as to correct the deep learning model in the fine-tune stage, which, in turn, reduces the required training data and make our method evolving over time. The system of DeepCount is performed and evaluated on the commercial WiFi devices. By massive training samples, our end-to-end learning approach can achieve an average of 86.4% prediction accuracy in an environment of up to 5 people. Meanwhile, by the amendment mechanism of the activity recognition model to judge door switch to get the variance of crowd to amend deep learning predicted results, the accuracy is up to 90%.

研究动机与目标

• 在使用普及的 WiFi 信号对室内多人员环境中的人群计数进行动机说明。
• 开发一个深度学习模型，将 Channel State Information (CSI) 映射到人群计数。
• 通过活动识别将在线学习整合到模型中，以便随时间进行自适应。
• 在商用 WiFi 硬件上展示系统的可行性，并实现端到端处理。

提出的方法

• 从 5 GHz WiFi 链路的 CSI 幅度和相位，使用 2Tx 和 3Rx 天线来获得 180 条子载波流。
• 对 CSI 进行 Butterworth 滤波、基于 PCA 的降噪（舍弃第一主成分）和中值平滑以进行特征准备。
• 通过离散小波变换（Daubechies D4）提取时域和频域特征，在 128-s 窗口内的 10 个尺度计算能量/方差。
• 使用一个 LSTM 层（64 单元）随后是 CNN 块和全连接层，以软最大输出进行端到端的人群计数，分为 5 个类别。
• 结合在线纠错机制，使用活动识别模型（门/开关事件）在出现不一致时仅重新训练最后一层全连接层。

实验结果

研究问题

• RQ1 CSI-based WiFi 感知是否能够在多人房间内准确估计人数？
• RQ2 深度学习如何利用 CSI 特征将室内动态环境映射到人群计数？
• RQ3 通过活动识别的在线学习是否随着时间推移提高计数准确性？
• RQ4 哪些预处理和特征提取步骤能最好地保留用于人群计数的 CSI 信息？

主要发现

• 在最多 5 个人的环境中，平均计数准确率为 86.4%。
• 使用门进入/退出检测的在线修正机制，准确率提升至 90%。
• 在商业 WiFi 硬件上对系统进行了评估，采样率为 1500 包/秒，带宽为 5 GHz。
• 为活动识别收集了 800 个人活动样本，来自 10 名志愿者执行 8 种活动。
• 该架构将 CNN 用于特征提取、LSTM 用于时序依赖，输入为相位和幅度 CSI。