This paper presents a low-complexity motion detection method for outdoor Wi-Fi sensing based on a model-driven approach. The method exploits the structural characteristics of the phase components in channel state information (CSI) for low-multipath propagation environments, which are generally considered disadvantageous for Wi-Fi sensing, to mitigate the phase offset errors originating from wireless devices. In addition, phase averaging provides a processing gain that reduces the random noise components, including quantization and thermal noise. The theoretical basis of the method is described and its effectiveness is experimentally evaluated using Compressed Beamforming frames obtained from commercial IEEE 802.11ac devices. The experiments primarily focus wild crows flying in an outdoor orchard environment. The experimental results demonstrate that the method can detect birds even when they fly several meters away from the direct line-of-sight path between the transmitter and receiver antennas. Furthermore, the results indicated that fluctuations caused by vegetation movement were negligible when the wind speed was less than 3~m/s. The proposed approach is expected to be applicable not only to orchard monitoring but also to other outdoor Wi-Fi sensing applications in low-multipath environments.
DeepAoANet: Learning Angle of Arrival from Software Defined Radios with Deep Neural Networks
University of Oxford(牛津大学)
基于RF信号的测向和定位系统受到多径传播的显著影响,特别是在室内环境中。现有的算法(例如MUSIC)在多径存在下或在弱信号状态下操作时在分辨到达角(AoA)方面表现不佳。我们注意到,数字采样RF前端允许轻松分析信号及其延迟分量。低成本的软件定义无线电(SDR)模块能够在宽频谱范围内提取信道状态信息(CSI),从而推动了增强型到达角(AoA)解决方案的设计。我们提出了一种深度学习方法,从SDR多通道数据的单个快照中获得AoA。我们比较和对比基于深度学习的角度分类和回归模型,以准确估计多达两个AoA。我们已经在不同的平台上实现了推理引擎,以实时提取AoA,证明了我们的方法的计算易处理性。为了证明我们的方法的实用性,我们已经从四元件通用线性阵列(Universal Linear Array,简称UART)中收集了各种视距(LOS)和非视距(NLOS)环境中的IQ(同相和正交分量)样本,并发布了数据集。我们所提出的方法在确定碰撞信号的数量方面表现出良好的可靠性,并且实现了小于$2^{\circ}$的平均绝对AoA误差。