Wi-GC: A Deep Spatiotemporal Gesture Recognition Method Based on Wi-Fi Signal

Abstract

Wireless sensing has been increasingly used in smart homes, human–computer interaction and other fields due to its comprehensive coverage, non-contact and absence of privacy leakage. However, most existing methods are based on the amplitude or phase of the Wi-Fi signal to recognize gestures, which provides insufficient recognition accuracy. To solve this problem, we have designed a deep spatiotemporal gesture recognition method based on Wi-Fi signals, namely Wi-GC. The gesture-sensitive antennas are selected first and the fixed antennas are denoised and smoothed using a combined filter. The consecutive gestures are then segmented using a time series difference algorithm. The segmented gesture data is fed into our proposed RAGRU model, where BAGRU extracts temporal features of Channel State Information (CSI) sequences and RNet18 extracts spatial features of CSI amplitudes. In addition, to pick out essential gesture features, we introduce an attention mechanism. Finally, the extracted spatial and temporal characteristics are fused and input into softmax for classification. We have extensively and thoroughly verified the Wi-GC method in a natural environment and the average gesture recognition rate of the Wi-GC way is between 92–95.6%, which has strong robustness.

Advancements in UWB-Based Human Motion Detection Through Wall: A Comprehensive Analysis

“…Complementing these developments, Artit Rittiplang and Pattarapong Phasukkit [27] introduced a through-wall Sband UWB radar with a switched antenna array, focusing on detecting stationary subjects via respiration analysis. Despite its effectiveness, this system lacks specific functionalities required for comprehensive rescue operations in disaster scenarios, highlighting the potential for further advancements in emergency response technologies.Zhang, Z., et al [48] proposed an innovative way through the development of TwSense to develop an innovative Through-the-wall detection system with a commercial Wi-Fi device. It had features different from traditional means and concentrated on alleviating the efficiency and robustness of detection.…”

“…Mitigating these strong backscattered signals is crucial to enhance detection accuracy. 6) TwSense Model Limitations ( [48]): The TwSense model, while innovative, required a comprehensive validation of the through-the-wall condition to discern human body breathing patterns. This posed a significant challenge in distinguishing between stationary and unoccupied states of individuals.…”

Static Hand Gesture Recognition Based on Millimeter-Wave Near-Field FMCW-SAR Imaging

“…The authors of [19] designed a deep spatio-temporal gesture recognition method based on Wi-Fi signals, which segments continuous gestures using a time series differencing algorithm and achieved the goal of dynamic gesture recognition. The authors of [20] proposed a two-stage radio frequency algorithm for dynamic gesture classification by segmenting continuous Wi-Fi packets into gesture instances based on time stamps attached to CSI values.…”