Person tracking and identification using cameras and wi-fi channel state information (CSI) from smartphones

Fang, Shiwei; Munir, Sirajum; Nirjon, Shahriar

doi:10.1145/3419016.3431488

“…WiFi-based solutions have no requirements of LOS thereby enabling larger detection areas. Existing systems, however, are quite coarse [9]. Past systems focus primarily on manually designed features, dependent on prior knowledge and incapable of adequately mining spatiotemporal information in CSI streams [10].…”

Section: Introductionmentioning

confidence: 99%

WiFi-based Spatiotemporal Human Action Perception

Hao¹,

Shi²,

Liu³

2022

Preprint

0

View full text Add to dashboard Cite

WiFi-based sensing for human activity recognition (HAR) has recently become a hot topic as it brings great benefits when compared with video-based HAR, such as eliminating the demands of line-of-sight (LOS) and preserving privacy. Making the WiFi signals to 'see' the action, however, is quite coarse and thus still in its infancy. An end-to-end spatiotemporal WiFi signal neural network (STWNN) is proposed to enable WiFi-only sensing in both line-of-sight and non-lineof-sight scenarios. Especially, the 3D convolution module is able to explore the spatiotemporal continuity of WiFi signals, and the feature self-attention module can explicitly maintain dominant features. In addition, a novel 3D representation for WiFi signals is designed to preserve multi-scale spatiotemporal information. Furthermore, a small wireless-vision dataset (WVAR) is synchronously collected to extend the potential of STWNN to 'see' through occlusions. Quantitative and qualitative results on WVAR and the other three public benchmark datasets demonstrate the effectiveness of our approach on both accuracy and shift consistency.

show abstract

Enhancing Performance in Physical Activity Monitoring: Leveraging Wi-Fi Channel State Information (CSI)

Hosamani,

Yerriswamy

2024

SN COMPUT. SCI.

0

View full text Add to dashboard Cite

WiFi-Based Spatiotemporal Human Action Perception

Hao

¹

,

Shi

²

,

Liu

³

2022

2022 IEEE International Conference on Image Processing (ICIP)

0

View full text Add to dashboard Cite

WiFi-based sensing for human activity recognition (HAR) has recently become a hot topic as it brings great benefits when compared with video-based HAR, such as eliminating the demands of line-of-sight (LOS) and preserving privacy. Making the WiFi signals to 'see' the action, however, is quite coarse and thus still in its infancy. An end-to-end spatiotemporal WiFi signal neural network (STWNN) is proposed to enable WiFi-only sensing in both line-of-sight and non-lineof-sight scenarios. Especially, the 3D convolution module is able to explore the spatiotemporal continuity of WiFi signals, and the feature self-attention module can explicitly maintain dominant features. In addition, a novel 3D representation for WiFi signals is designed to preserve multi-scale spatiotemporal information. Furthermore, a small wireless-vision dataset (WVAR) is synchronously collected to extend the potential of STWNN to 'see' through occlusions. Quantitative and qualitative results on WVAR and the other three public benchmark datasets demonstrate the effectiveness of our approach on both accuracy and shift consistency.

show abstract

Person tracking and identification using cameras and wi-fi channel state information (CSI) from smartphones

Cited by 6 publications

References 13 publications

WiFi-based Spatiotemporal Human Action Perception

WiFi-based Spatiotemporal Human Action Perception

Enhancing Performance in Physical Activity Monitoring: Leveraging Wi-Fi Channel State Information (CSI)

WiFi-Based Spatiotemporal Human Action Perception

Contact Info

Product

Resources

About