File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICIP46576.2022.9897978
- Scopus: eid_2-s2.0-85146677189
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: WIFI-BASED SPATIOTEMPORAL HUMAN ACTION PERCEPTION
Title | WIFI-BASED SPATIOTEMPORAL HUMAN ACTION PERCEPTION |
---|---|
Authors | |
Keywords | 3D spatiotemporal human action recognition WiFi sensing wireless-vision |
Issue Date | 2022 |
Citation | Proceedings - International Conference on Image Processing, ICIP, 2022, p. 3581-3585 How to Cite? |
Abstract | 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-line-of-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. |
Persistent Identifier | http://hdl.handle.net/10722/349846 |
ISSN | 2020 SCImago Journal Rankings: 0.315 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hao, Yanling | - |
dc.contributor.author | Shi, Zhiyuan | - |
dc.contributor.author | Liu, Yuanwei | - |
dc.date.accessioned | 2024-10-17T07:01:18Z | - |
dc.date.available | 2024-10-17T07:01:18Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Proceedings - International Conference on Image Processing, ICIP, 2022, p. 3581-3585 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | http://hdl.handle.net/10722/349846 | - |
dc.description.abstract | 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-line-of-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. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - International Conference on Image Processing, ICIP | - |
dc.subject | 3D spatiotemporal | - |
dc.subject | human action recognition | - |
dc.subject | WiFi sensing | - |
dc.subject | wireless-vision | - |
dc.title | WIFI-BASED SPATIOTEMPORAL HUMAN ACTION PERCEPTION | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICIP46576.2022.9897978 | - |
dc.identifier.scopus | eid_2-s2.0-85146677189 | - |
dc.identifier.spage | 3581 | - |
dc.identifier.epage | 3585 | - |