Affiliation:
1. National Engineering ResearchCenter for Big Data Technology and System, Services Computing Technology and System Lab, Clusterand Grid Computing Lab, School of Computer Science and Technology, Huazhong Universityof Science and Technology 1037 Luoyu Road, Wuhan, Hubei, China
2. McMaster University Hamilton, Ontario, Canada
3. The Hong Kong Polytechnic University kowloon, Hong Kong, China
Abstract
In the last decade, many studies have significantly pushed the limits of
wireless device-free human sensing
(WDHS) technology and facilitated various applications, ranging from activity identification to vital sign monitoring. This survey presents a novel taxonomy that classifies the state-of-the-art WDHS systems into 11 categories according to their
sensing task type
and motion
granularity
. In particular, existing WDHS systems involve three primary sensing task types. The first type,
behavior recognition
, is a classification problem of recognizing predefined meaningful behaviors. The second type is
movement tracking
, monitoring the quantitative values of behavior states integrating with spatiotemporal information. The third type,
user identification
, leverages the unique features in behaviors to identify who performs the movements. The selected papers in each sensing task type can be further divided into sub-categories according to their motion granularity. Recent advances reveal that WDHS systems within a particular granularity follow similar challenges and design principles. For example, fine-grained hand recognition systems target extracting subtle motion-induced signal changes from the noisy signal responses, and their sensing areas are limited to a relatively small range. Coarse-grained activity identification systems need to overcome the interference of other moving objects within the room-level sensing range. A novel research framework is proposed to help to summarize WDHS systems from methodology, evaluation performance, and design goals. Finally, we conclude with several open issues and present the future research directions from the perspectives of
data collection
,
sensing methodology
,
performance evaluation
, and
application scenario
.
Funder
Technology Innovation Project of Hubei Province of China
Key Research and Development Program of Hubei
Publisher
Association for Computing Machinery (ACM)
Subject
General Computer Science,Theoretical Computer Science
Reference124 articles.
1. WiGest: A ubiquitous WiFi-based gesture recognition system
2. Fadel Adib, Zachary Kabelac, and Dina Katabi. 2015. Multi-person localization via RF body reflections. In Proceedings of the 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI’15). USENIX, 279–292.
3. Fadel Adib, Zach Kabelac, Dina Katabi, and Robert C. Miller. 2014. 3D tracking via body radio reflections. In Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI’14). USENIX, 317–329.
4. Smart Homes that Monitor Breathing and Heart Rate
5. Vid2Doppler: Synthesizing Doppler Radar Data from Videos for Training Privacy-Preserving Activity Recognition
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献