Sorry, you need to enable JavaScript to visit this website.

WiFi Action Recognition via Vision based Methods

Citation Author(s):
Kate Ching-Ju Lin, Winston Hsu
Submitted by:
Kuan Ying Lee
Last updated:
24 March 2016 - 12:05pm
Document Type:
Presentation Slides
Document Year:
Jen-Yin Chang, Kuan-Ying Lee
Paper Code:


Action recognition via WiFi has caught intense attention recently because of its ubiquity, low cost, and privacy- preserving. Observing Channel State Information (CSI, a fine-grained information computed from the received WiFi signal) resemblance to texture, we transform the received CSI into images, extract features with vision-based methods and train SVM classifiers for action recognition. Our experiments show that regarding CSI as images achieves an accuracy above 85%. Our contributions include:
• To our best knowledge,we are the first to investigate the feasibility of processing CSI by vision-based methods with extendable learning-based framework.
• We regard CSI of each Tx-Rx pair as a channel and investigate early and late fusion of multi-channels.
• We could know where and what action user performs with location-awareness classification.



WiFi Action Recognition via Vision based Methods.pptx