Abstract
As an essential requirement of pervasive smart devices, free hand gestural input considered as necessary for user interactions has attracted lots of research attention for nearly decades. Nevertheless, existing proposals heavily rely on either expensive pre-deployed equipment or user on-body sensors, thus confine their application scenarios. In this paper, we propose a novel hand gesture recognition system which purely relies on ubiquitous ambient light and low-cost photodiodes. The proposed system does not need any modification to existing lighting infrastructure. While without complex signal pre-processing for modulated light, very low-cost photodiodes and processors can capture and process the light variations caused by hand gesture. To produce accurate hand gesture recognition, we design efficient algorithms based on recurrent neural network to process sensing data collected by a photodiode array. We implement a prototype consisting of an array of 8 photodiodes and extensive experiments demonstrate that the proposed solution can achieve a very high overall recognition accuracy of 99.31%.
Highlights
To seek applicable hand gesture recognition solutions, a lot of researchers from both academic and industrial communities devote to this field, and many methods are proposed
We propose a novel idea of using ambient light for hand gesture recognition, and build a prototype consisting of 8 low cost photodiodes to showcase the feasibility and effectiveness of this lightweight hand gesture recognition approach
We conduct extensive field experiments based on the implemented prototype, and the results show its high accuracy of 99.31% for hand gesture recognition
Summary
To seek applicable hand gesture recognition solutions, a lot of researchers from both academic and industrial communities devote to this field, and many methods are proposed. To release the bottleneck of heavy deployment for both light source of LEDs and massive sensors of photodiodes, in this paper, we propose to use unmodulated ambient light as the sensing medium for hand gesture recognition. To verify our idea of using ambient light for hand gesture recognition, we build a prototype consisting of 8 low cost photodiodes to record the shadow of hand gesture. We propose a novel idea of using ambient light for hand gesture recognition, and build a prototype consisting of 8 low cost photodiodes to showcase the feasibility and effectiveness of this lightweight hand gesture recognition approach. We design a data processing and RNN-based algorithm to map the multi-dimensional sensing data to form the shadow of hand gesture so as to recognize each hand gesture. We conclude this paper in the last section of Section V
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
