Summary of Helios: An Extremely Low Power Event-based Gesture Recognition For Always-on Smart Eyewear, by Prarthana Bhattacharyya et al.
Helios: An extremely low power event-based gesture recognition for always-on smart eyewear
by Prarthana Bhattacharyya, Joshua Mitton, Ryan Page, Owen Morgan, Ben Menzies, Gabriel Homewood, Kemi Jacobs, Paolo Baesso, David Trickett, Chris Mair, Taru Muhonen, Rory Clark, Louis Berridge, Richard Vigars, Iain Wallace
First submitted to arxiv on: 6 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces Helios, an extremely low-power and real-time event-based hand gesture recognition system designed for all-day use on smart eyewear. The authors aim to address the limitations of current human-machine interfaces (HMIs) in smart glasses, which prioritize visual and wearable comfort over functionality. To achieve this, they develop a system that utilizes natural hand interactions for a more intuitive and comfortable user experience. The Helios system consists of an extremely low-power and compact 3mmx4mm/20mW event camera, which outputs are processed by a convolutional neural network (CNN) running on a NXP Nano UltraLite compute platform. The entire system consumes less than 350mW, making it suitable for always-on smart eyewear. The authors demonstrate the capabilities of Helios in recognizing seven classes of gestures, including subtle microgestures like swipes and pinches, with an accuracy rate of 91%. They also show real-time performance across 20 users at a remarkably low latency of 60ms. The results align with positive feedback from user testing and a recent demo at AWE-USA-2024. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Helios is a new system that lets you control smart glasses just by using hand gestures. It’s really low-power, so it won’t drain your battery quickly. The system uses an event camera that can see what’s happening in the world around you and a special kind of computer chip that can process information fast. This means you can use the system to recognize different hand movements, like swiping or pinching, with high accuracy. The authors tested Helios on 20 people and it worked really well. They also showed it off at an event called AWE-USA-2024 and people liked what they saw. |
Keywords
* Artificial intelligence * Cnn * Gesture recognition * Neural network
