Speaking of glasses.
@Frangipani & others had posted some info previously that involved Luxottica and Nuance Audio in glasses.
Also about an interview with Steve Brightfield on smart glasses too.
https://www.linkedin.com/posts/edgx-space_happy-to-welcome-edgx-as-a-satsearch-trusted-activity-7330955537976598528-g7I_?utm_source=share&utm_medium=member_ios&rcm=ACoAADXcDGoBrlbyjzyvD2JFuq1hoU6lQFpxvLA Happy to welcome EDGX as a satsearch trusted supplier. Introducing the EDGX DPU, a...
thestockexchange.com.au
Well, Francesca Palermo, Research Principal Investigator at Luxottica will be presenting at Embedded Vision around now on their next product being Ego Vision Devices on smart glasses.
Francesca Palermo, Research Principal Investigator at EssilorLuxottica, presents the “Enabling Ego Vision Applications on Smart Eyewear Devices” tutorial at the May 2025 Embedded Vision Summit. Ego vision technology is revolutionizing the capabilities of smart eyewear, enabling applications that...
www.edge-ai-vision.com
Ego vision technology is revolutionizing the capabilities of smart eyewear, enabling applications that understand user actions, estimate human pose and provide spatial awareness through simultaneous localization and mapping (SLAM). This presentation will dive into the latest advancements in...
embeddedvisionsummit.com
This is a computer vision application obviously and different from the Nuance glasses.
I also believe that Luxottica might be doing the frames for Onsors glasses if correct?
In March this year herself and other authors released a paper titled:
Advancements in Context Recognition for Edge Devices and Smart Eyewear: Sensors and Applications.
Makes for an interesting read through when discussing Arm Cortex M0, M33 and A53 regards to power, processing etc of which we are compatible with.
@Diogenese will probs be able to glean more from the document.
No mention of Akida at this point however under Optimised Algos the below excerpt indicates that exploration of neuromorphic should occur.
I'd expect these sorts of devices would be an excellent fit for something like Akida, TENNs, Pico?
To fully harness the potential of TinyML, future work must focus on designing ultra-efficient algorithms tailored for specific sensor types and exploring energy-efficient hardware accelerators to support TinyML workloads.
Future work should also explore neuromorphic computing and event-driven processing architectures, which mimic biological neural systems to achieve ultra-low power consumption for always-on context recognition. Successfully integrating TinyML into edge devices will be a crucial step toward delivering responsive, personalized, and context-aware functionalities while overcoming the limitations of current edge AI systems.
When I had a look at her background and education she appears no stranger to SNN after studying them as below.
francescapalermo.github.io
- October 2011 - December 2014: B.Sc. in Computer and Automation Engineering, University of Rome “La Sapienza”, Rome, Italy, Italian Mark 95/110, 2010-2014
- Analysis and development of spiking neural network Izhikevich models
Abstract:
Edge devices have garnered significant attention for their ability to process data locally, providing low-latency, context-aware services without the need for extensive reliance on cloud computing. This capability is particularly crucial in context recognition, which enables dynamic adaptation to a user’s real-time environment. Applications range from health monitoring and augmented reality to smart assistance and social interaction analysis. Among edge devices, smart eyewear has emerged as a promising platform for context recognition due to its ability to unobtrusively capture rich, multi-modal sensor data. However, the deployment of context-aware systems on such devices presents unique challenges, including real-time processing, energy efficiency, sensor fusion, and noise management. This manuscript provides a comprehensive survey of context recognition in edge devices, with a specific emphasis on smart eyewear. It reviews the state-of-the-art sensors and applications for context inference. Furthermore, the paper discusses key challenges in achieving reliable, low-latency context recognition while addressing energy and computational constraints. By synthesizing advancements and identifying gaps, this work aims to guide the development of more robust and efficient solutions for context recognition in edge computing
