- Blog, Edge
Edge
Edge
What happens when smart sensors move intelligence to the edge?
What happens when smart sensors move intelligence to the edge?
Not all that long ago deploying a diverse set of sensors was an expensive, often proprietary, commercial endeavor with limited reach. Today, the game has changed and sensor networks have become an increasingly omnipresent part of the world around us.
What does it mean to live, work, and play in an environment that is continually capturing data?
How can Open Source tech innovation help us understand the opportunities…and the risks associated with this new reality?
Dramatic reductions in component costs and ubiquitous access alternative hardware supply chains have catalyzed global DIY community innovation in this space. Anyone with access to Amazon, GitHub, Substack, and perhaps a 3D printer can create integrated systems of low-cost hardware, Open Source software, and lightweight machine learning models to collect a wide range of data.
These may be 80% solutions compared to state-of-the-art commercial products, but they are a fraction of the cost, robust, and increasingly making autonomous decisions about what data is of value – all while unlocking new possibilities of what can be monitored. Cameras can now count objects instead of capturing images. Road sensors can weigh trucks instead of just measuring vibrations. Every signal from a mobile phone can be parsed to the nth degree.
It is an evolution completely transforming the way we measure and understand both ourselves, and the wider world around us. As a team, we are continually exploring the ramifications of this shift in our environment.
Related Content
- Blog, Edge
When using Automatic Identification System (AIS) messages to auto-label data, we encountered several issues. This blog gives a primer on AIS and discusses the various challenges that need to be addressed to make AIS messages viable auto labels.
- Blog, Edge
This is the third post in a blog series detailing the development process of the AI Sonobuoy project by IQT Labs. You can find the first one here and the second one here.
In this blog, we delve further into the evolution of the hardware involved and cover the progression of different iterations of the software which interfaced with each of these stages.
- Blog, Edge
This post is the second blog in an ongoing series by IQT Labs on the AI Sonobuoy project. Please visit the first blog in the series here. As part of our exploration into AI in the maritime domain through this project, we arrived at several mental models that can be broadly applied to AI at the Edge. In true IQT Labs fashion, we are looking to stress test and improve these models, so do come join the conversation and let us know what you think. If you’d like to learn more about current or future Labs projects, or are looking for ways to collaborate, please contact us at info@iqtlabs.org.
- Blog, Edge
This blog kicks off a series of posts around the AI Sonobuoy project by IQT Labs. We discussed the first iteration of this project previously here, and, since then, have rapidly iterated on all parts of the project—including building an automated dataset collection system, creating a machine learning pipeline, and deploying a trained model on a microcontroller.
- Blog, Edge, Home: Position 03
IQT Labs has been experimenting using Raspberry Pi4s and Software Defined Radios (SDR) as an on-the-go platform, through the GamutRF project. Learn how we made GamutRF, running on a Pi4, more responsive and reliable by utilizing the built-in GPU to perform fast Fourier transforms.
- Blog, Edge
What happened when we dropped one of our latest creations out of a boat? Read on to learn about the story of the AI Sonobuoy — a low-cost hydrophone that uses AI to process sound data collected at sea:
- Project
Using low-cost sensors to locate the source of an RF signal
- Edge
These days there are all kinds of invisible signals in the environment around us. If you see a problematic consumer drone in your area, how do you find its operator? In the Birdseye project, we simulated the use of mobile, low-cost sensors to geolocate a moving RF-signal. More specifically, we simulated the collection of RF signals coming off a commercial drone flying overhead to see if we could use it to locate its controller.
- Project
DIY Open Source cell towers for research
- Edge
This project spun up a fully operational 5G mobile phone infrastructure based on Open Source code and low cost commercially available Software Defined Radios and Computers.
- Project
Designing a $100 AI-Enabled Sonobuoy
- Edge
You can now do a lot more with a lot less when it comes to deploying AI systems. Low-power edge inference techniques are fundamentally changing the design of fieldable smart sensors. This project is looking at the evolution of design in AI enabled, acoustic sensors that live at the edge by designing and fielding a smart hydrophone.
- Project
Automatic collection of labeled datasets
- Data, Edge
Quickly and efficiently building and labeling image datasets for machine learning applications can be a prohibitively time-consuming and expensive activity. SkyScan demonstrates a low-cost system that can capture images of aircraft in flight and automatically label the image with captured metadata.
- BLOG
- Edge
Event cameras are like an Etch A Sketch with version control built in. Piqued your interest? This blog details how we investigated and experimented with event cameras.
- BLOG
- Edge
Learn how we developed an Open Source power management system and displayed its practical remote sensing applications in stormy New Zealand weather conditions.
- BLOG
- Edge
Interested in learning how we built our own teachable camera, or perhaps you’re thinking of building your own? This blog details the electronics used and the different hardware configurations we developed and tested to make Teachable Camera possible.
- BLOG
- Edge
Beatrix Potter's The Tale of Peter Rabbit might have turned out differently if Mr. McGregor, the gardener and antagonist in the classic children's book, had employed the technology embodied in the Teachable Camera, a new Open Source computer vision hardware and software kit we created. This blog explores the underlying technology of this kit and uses the story of Peter Rabbit to explain how computer vision and the Teachable Camera can be used to monitor remote locations.
- Git Repo
- Edge
- Git Repo
- Build, Edge
- Git Repo
- Build, Edge
Copyright © 2022 · IQT Labs LLC. All Rights Reserved.
