Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a cutting-edge battery-free long-range wireless smart camera for face detection in this 21-minute EMEA tiny Talk. Dive into the world of Edge AI platforms and milliwatt microcontrollers as Michele MAGNO, Head of the Project-based learning Center at ETH Zurich, D-ITET, presents an accurate benchmark. Learn about the challenges and solutions in developing miniaturized IoT smart cameras with limited energy storage and the emerging field of tiny machine learning. Discover how novel hardware architectures and compressed ML algorithms are enabling effective tiny ML systems on resource-constrained microcontrollers. Examine the potential of energy harvesting technology for achieving perpetually powered sensors and the design of a battery-less video sensor node capable of continuous image processing. Gain insights into the implementation of a Tiny ML algorithm for face identification, optimized for low-power microcontrollers, and understand how this innovative camera can operate from a cold start with minimal luminosity.
Syllabus
Intro
The range of cameras
Advantages of edge computing
Next generation IoT
New trend of microcontroller
Overview of microcontrollers
Prototype
Machine Learning
Optimization
Final Network
Benchmark
Why we are interesting
Working camera
Conclusion
Thank you
Setting up the camera
Processor processing
Thanks
Sponsors
Taught by
tinyML