Hardware Podcasts

497: Everyone Likes Tiny

Embedded.fm · 20 Mar 2025 · 1h 24m · Episode 497

AI in practice: one real use of AI described

What this episode covers

Kwabena Agyeman, President and Co-Founder of OpenMV, discusses the launch of two new programmable camera systems, the OpenMV Cam N6 and the OpenMV AE3, via a Kickstarter campaign. He explains how integrating Neural Processing Units (NPUs) and Arm Helium SIMD instructions enables high-performance computer vision and edge AI on microcontrollers, achieving significant speedups while maintaining ultra-low power consumption. Agyeman details the software ecosystem, including MicroPython, TensorFlow Lite for Microcontrollers, and partnerships with Edge Impulse and Roboflow, which simplify model training and deployment for embedded developers.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulationEdge Impulse

Edge Impulse is used in partnership with OpenMV to allow users to create customized AI models using their own data, leveraging the platform's tools for training and deployment.

“And then for training your own models though, we are actually in partnership with Edge Impulse. And another company called "Roboflow," which is a big leader in training AI models. With both of their support, they actually allow you to make customized models using data.”

Kwabena Agyeman · Hear it at 40:16

Most relevant to

early-stage companies

Topics

Mentioned

Companies
OpenMV, Edge Impulse, Roboflow, PixArt Imaging, Alif Semiconductor, Arduino
Products
OpenMV Cam N6, OpenMV AE3, FOMO, YOLO, Prophesee GenX320
Chips
STM32N6, Arm Ethos-U55
Tools
TensorFlow Lite for Microcontrollers, MicroPython
Also
Edge AI Foundation

Related episodes from other shows

Other shows on the same ground, closest first.

  • EE Times Current · 22m

    Embedded World 2023 Recap

    Nitin Dahad, Francoise Pelle, and Sally Ward Foxton of EE Times recap Embedded World 2023, highlighting the shift toward edge AI, tiny ML, and software-defined vehicles. They discuss specific implementations from companies like Renaissance, STMicroelectronics, and Silicon Labs, focusing on running AI models on Cortex-M85 and STM32 microcontrollers with low power consumption. The episode also covers security initiatives from Kudosip and Trust In Software, as well as neuromorphic computing demos from InnerTense and Brain Chip.

    Embedded firmwareSecurity & privacy
    8 chapters

  • The Electromaker Show · 24m

    On the floor of Maker Faire Shenzhen, Neuton.AI on Nordic hardware, Win a HuskyLens2!

    The host discusses Nordic Semiconductor's acquisition of Neuton.AI, highlighting how Neuton's tiny ML models (under 5KB) enable edge AI on microcontrollers like the nRF52 series without cloud dependency. The episode features the HuskyLens2, a Seeed Studio computer vision module with a built-in screen, speaker, and one-button training interface, powered by a Kendryte K53 processor. Finally, the host reflects on Electromaker's coverage of Maker Faire Shenzhen, noting the strong maker community and the pervasive theme of 'AI without Borders'.

    AI & machine learningMicrocontrollers & dev platforms
    1 chapters

  • Coredump Sessions · 58m

    #004: The Future of Edge AI and What it Means for Device Makers

    Alex Samuelson, CTO and co-founder of Imagimob, joins Memfault founders Francois Baldassari and Chris Coleman to discuss the practical implementation of Edge AI on embedded devices. They highlight how hardware accelerators like the Cortex-M55 and U55 have enabled GPU-like performance on microcontrollers, allowing for real-time inference in applications such as welding quality monitoring and fall detection. The conversation emphasizes that data collection, labeling, and memory constraints are the primary bottlenecks, requiring device makers to build data acquisition firmware early in the development process. Finally, they discuss the shift toward 'AI as a Service' business models, where hardware companies generate recurring revenue by updating models over the device's lifecycle.

    AI & machine learningMicrocontrollers & dev platforms
    8 chapters

  • The Electromaker Show · 37m

    Arduino Ventuno Q, Nordic AI and More from Embedded World 2026

    Ian from Electromaker tours Embedded World 2026, highlighting the Arduino Ventuno Q, a Linux single-board computer paired with an STM32 microcontroller for edge AI, and Silicon Labs' Bluetooth channel sounding demo for secure keyless entry. He covers Nordic Semiconductor's in-house Neuton and Axon AI tools for edge inference, alongside their nRF9151 satellite connectivity and fuel gauge software. The episode also features D-Robotics' RDKS 100 robotics platform, Texas Instruments' humanoid robot reference designs, and Epishine's flexible indoor solar energy harvesting technology.

    Microcontrollers & dev platformsAI & machine learning
    1 chapters

  • The Next Byte Podcast · 47m

    244. The Hidden Power of Engineers as Storytellers (with Mouser’s Matt Campbell & Ricky Flores)

    Matt Campbell and Ricky Flores, Technical Marketing Engineers at Mouser Electronics, discuss their transition from traditional engineering roles to customer-facing positions that bridge the gap between semiconductor suppliers and developers. They highlight specific technologies like the STM32N6 microcontroller and the Synaptics Astra 1680 processor, which enable low-cost AI and computer vision projects for makers. The conversation also covers the importance of communication skills for engineers, the 'button renaissance' in hardware design, and Mouser's rapid logistics capabilities, including same-hour shipping and robotic arms.

    Embedded firmwareCareers & education
    10 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Embedded.fm. The episode itself belongs to its publisher.