Embedded.fm · 24 Aug 2017 · 1h 11m · Episode 212
Kwabena Agyeman, co-founder of OpenMV, explains how his OpenMV Cam simplifies embedded computer vision by wrapping complex algorithms like April Tags and barcode detection into single MicroPython function calls. He details the hardware choice of an STM32 Cortex-M7 processor, which offers high-speed internal memory access, and discusses the software architecture that allows users to write simple Python code while the underlying C firmware handles heavy lifting. Agyeman also describes the development of a cross-platform IDE using Qt to solve deployment headaches, and shares insights on managing early-stage production, pricing strategies, and the challenges of supporting counterfeiters while maintaining an open-source hardware business.
early-stage companies
Other shows on the same ground, closest first.
Hackaday editors Mike Fish and Elliot Williams discuss the OSIRIS-REx asteroid sample return, the new Raspberry Pi Compute Module 4, and a DIY Linux single-board computer shootout by Jay Carlson. They also cover a motorized HDMI CEC volume control for a vintage receiver, a 3D-printed SCARA robot arm, and a deep dive into fake and clone STM32 'Blue Pill' microcontrollers.
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.
James Adams, Liam Fraser, and Luke Renn from Raspberry Pi Trading discuss the development of the RP2040 microcontroller and the Pico board. They explain the architectural decisions behind the chip, including the use of programmable IO (PIO) state machines, the choice of Cortex-M0+ cores, and the strategic decision to use external flash to maximize SRAM and minimize cost. The conversation also covers the company's flat engineering culture, their low-cost manufacturing strategy, and the integration of the Compute Module 4 (CM4) into industrial applications.
Ian from Electromaker reviews several maker projects, including Mellow Labs' automated washing machine detergent dispenser and aesthetic's thermal-sensor-driven Mr. Krabs violin. He highlights Carl Bugeja's tiny ESP32-C3 devboard with an integrated IMU and the Makerdiary iMX RT1011 Nano, a $15 board featuring an NXP Cortex-M7 processor. The episode also covers the Raspberry Pi AI Camera Module for edge detection and Ollie Q's internet-controlled Roomba project.
Jeff Bier, founder of the Embedded Vision Alliance (now Edge AI and Vision Alliance), explains how embedded vision has evolved from expensive industrial inspection to ubiquitous consumer applications like automotive safety and smartphone face ID, driven by domain-specific processors and deep learning. Jens Gamperl, CEO of Sourceability, describes his company's hybrid distribution model, which uses tools like Source Engine to integrate real-time supply chain data directly into design workflows via APIs, bridging the gap between engineering and procurement.
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.