Train a domain-specific image to keywords model that is 200x lighter (9MB) and runs with low latency on hardware such as Raspberry Pi 4.
With ROS 2 integration, the YOLO-Pro model from Edge Impulse powers real-time hand tracking on the Rubik Pi 3, accelerated by Qualcomm AI.
Autonomous humanoid robot uses Edge Impulse YOLO-Pro model on Particle Tachyon with Qualcomm AI Accelerator for balls detection and kicking
This project showcases the inference of an Edge Impulse YOLO-Pro model using a 12 TOPS AI Accelerator on the Qualcomm Dragonwing SoC.
A smart helmet for cyclists that recognise audio instructions from the rider and activates LEDs at the back to indicate left or right turns.
An industrial automation system for block sorting, utilizing Computer Vision and Finite State Machines, implemented with Edge Impulse.
Going beyond general steps tracking by factoring terrain to deliver advanced calorie and cardiovascular insights.
Measure your heart rate wirelessly using ESP32 dev boards and AI.
An AI sleep monitor that tracks snoring and breathing to deliver actionable insights for better sleep.
An affordable, battery-powered ML device detects Atrial Fibrillation using PPG for real-time heart monitoring with Edge Impulse
Flockr uses the Particle Tachyon running a TensorFlow Lite edge AI model capable of classifying bird species from a video feed.
A prototype designed for an intruder detection system capable of identifying human presence and initiating preemptive measures.
An ML based HMI system that translates your unique heat signature into seamless and intuitive gesture commands using Edge Impulse.
Skynet is a lightweight command line interface for LLMs to control real robots and drones using Bash.
It is an lightweight intelligent solution designed to monitor and identify abnormal vibration patterns in real-time.
Simulate talking with WOPR from WarGames by using a Raspberry Pi 400, a General Instrument SP0256-AL2 speech chip, and a Google Gemini LLM.
You can quickly start with Raspberry PI AI camera powered by Sony's IMX500 Intelligent Sensor and try pre-trained sample AI models.
This project describes how it is possible to modify an existing code created for AIE to target AI Engine-ML device
PageParrot turns any book into an audiobook in seconds.
CCTVs just watch, this one thinks! Using AI to identify human activities that may pose security threats to vehicles!
Machine Learning for Conservation: Detecting the voice of the Wood Grouse
Can both ML training and inference be done on MCU? This project illustrates how to implement on-device Edge AI with the XIAO ESP32S3 Sense.
Edge AI sounds fun... until data capture hits? We hear you! MicroPython integration with DEEPCRAFT™ Studio makes it easy like never before.
AI is improving, we are becoming more dependent on it, and soon it will turn on us — unless we save ourselves with 1990s digital organizers.
