An industrial automation system for block sorting, utilizing Computer Vision and Finite State Machines, implemented with Edge Impulse.
Going from demo to production with NVIDIA Deepstream means custom models, C++ pipelines and real world fine-tuning, Find out what we learnt.
AI-powered recognition, no cloud, no subscriptions — just smart vision on board
Pruning the Yolov3 with Pytorch based pruning method and Quantizing/compiling the pruned model with Vitis AI for AMD-Xilinx KV260 FPGA.
A robotic arm that uses Google's Coral Edge TPU USB Accelerator to run object detection and recognition of different recycling materials.
The image extraction is based on a novel algorithm which effectively works with the encoding system of the robot movement.
Donkey Car featuring the Ultra96 board, a Raspberry Pi, FPGA accelerated stereo vision, MIPI CSI-2 image acquisition, a LiDAR sensor and AI.
Using the TensorFlow Lite library, we can flash tiny machine learning models on an Arduino to detect humans from a camera.
Pose estimation on a Raspberry Pi to guide and correct positions for any yogi.
Kindbot packs an app, sensors, voice-control, and state-of-the-art computer vision to eliminate guess work & maximize yields.
This project shows how you can bring the Wizarding of Harry Potter to reality with computer vision and machine learning!
An implementation of stereo-vision-based SLAM on Ultra96-V2 with FPGA acceleration for 10 FPS real-time operation.
Combine the power of autonomous flight and computer vision in a UAV that can detect people in search and rescue operations.
This in-depth article is what you should go first to be able to work with Industry-Standard FPGA HDMI designs. Don't Miss it!
Allows the reading impaired to hear both printed and handwritten text by converting recognized sentences into synthesized speech.
The project focuses on a real-time robust human detection and tracking system for video surveillance that can be used in varying situations.
Sudoku-robot is a robot that solves and fills Sudoku grids!
Project ARIES - A system of intelligent and connected autonomous vehicles to provide an immediate response and action to emergency scenarios
Avnet provides pre-verified designs for its platforms. This project describes how to re-generate the ZUBoard designs from source.
Amateur's Guide: Comparing Vision AI MCUs on Ease & Speed
In this article, I'll show how to train a custom machine learning model with Edge Impulse and deploy it to the Arduino Nano 33 BLE Sense.
Avnet provides pre-verified designs for its platforms. This project describes how to re-generate the Ultra96-V2 designs from source.
An autonomous car able to drive along a lane and react to roadsigns, obstacles and smart RFID markers, powered by OpenCV and Embedded Linux.
An AI-based assistive tool for blind people for the edge of easy movement.
