Turn your family photos into retro 8-bit masterpieces with this Atari 2600 digital frame.
It was a creative gift for my girlfriend Jennifer. I dedicate this project to her with lots of love! ❤️
This post adds a toggle for the Sobel filter, ensuring the screen remains stable with no blackout.
This time, we are adding the HLS Sobel filter IP to the HDMI Passthrough to achieve real-time image processing.
An exploration of accelerating the MediaPipe models with MemryX's MX3 AI Accelerator.
Altera Accelerator Image Convolution Filter Demo with Agilex 7, Arria 10, and MAX 10 FPGAs.
On PYNQ-Z2, HDMI displays via TPG and supports rx/tx passthrough. See article 1 for TPG details; this article covers passthrough.
A maze navigation case that integrates digital twin with computer vision, using Matlab simulation to validate the robot’s motion results.
PYNQ-Z2's HDMI offers TPG for test patterns and passthrough for direct video. In this tutorial, we demonstrate TPG output functionality.
Getting Started with Infinite-ISP, the open source image signal processor on AMD Kria KV260 AI Starter kit.
Getting a correct white balance is not an easy task. The project proposes a simple technque to validate our White Balance.
We will learn Vison-Language Models across tasks such as captioning, object detection, grounding, and segmentation on a Raspberry Pi.
This project explores how to add support for the open-source LIBCAMERA project on our Zynq-UltraScale+ platform.
In order to add support for V3, HQ, and AI cameras on your Zynq-UltraScale+ platform, leverage Raspberry Pi's linux kernel repository.
If you are looking to add support for RPI cameras on your Zynq-UltraScale+ platform, start with Opsero's RPI Camera reference design.
Introducing AeroCommand: Hands-free drone control. Face and voice command your DJI mavic pro drone!
This article introduces how to install OpenCV in Vitis HLS 2022.2 and successfully run examples from the Vitis Vision Library.
Build a machine learning model using a federated training framework to keep data on-device, train locally, and update a global model.
Using the power of LLaVA (Large Language and Vision Assistant) multimodel model to allow you to organise and find your images with ease.
A smart IoT solution for real-time waste monitoring, optimized collection, and cleaner communities through seamless data sharing.
Using embedded Vision AI for detecting reckless bravados trespassing and breaking proximity safety rules in Zoo
Building a more effective fire detection machine learning model by combining image and temperature sensor data.
Expansion library for using blended transparent images on the Arduino Portenta H7 board.
BisindoMate Empowering deaf individuals by providing accessible sign language interpretation
