Hi! I'm TheAypisamFpv, a French computer science and AI student at CESI.
Everything you know about me, you know it only because i let you.
Currently developping an end2end AI to play Minecraft (plz send RTX5090).
A highly complex Proof of Concept (POC) for a vision-only system to detect, track, and position containers in 3D space (vSLAM).
Developed during an internship, it integrates advanced YOLO-based detection, single-optic visual odometry and GPS for camera tracking and positioning, and 3D visualization using the Ursina engine.
Note: This is an internal company project and is not publicly available. (maybe something soon-ish™)
Python tool used to visualize and use a Neural Network.
This project is a port of the Bad Apple video to the BatPU-2, a 8-bit computer designed by mattbatwings in Minecraft, programmable in ASM using a custom instruction set.
Uses YoloV9c-seg to detect drivable surfaces, lines and obstacles.
It is trained on human-labeled images. Later I will try to integrate auto labeling.
I use at least one thing learned during a course to play Bad Apple!! (Video and/or Sound)
A Python application that automatically sets your desktop wallpaper to near real-time images of Earth.
Features include configurable image sources, automatic cropping, and resolution adaptation.
This is a real-time image of Earth from EUMETSAT.