Enregistré dans:
Détails bibliographiques
Auteurs principaux: Al Bulushi, Mazin, Al Busaidi, Abdulaziz
Format: Recurso digital
Langue:
Publié: Zenodo 2025
Accès en ligne:https://doi.org/10.5281/zenodo.19548187
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • <p>This project presents a vision-based piano learning assistant that uses computer vision techniques to detect key presses from video input and provide real-time feedback through a gamified “falling notes” interface. Implemented on a Raspberry Pi, the system combines perspective correction, key segmentation, and skin tracking to achieve accurate detection while filtering noise such as shadows and reflections. A two-phase pipeline ensures high performance and smooth visualization, achieving around 93% accuracy and enabling an interactive and engaging piano learning experience.</p>