Authors:

William P Jiang

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

When practicing, professional string musicians must pay attention to various aspects of their playing, including intonation, tempo, and posture. Our research aims to aid cello players in their practice by accurately detecting any deviations in posture and reporting them to the user. This enables them to both enhance their musical ability and reduce injuries caused by incorrect posture. Using recorded video data in the form of .mp4 files, body-pose detection is done using Google's MediaPipe framework and instrument-component (bow and string) detection is done using YOLOv8, a real-time object detection algorithm. Deviations in posture are detected by comparing this data with sample performers' postures in video training data. The current prototype indicates that using these tools, the hand positions of the cellist along with the bow and strings of the cello can be tracked in real time. Our long-term goal is to create an Evaluator app that will present several advantages for string players, including instantaneous feedback, consistent and objective analysis, enhanced precision in identifying subtle deviations that might be missed by the human eye, and the ability to practice independently without the constant need for a teacher or coach. Keywords: Neural Networks; Real-Time Tracking; Roboflow; Mediapipe; YOLOv8

Source:

Purdue University / 2024

Topics:

No topics listed

Co-authors:

William P Jiang