以視覺為基礎之指揮練習系統研究

A Vision-based Music Conducting Practicing System

劉定翔(Ting-Shiang Liu)

指導教授 ： 李忠謀

國立臺灣師範大學/理學院/資訊工程研究所/碩士(2009年)

摘要

本研究提出視覺化互動式音樂指揮系統供使用者培養音樂節奏感。利用快速平均位移追蹤演算法即時追蹤指揮動作，並藉由分析指揮軌跡可以決定指揮速度。使用者練習指揮時，本系統可以提供聽覺與視覺的節奏提示，來幫助使用者穩定節奏感。甚至音樂速度可隨著指揮速度改變，作為進階的節奏訓練。
實驗結果顯示本研究的指揮追蹤與指揮速度偵測是很可靠的。音樂指揮實驗顯示使用者藉由指揮系統練習節奏，對提升節奏感是很有效果的。

關鍵字

物體追蹤 ； 指揮

並列摘要

This paper presents a vision-based interactive music conducting practice system. A fast mean-shift object tracking algorithm is implemented to track the baton of the conductor in real time. By analyzing the tracked baton path, the conducting tempo is determined. When practicing, the system provides both visual and audio cues to help user to improve their steadiness. Furthermore, practice conduction of MP3 music with realtime feedback is possible.
Experimental results show that the system is robust in terms of baton tracking and tempo detection. Furthermore, music conduction experiments show that the practicing system is effective for steading user's conducting tempo and enhancing conducting skills with only limited number of practices.

並列關鍵字

object tracking ； conducting

參考文獻

[4] J. Borchers, E. Lee, W. Samminger, and M. Mühlhäuser, "Personal orchestra: a real-time audio/video system for interactive conducting," Multimedia Systems, vol. 9, pp. 458- 465, 2004

[5] R.V. Babu, P. Pérez, and P. Bouthemy, "Robust tracking with motion estimation and local Kernel-based color modeling," Image and Vision Computing, vol. 25, pp. 1205- 1216, 2007

[7] A. Camurri, S. Hashimoto, M. Ricchetti, A. Ricci, K. Suzuki, R. Trocca, and G.. Volpe, "EyesWeb: Toward Gesture and Affect Recognition in Interactive Dance and Music Systems," Computer Music Journal, vol. 24, pp. 57- 69. 2000

[9] M.T. Driscoll, "A Machine Vision System for Capture and Interpretation of an Orchestra Conductor’s Gestures," M.S Degree, Worcester Polytechnic Institute, 1999

[10] A. Elgammal, R. Duraiswami, D. Harwood, and L.S. Davis, "Background and foreground modeling using nonparametric kernel density estimation for visual surveillance," Proceedings of the IEEE, vol. 90, pp. 1151- 1163, 2002