Automatic detection of musicians’ ancillary gestures based on video analysis
作者：
Highlights：
• A novel approach for the detection of ancillary gestures produced by clarinetists during musical performances.
• Detect, segment and track points of interest and parts of the musician body in video scenes.
• Detect the three most commonly seen ancillary gestures of this class of musicians.
• Evaluation with respect to the precision and recall in detecting ancillary gestures on 12,423 video frames.
• Precision in detecting ancillary gestures varies between 78.4% and 92.8%, while the recall varies between 85.3% and 95.5%.
摘要
•A novel approach for the detection of ancillary gestures produced by clarinetists during musical performances.•Detect, segment and track points of interest and parts of the musician body in video scenes.•Detect the three most commonly seen ancillary gestures of this class of musicians.•Evaluation with respect to the precision and recall in detecting ancillary gestures on 12,423 video frames.•Precision in detecting ancillary gestures varies between 78.4% and 92.8%, while the recall varies between 85.3% and 95.5%.
论文关键词：Gestures,Music expression,Video analysis,Image processing
论文评审过程：Available online 27 September 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.09.009
