A Realtime Shrug Detector

A realtime system for shrug detection is discussed in this paper. The system is automatically initialized by a face detector based on Ada-boost[14]. After frontal face is localized by the face detector, shoulder position is detected by fitting a parabola to the nearby horizontal edges using weighted Hough Transform[13]. Since shrug is an action which is defined not only by the distance between face and shoulder but also the relative temporal-spacial changing between them, we propose a parameterizing scheme using two different parabolas, named as ”Stable Parabola” (SP) and ”Transient Parabola” (TP) to characterize the action shrug. Stable Parabola represents the mean shoulder position over a long time duration, while Transient Parabola represents the mean shoulder position of a very short time duration. By using this scheme (only 6 dimensions), we avoid the high dimensional representation of the temporal process—shrug, and therefore make the realtime implementation possible...

• Type: Conference
• Year: 2006
• Where: FGR
• Authors: Huazhong Ning, Tony X. Han, Yuxiao Hu, ZhenQiu Zhang, Yun Fu, Thomas S. Huang
• Keywords: Face Detector, FGR 2006, Shoulder Position, Shrug Detector