gesture segmentation notes

Alon J , Athitsos V , Yuan Q , et al. A Unified Framework for Gesture Recognition and Spatiotemporal Gesture Segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2009, 31(9):1685-1699.

• gestureing hand location, when the gesture start and end
• this paper introcduces a unified framework for simultaneously performing spatial segmentation, temporal segmentation and recognition.
• three novel contributions:

  a spatiotemporal matching algorithm that can accommodate multiple candidate hand detections in every frame;
  a classifier-based pruning framework that enables accurate and early rejection of poor matches to gesture models;
  a subgesture reasoning algorithm that learns which gesture models can falsely match parts of other longer gestures.

• evaluated on two applications:

  recognition of hand-signed digits gesture by users wearing short sleeved shirts, in front of a cluttered background;
  retrieval of occurences of signs of interest in a video database containing continuous, unsegmented signing in American sign;
  information flows both bottom-up and top-down: in the bottom-up direction, multiple candidate hand locations are detected and their features.