We focus on the visual sensory information to recognize human activity in form of hand-arm movements from a small, predefined vocabulary. We accomplish this task by means of a matching technique by determining the distance between the unknown input and a set of previously defined templates. A dynamic time warping algorithm is used to perform the time alignment and normalization by computing a temporal transformation allowing the two signals to be matched. The system is trained with finite video sequences of single gesture performances whose start and end-point are accurately known. Preliminary experiments are accomplished off-line and result in a recognition accuracy of up to 92%.
Dynamic time warping for off-line recognition of a small gesture vocabulary
2001-01-01
715437 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Dynamic Time Warping for Off-Line Recognition of a Small Gesture Vocabulary
British Library Conference Proceedings | 2001
|Speech Recognition using Dynamic Time Warping
IEEE | 2008
|Randomized time warping for motion recognition
British Library Online Contents | 2016
|Gesture Recognition Under Small Sample Size
Springer Verlag | 2007
|