Sciweavers

Share
HAIS
2010
Springer

Recognition of Manual Actions Using Vector Quantization and Dynamic Time Warping

11 years 4 months ago
Recognition of Manual Actions Using Vector Quantization and Dynamic Time Warping
The recognition of manual actions, i.e., hand movements, hand postures and gestures, plays an important role in human-computer interaction, while belonging to a category of particularly difficult tasks. Using a Vicon system to capture 3D spatial data, we investigate the recognition of manual actions in tasks such as pouring a cup of milk and writing into a book. We propose recognizing sequences in multidimensional time-series by first learning a smooth quantization of the data, and then using a variant of dynamic time warping to recognize short sequences of prototypical motions in a long unknown sequence. An experimental analysis validates our approach. Short manual actions are successfully recognized and the approach is shown to be spatially invariant. We also show that the approach speeds up processing while not decreasing recognition performance.
Marcel Martin, Jonathan Maycock, Florian Paul Schm
Added 19 Jul 2010
Updated 19 Jul 2010
Type Conference
Year 2010
Where HAIS
Authors Marcel Martin, Jonathan Maycock, Florian Paul Schmidt, Oliver Kramer
Comments (0)
books