This paper describes a novel approach for human gesture recognition from motion data captured by a Kinect camera. The proposed method is based on encoding the temporal history of input data using bidirectional Echo State Networks, whereas the output is computed by means of a multi-layer perceptron with softmax. Results achieved at the time-series classification challenge organized within the 2016 ECML PKDD Workshop on Advanced Analytics and Learning on Temporal Data show the potentiality of the approach.
A reservoir computing approach for human gesture recognition from kinect data
GALLICCHIO, CLAUDIO;MICHELI, ALESSIO
2017-01-01
Abstract
This paper describes a novel approach for human gesture recognition from motion data captured by a Kinect camera. The proposed method is based on encoding the temporal history of input data using bidirectional Echo State Networks, whereas the output is computed by means of a multi-layer perceptron with softmax. Results achieved at the time-series classification challenge organized within the 2016 ECML PKDD Workshop on Advanced Analytics and Learning on Temporal Data show the potentiality of the approach.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.