3D gesture classification with convolutional neural networks
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 5432-5436
Abstract
In this paper, we present an approach that classifies 3D gestures using jointly accelerometer and gyroscope signals from a mobile device. The proposed method is based on a convolutional neural network with a specific structure involving a combination of 1D convolution, averaging, and max-pooling operations. It directly classifies the fixed-length input matrix, composed of the normalised sensor data, as one of the gestures to be recognises. Experimental results on different datasets with varying training/testing configurations show that our method outperforms or is on par with current state-of-the-art methods for almost all data configurations.Keywords
This publication has 8 references indexed in Scilit:
- Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition2012
- Convolutional networks and applications in vision2010
- Breaking the status quo: Improving 3D gesture recognition with spatially convenient input devices2010
- Accelerometer-based gesture recognition via dynamic-time warping, affinity propagation, & compressive sensing2010
- Accelerometer-based gesture control for a design environmentPersonal and Ubiquitous Computing, 2005
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Online gesture recognition system for mobile interaction2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998