ACTIVITY AND GESTURE RECOGNITION

Within the context of Home Automation, the design of man-machine interfaces have assumed a central role for the development of smart environments. In this respect, the interaction based on gestures measured through inertial devices represents a fascinating and interesting solution thanks to a new generation of ubiquitous technologies that allow to pervasively and seamlessly control the human space.

This research line regards a Machine Learning (ML) approach to gesture recognition (GR), in its main aspects of (i) event identification, (ii) feature extraction and (iii) classification: in detail, an informative and compact representation of the gesture input signals is defined, using both feature extraction and the analysis in the time domain through signal warping, a pre-processing phase based on Principal Component Analysis is proposed to increase the performance in real-world scenario conditions, and, finally, parsimonious classification techniques based on Sparse Bayesian Learning are designed and compared with more classical ML algorithms. These contributions yield the definition of a system that is user independent, device independent, device orientation independent, and provides a high classification accuracy.

Related publications:
- G. Belgioioso, A. Cenedese, G.I. Cirillo, F. Fraccaroli, G.A. Susto. A Machine Learning based Approach for Gesture Recognition from Inertial Measurements. IEEE 53rd Conference on Decision and Control, pp. 4899--4904, 2014
- A. Cenedese, G.A. Susto, G. Belgioioso, G.I. Cirillo, F. Fraccaroli. Home Automation Oriented Gesture Classification From Inertial Measurements. IEEE Transactions on Automation Science and Engineering, vol. 12(4), pp. 1200--1210, 2015
- A. Cenedese, G.A. Susto, M. Terzi. A Parsimonious Approach for Activity Recognition with Wearable Devices: an Application to Cross-country Skiing. European Control Conference 2016 (ECC'16), 2016

Reference

Beginning Date date: Sept. 2013
HIT project coordinator: prof. Angelo Cenedese
HIT Involved Staff: TBD
Contact: angelo.cenedese[at]dei.unipd.it