Fusion of Inertial and Depth Sensor Data for Robust Hand Gesture Recognition
- 19 February 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 14 (6), 1898-1903
- https://doi.org/10.1109/jsen.2014.2306094
Abstract
This paper presents the first attempt at fusing data from inertial and vision depth sensors within the framework of a hidden Markov model for the application of hand gesture recognition. The data fusion approach introduced in this paper is general purpose in the sense that it can be used for recognition of various body movements. It is shown that the fusion of data from the vision depth and inertial sensors act in a complementary manner leading to a more robust recognition outcome compared with the situations when each sensor is used individually on its own. The obtained recognition rates for the single hand gestures in the Microsoft MSR data set indicate that our fusion approach provides improved recognition in real-time and under realistic conditions.This publication has 19 references indexed in Scilit:
- Real-time robust vision-based hand gesture recognition using stereo imagesJournal of Real-Time Image Processing, 2013
- Kinect Based Dynamic Hand Gesture Recognition Algorithm ResearchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Robust hand gesture recognition with kinect sensorPublished by Association for Computing Machinery (ACM) ,2011
- Real time hand pose estimation using depth sensorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Real-Time Activity Recognition in Wireless Body Sensor Networks: From Simple Gestures to Complex ActivitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- A customizable framework of body area sensor network for rehabilitationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Monitoring Motor Fluctuations in Patients With Parkinson's Disease Using Wearable SensorsIEEE Transactions on Information Technology in Biomedicine, 2009
- Target Tracking by Particle Filtering in Binary Sensor NetworksIEEE Transactions on Signal Processing, 2008
- A Survey of Elastic Matching Techniques for Handwritten Character RecognitionIEICE Transactions on Information and Systems, 2005
- A real-time articulated human motion tracking using tri-axis inertial/magnetic sensors packageIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2004