Recognition of Hand Gestures Observed by Depth Cameras. (14th April 2015)

• Record Type: Journal Article
• Authors: Kapuscinski, Tomasz; Oszust, Mariusz; Wysocki, Marian; Warchol, Dawid
• Is Part Of: International journal of advanced robotic systems. Volume 12:Number 4(2015)
• Publication Date: 2015-04-14
• Subjects: Hand Gesture Recognition -- Depth Cameras -- Viewpoint Feature Histogram -- Dynamic Time Warping Hidden Markov Models; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.5772/60091
• Languages: English
• ISSNs: 1729-8806

Abstract

We focus on gesture recognition based on 3D information in the form of a point cloud of the observed scene. A descriptor of the scene is built on the basis of a Viewpoint Feature Histogram (VFH). To increase the distinctiveness of the descriptor the scene is divided into smaller 3D cells and VFH is calculated for each of them. A verification of the method on publicly available Polish and American sign language datasets containing dynamic gestures as well as hand postures acquired by a time-of-flight (ToF) camera or Kinect is presented. Results of cross-validation test are given. Hand postures are recognized using a nearest neighbour classifier with city-block distance. For dynamic gestures two types of classifiers are applied: (i) the nearest neighbour technique with dynamic time warping and (ii) hidden Markov models. The results confirm the usefulness of our approach.