A method and device for recognizing a gesture in real-time

摘要

The present disclosure relates to a method and a device for recognizing hand gestures in real-time. A shape is given as an input in a form of a binary image. The shape contour is partitioned into radial and angular spaces by means of an Angular Radial Bin distribution comprising multiple concentric circles and angular space partitions in a way that multiple angular radial sections are created denoted Angular Radial Bins. The ARB distribution is angle tilted through its centre of mass multiple times and the same procedure is repeated in order to capture a shape descriptor from different angle perspectives. A shape descriptor is calculated for each of an angle tilted instance of the ARB distribution belonging to a sequence of angle tilted instances of the ARB distribution.