Abstract
RGB-D cameras and depth sensors have made possible the development of an uncountable number of applications in the field of human-computer interactions. Such applications, varying from gaming to medical, have made possible because of the capability of such sensors of elaborating depth maps of the placed ambient. In this context, aiming to realize a sound basis for future applications relevant to the movement and to the pose of hands, we propose an approach to recognize fingers and to identify their position by means of the Microsoft Kinect technology. The experimental results exhibit a decent identification rate. Furthermore, the scored identification accuracy confirms the capability of following also little movements of the hand and it encourages the real possibility of successive implementations in more complex gesture recognition systems.
Kinect, What it is and How it Works
The Kinect sensor is composed by an RGB camera, which is similar to an autofocus webcam, with an 8-bit VGA resolution of 640 X 480 pixels at 30 frames per second (fps) and using a Bayer color filter. The depth sensor uses an infrared laser projector combined with a monochrome CMOS sensor, allowing to capture data under any light conditions, with 11-bit depth resolution that provides 2048 levels of sensitivity. The combination of the RGB camera in the visible range with the infrared depth sensor realizes the so called RGB-D sensor.
Authors and Contributors
This project is the contribution of Mridul Gupta (@mridulg), Syesha Girdher (@s1997), Abhijeet Singh (@abhijeet15004) and Aravinda Kumaran (@Mugen17).