Hand gesture recognition with leap motion and kinect devices

Abstract

The recent introduction of novel acquisition devices like the Leap Motion and the Kinect allows to obtain a very informative description of the hand pose that can be exploited for accurate gesture recognition. This paper proposes a novel hand gesture recognition scheme explicitly targeted to Leap Motion data. An ad-hoc feature set based on the positions and orientation of the fingertips is computed and fed into a multi-class SVM classifier in order to recognize the performed gestures. A set of features is also extracted from the depth computed from the Kinect and combined with the Leap Motion ones in order to improve the recognition performance. Experimental results present a comparison between the accuracy that can be obtained from the two devices on a subset of the American Manual Alphabet and show how, by combining the two features sets, it is possible to achieve a very high accuracy in real-time

Theoretical Frames for Sign and Dactyl Recognition System GESL data

“…not graphical /visual format) the data depends on the particular device and on its technical characteristics. It can be as a custom made device as well as any other existing devises, like Microsoft Kinect (Marin at al 2014, Yi Li 2012, Murata & Shin 2014Tang 2011), or LeapMotion (Marin at al 2014, Marin at al 2015, McCartney, at al 2015, Nowicki, et al 2014. These devices are cheap and do not require additional supplies or a special studio environment.…”

“…Surprisingly, the results varied between 60-70% for dozens of signs. Taking into consideration the work of our colleagues (Nowicki et al 2014, Marin et al 2014. We tried SVM method and improved the results.…”

Mobile Platform Motion Control System Based on Human Gestures

“…Computer vision can be applied to various domains, such as, Virtual Reality, Robotics, Desktop and Tablet applications, Games, Sign Languages, among others [13]. Solutions based on ordinary webcams [14], infrared sensors (Leap Motion) [15] or depth sensors (Kinect and RealSense 3D) [16] [17] were already implemented in the literature. Cameras represent a less intrusive solution, since the user is completely equipment free but, once data is obtained from the cameras, the quality and reliability of this data have a great dependency over the environment light, the capture distance/perspective and even the camera quality.…”

A Non-parametric RDP Algorithm Based on Leap Motion

“…Leap Motion [1][2][3][4][5][6][7][8][9][10][11][12][13] is a somatosensory controller for PC and Mac released by Leap in 2013. And Kinect [14], [15] different, Leap Motion can only recognize hand movements, such as the palm, finger position, direction, angle and other information.…”