Real-Time Gesture Recognition for Controlling a Virtual Hand

2012 ◽  
Vol 463-464 ◽  
pp. 1147-1150 ◽  
Author(s):  
Constantin Catalin Moldovan ◽  
Ionel Staretu
Keyword(s):  
Virtual Environments ◽  
Real Time ◽  
Three Dimensional ◽  
Video Stream ◽  
Human Hand ◽  
Hand Motion ◽  
Virtual Hand ◽  
Hand Control ◽  
Hand Gesture Detection ◽  
Detection And Recognition

Object tracking in three dimensional environments is an area of research that has attracted a lot of attention lately, for its potential regarding the interaction between man and machine. Hand gesture detection and recognition, in real time, from video stream, plays a significant role in the human-computer interaction and, on the current digital image processing applications, this represent a difficult task. This paper aims to present a new method for human hand control in virtual environments, by eliminating the need of an external device currently used for hand motion capture and digitization. A first step in this direction would be the detection of human hand, followed by the detection of gestures and their use to control a virtual hand in a virtual environment.

scholarly journals Real-Time Calibration and Registration Method for Indoor Scene with Joint Depth and Color Camera

2018 ◽  
Vol 32 (07) ◽  
pp. 1854021 ◽  
Author(s):  
Fengquan Zhang ◽  
Tingshen Lei ◽  
Jinhong Li ◽  
Xingquan Cai ◽  
Xuqiang Shao ◽  
...  
Keyword(s):  
Real Time ◽  
Color Image ◽  
Random Noise ◽  
Three Dimensional ◽  
Depth Map ◽  
Video Stream ◽  
Depth Information ◽  
Registration Method ◽  
The Real ◽  
Time Calibration

Traditional vision registration technologies require the design of precise markers or rich texture information captured from the video scenes, and the vision-based methods have high computational complexity while the hardware-based registration technologies lack accuracy. Therefore, in this paper, we propose a novel registration method that takes advantages of RGB-D camera to obtain the depth information in real-time, and a binocular system using the Time of Flight (ToF) camera and a commercial color camera is constructed to realize the three-dimensional registration technique. First, we calibrate the binocular system to get their position relationships. The systematic errors are fitted and corrected by the method of B-spline curve. In order to reduce the anomaly and random noise, an elimination algorithm and an improved bilateral filtering algorithm are proposed to optimize the depth map. For the real-time requirement of the system, it is further accelerated by parallel computing with CUDA. Then, the Camshift-based tracking algorithm is applied to capture the real object registered in the video stream. In addition, the position and orientation of the object are tracked according to the correspondence between the color image and the 3D data. Finally, some experiments are implemented and compared using our binocular system. Experimental results are shown to demonstrate the feasibility and effectiveness of our method.

Equations of Hand Motion Path for Work Space Design

1969 ◽  
Vol 11 (2) ◽  
pp. 123-129 ◽  
Author(s):  
Appu Kattan ◽  
Gerald Nadler
Keyword(s):  
Three Dimensional ◽  
Motion Path ◽  
Human Hand ◽  
Prediction Equations ◽  
Hand Motion ◽  
Work Space ◽  
Space Design ◽  
Movement Distance ◽  
Linear Movement ◽  
Depth Dimension

This work developed a set of prediction equations for three-dimensional motions of the human hand, thus facilitating the design of the dynamic elements in work space. The variables considered were the distance moved and the direction of motion. It was concluded from the results that: (a) it is possible to develop accurate prediction equations for three-dimensional motions of body members; (b) distance has only a negligible effect on motion path; (c) the effect of direction on motion path is uniform except for the 90° motion; (d) only two sets of equations, one for 90° motions and the other for motions in other directions, are required to predict the path of any motion in the experimental region; (e) the overall length of motion path is only slightly more than the linear movement distance; and (f) the depth dimension in a three-dimensional motion is negligibly small.

Sign in / Sign up

Export Citation Format

Share Document