Speed, robustness, and cost are three important factors that determine the success of a vision-based human-computer interaction system. In our system, we introduce a scheme that uses only one camera (together with a mirror) to derive the 3D coordinates of a target object. To ensure a more natural interaction between the human and the computer, our system allows the user to use his/her bare fingers to point to any position in the 3D space. In addition, robustness and speed is
achieved through the use of the chain-code algorithm. The accuracy of the results is improved through the use of suitable post-processing filters. The performance of our system is thoroughly
evaluated.
In this paper, we propose a novel 3D vision-based solution using only one camera and a mirror. A number of experiments have been performed to show that our solution is robust to movement; has a fast pick -up rate so as to allow the user’s hand to move in and out of the scene just as s/he tends to pick up a normal 2D mouse now and then; and has a low computational cost –thus resulting in fast response time.
Did you find this white paper useful?
27 out of 50 users found this white paper useful
Related white papers
Using Multiple Graphics Cards as a General Purpose Parallel Computer: Applications to Computer Vision
Pattern recognition and computer vision tasks are computationally intensive, repetitive, and often exceed the capabilities of the CPU, leaving little time for higher level tasks. This paper presents a novel...
Select Text and Graphics
One can select text and graphics by using the mouse or the keyboard, including items that aren't next to each other. For example, one can select a paragraph on page...
Explore Model-Driven Development (MDD) and Related Approaches: Applying Domain-Specific Modeling to Model-Driven Architecture
In this paper, use Eclipse Modeling Framework (EMF) and Graphical Modeling Framework (GMF) technologies to produce domain-specific modeling tooling aids for domain-specific languages. Learn the value of defining a domain-specific...
NASA Mars Rover: Visualizing the Red Planet With NVIDIA Quadro Graphics
NASA lands two rovers on Mars and receives photographic image data from the surface. The data transmissions from Mars involve massive amounts of image data that must be quickly studied....
Touch Panel Technology: How Does it Work?
The first touchscreen was created by adding a transparent surface to a touch-sensitive graphics digitizer and sizing it to fit a computer monitor. The purpose was to increase the speed...
NVIDIA and the Celestia Program: A Window Into the Universe
The Celestia program was written to be platform-independent. SGI OpenGL functionality provided basic capabilities for building the visualization solution, but Chris wanted to maximize visual clarity and give users the...
Dell Precision Workstations With NVIDIA Graphics Cards Enhance Cutting-Edge Scientific Research at the University of Maryland Institute for Advanced Computer Studies
Researchers at the University of Maryland Institute for Advanced Computer Studies are contributing to the development of a new approach to high-performance parallel computing that uses clusters of processors and...
