OpenVIDIA : Parallel GPU Computer Vision


Home
Features
Screenshots & Videos
Installation
Instructions
Quickstart
Programming
Example v0-0.07x
Programming
Example v0.8
Computer Vision with CUDA (new 1May08)
Framebuffer Objects
Download
Papers
Contributing
Project
sf.net project page
Tracker Tracker

 - Bugs ( 0 open / 0 total )
Bug Tracking System

 - Support Requests ( 1 open / 1 total )
Tech Support Tracking System

 - Patches ( 1 open / 1 total )
Patch Tracking System

 - Feature Requests ( 0 open / 1 total )
Feature Request Tracking System

Forums Forums ( 246 messages in 2 forums )
Docs Doc Manager
Mail Lists Mailing Lists ( 0 mailing lists )
Screenshots Screenshots
Tasks Task Manager
There are no public subprojects available
CVS CVS Tree ( commits, adds ) known bug
FTP Released Files

Related Projects

Comparametric Toolkit

Reference Links

Open GL Reference

nVIDIA cg homepage

GeForce FX Overclocking

GPGPU

gpu's arent just good for vision and computation - some clever folks have started using them for games as well. ;) har har linux-games.net

7 Years of Graphics Card History

SourceForge.net Logo

Page design based on Blosxom (which was used originally before the move to sourceforge).

This page best viewed with Dillo, Lynx, w3m, Mozilla-Firefox, Galeon, Epiphany, konqueror . . .

    

Contributing

We welcome any contributions you may have to the openvidia source code Email us to add a contribution

Here are some general items to help you get started, if you can think of some projects to add to our list then perhaps you could let us know.

Development

To develop for openvidia, it would be good to familiarize oneself with OpenGL and also cg since these are both extensively used in the openVIDIA library.
  • Porting to Multiple Platforms We would like to see OpenVIDIA run on multiple platforms including Windows, FreeBSD, MacOS etc in the future.
  • Creating a debian package for easy installation of openvidia, which could be downloaded from the official distribution site
  • Single pass orbits glDrawBuffersATI() is now supported by GeForce FX 6800 cards. (need to install the glext.h header from hte NVIDIA driver downloads (See readme in the download, it put them in /usr/share/doc/NVIDIA...). Right now orbits needs about 16 rendering passes. Single pass orbits could potentially be hugely faster on the GPU and save huge amounts of CPU overhead, and form a generalized framework for large matrix processing.
  • Benchmarking This benchmarking site describes some ways of benchmarking performance. What kind of performance can we get on the GPU relative to these? Where is the GPU the best? Where is multiple GPU the best (parallel streaming memory accees maybe? see this

Documentation

  • We need effective documentation which communicates the power of openVIDIA's many functions