OpenVIDIA : Parallel GPU Computer Vision

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

 Doc Manager

 Mailing Lists

 Screenshots

 Task Manager

 CVS Tree

 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

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 . . .

Features

Real-Time Computer Vision openVIDIA allows processor intensive computer vision to be offloaded to the GPU.This includes the following vision algorithms performed in real-time: Edge and Corner Detection Feature Based Corner Tracking Skin Tone Tracking Color Object Tracking Contrast/Brightness Image Enhancement Video Orbits Image Compositing Algorithm Parallel GPU Computation OpenVIDIA allows for unprecedented high-performance computer vision by harnessing the power of multiple GPUs to process images in parallel. This allows for the creation of a cheap, powerful, and easily constructed parallel architecture well suited for pattern recognition and computer vision. Mediated Reality Mediated Reality, unlike virtual reality which blocks the user from seeing the real-world, allows the user to experience a computationally enhanced or mediated version of reality that mixes both real and virtual worlds. This is often also refered to as augmented or mixed reality. With the power of openVIDIA it becomes possible to experience real-time, seamless real--time mediated reality. This includes the following features: 2D virtual tags to label the real world around the user 3D objects created in 3D Studio or Cal3D to be inserted into the real world (still under development)

Features are tracked and given an ID number Possibly useful input for higher level vision tasks. [16MB video]. A computer vision machine with 6 PCI graphics cards, and 1 AGP graphics card. Each PCI card has a GeForce FX 5200 GPU which runs pattern recognition and computer vision tasks in parallel. flcornersTrack scene tracking/annotation program.