OpenCV is a free library for research and commercial purposes that includes hundreds of optimized computer vision and image processing algorithms. NVIDIA and Itseez have optimized many OpenCV functions using CUDA on desktop machines equipped with NVIDIA GPUs. These functions are 5 to 100 times faster in wall-clock time compared to their CPU counterparts.
Anatoly Baksheev, OpenCV GPU Module Team Leader at Itseez, demonstrates how to obtain and build OpenCV, its GPU module, and the sample programs. You’ll then learn how to use the OpenCV GPU module to create your own high-performance computer vision applications. Finally, you’ll learn how to start using CUDA to create your own custom GPU computer vision functions and integrate them with OpenCV GPU functions to add novel capabilities.
Please see here for a downloadable set of presentation slides in PDF format, along with a downloadable version of the video.