GpuCV: GPU-accelerated Computer Vision

原創

东方未晞

2020-07-03 02:14

GPUCV提供的GPU加速替代例程，是與OpenCV兼容的。圖像處理應用程序員無需關心圖形上下文或硬件，而且範例應用由程序提供。程序員可以通過能夠自動管理着色、紋理和先進的OpenGL延伸。其框架透明化管理着硬件功能，數據同步，低層次GLSL的和CUDA方案，快速的動態測試以及到最有效實現的切換，最終提供一套GPUCV加速器上的圖像處理操作。另外，GPUCV還提供一些高級操作，如形態學和邊緣檢測、矩陣乘法、離散傅里葉變換等等。

https://picoforge.int-evry.fr/cgi-bin/twiki/view/Gpucv/Web/WebHome

GpuCV: GPU-accelerated Computer Vision

GpuCV: GPU-accelerated Computer Vision

New release of GpuCV is v1.0.0 rev 600 (Oct. 6th, 2010).

Presentation

GpuCV is an open-source GPU-accelerated image processing and Computer Vision library. It offers an Intel's OpenCV-like programming interface for easily porting existing OpenCV applications, while taking advantage of the high level of parallelism and computing power available from recent graphics processing units (GPUs). It is distributed as free software under the CeCILL-B license.

Longer descriptions are available as:

Yannick Allusse, Patrick Horain, Ankit Agarwal and Cindula Saipriyadarshan, "GpuCV: An OpenSource GPU-Accelerated Framework for Image Processing and Computer Vision", Proc. ACM Multimedia 2008, October 27-31, 2008, Vancouver, BC, Canada, pp. 1089-1092 [ doi:10.1145/1459359.1459578 ].
Yannick Allusse, Patrick Horain, Ankit Agarwal and Cindula Saipriyadarshan, "GpuCV: A GPU-accelerated framework for Image Processing and Computer Vision", Advances in Visual Computing, Proceedings of the 4th International Symposium on Visual Computing (ISVC08), December 1-3, 2008, Las Vegas, Nevada, USA, LNCS Volume 5359, Springer-Verlag, p. 430-439 [ doi:10.1007/978-3-540-89646-3_42 ].
J.-P. Farrugia, P. Horain, E. Guehenneux, Y. Allusse, "GPUCV: A framework for image processing acceleration with graphics processors", CDROM proc. of the IEEE International Conference on Multimedia & Expo (ICME 2006), July 9-12, 2006, Toronto, Ontario, Canada [ doi:10.1109/ICME.2006.262476 ].

Features

GpuCV offers GPU-accelerated replacement routines that are fully compatible with their OpenCV counterpart.

Image processing applications programmers do not have to care for graphics context nor hardware. Examples applications are provided.

Operator developers may access graphics functionalities through the GpuCV framework that automatically manages shader programs, textures and advanced OpenGL extensions.

More...

Coming events

...

Last events

Oct. 6 2010: GpuCV 1.0.0 rev 600 released.
July 6 - July 10, 2010: GpuCV author(s) will talk at the RMLL2010 (Libre Software meeting) event in Bordeaux, FRANCE.
June 29 - July 2nd, 2010: GpuCV author(s) will talk at the French speaking summer school on image processing with GPUs.
February, 2010: A new release of GpuCV has been scheduled for March 2010. Stay tuned!
June 15-16, 2010: GpuCV authors(s) will be present at TER@TEC 2010 event on HPC.
April 7-9, 2010: GpuCV authors(s) will be present at LAVAL VIRTUAL 2010, International conference on Virtual Reality.
September 30, 2009: GpuCV was presented at EPITA/LRDE seminar. Here are the slides .
December 6, 2008: GpuCV was presented at the first GPUCamp. Here are the slides .
December 4, 2008: GpuCV was presented at the 2nd 2e Journée Thème Emergent GPGPU.
December 3, 2008: A publication was presented at ISVC08, Las Vegas, Nevada.
November 15-21, 2008: GpuCV was demonstrated by NVIDIA at SC08, Austin, Texas.