GPUCV: A Framework for Image Processing Acceleration with Graphics Processors

Farrugia, Jean-Philippe; Horain, Patrick; Guehenneux, Erwan; Alusse, Yannick

doi:10.1109/icme.2006.262476

Cited by 40 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Libraries of computer vision and image processing have been developed in the OpenVIDIA [17] project and GPUCV [29]. This has aided development of higher level algorithms.…”

Section: Gpu Computer Visionmentioning

confidence: 99%

Using graphics devices in reverse: GPU-based Image Processing and Computer Vision

Fung

Mann

2008

2008 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

Graphics and vision are approximate inverses of each other: ordinarily Graphics Processing Units (GPUs) are used to convert "numbers into pictures" (i.e. computer graphics). In this paper, we discus the use of GPUs in approximately the reverse way: to assist in "converting pictures into numbers" (i.e. computer vision). For graphical operations, GPUs currently provide many hundreds of gigaflops of processing power. This paper discusses how this processing power is being harnessed for Image Processing and Computer Vision, thereby providing dramatic speedups on commodity, readily available graphics hardware. A brief review of algorithms mapped to the GPU by using the graphics API for vision is presented. The recent NVIDIA CUDA programming model is then introduced as a way of expressing program parallelism without the need for graphics expertise.

show abstract

“…Libraries of computer vision and image processing have been developed in the OpenVIDIA [17] project and GPUCV [29]. This has aided development of higher level algorithms.…”

Section: Gpu Computer Visionmentioning

confidence: 99%

Using graphics devices in reverse: GPU-based Image Processing and Computer Vision

Fung

Mann

2008

2008 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

show abstract

“…The GPUCV main goal is to allow the use of GPU in image processing with minimal effort [2,7]. It has a subset of the OpenCV functions ported to GPU.…”

Section: Solutions Availablementioning

confidence: 99%

“…In fact, computer vision researchers are creating libraries to accelerate calculations, like GPUCV [2] and OpenVidia [3].…”

Section: Introductionmentioning

confidence: 99%

Automatic Generation of Wrapper Code for Video Processing Functions

Dantas¹,

Barrera²

2011

L&NLM

View full text Add to dashboard Cite

-Processing video with GPUs requires the use of an API such as OpenGL or CUDA API. Recent advances are libraries such as GPUCV, with fast operators that take advantage of the GPU processing power but hide from the user its programming complexities. However the implementation of new operators is not as simple as it can be, and in GPUCV it is limited by the built-in templates. Here we describe a code generator that, from two kinds of directives merged in a shader source code, generates a wrapper code with all the OpenGL or CUDA API calls needed before calling the shader, simplifying the creation and maintenance of a library of video processing operators. The proposed library performance is better than GPUCV for almost all the tested operators.

show abstract

“…Unfortunately, the need to translate regular programs in to graphics metaphors has meant that only a small group of dedicated researchers with graphics knowledge used the power of the GPUs for non-graphical computing. The computer vision library OpenVidia [7] is an application of this type, as is GpuCV [12].…”

Section: Introductionmentioning

confidence: 99%