GpuCV: A GPU-Accelerated Framework for Image Processing and Computer Vision

Allusse, Yannick; Horain, Patrick; Agarwal, Ankit; Saipriyadarshan, Cindula

doi:10.1007/978-3-540-89646-3_42

Cited by 35 publications

(26 citation statements)

References 7 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Libraries such as GPUCV [1], NVIDIA Performance Primitives (NPP) and CUVIlib [20] provide GPU implementations for a range of algorithms.…”

Section: B Image Processingmentioning

confidence: 99%

“…It uses the on-chip shared memory to store intermediate results in order to access the off-chip memory coalesced. 1 Parallelism can be higher depending on the algorithm…”

Section: A Pixel To Pixelmentioning

confidence: 99%

“…The generation of lines 18-20 is relatively straightforward, and is performed by: (1) off-chip to on-chip address transformation, and (2) storing intermediate results in the first element to create the tree structure. To generate lines 7-12, we use rewrite rules 1 to: (1) transform off-chip to on-chip addresses, (2) execute the first computation, and (3) extend the computation with an else statement to ensure a load. Rewrite rules and the skeleton implementation ensure hardware efficiency according to NVIDIA guidelines [10], enabling sequential addressing, on-chip shared memory, coalesced loads, loop unrolling and limited bank conflicts.…”

Section: E An Illustrating Examplementioning

confidence: 99%

See 2 more Smart Citations

Skeleton-based automatic parallelization of image processing algorithms for GPUs

Nugteren

Corporaal

Mesman

2011

2011 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation

View full text Add to dashboard Cite

Abstract-Graphics Processing Units (GPUs) are becoming increasingly important in high performance computing. To maintain high quality solutions, programmers have to efficiently parallelize and map their algorithms. This task is far from trivial, leading to the necessity to automate this process.In this paper, we present a technique to automatically parallelize and map sequential code on a GPU, without the need for code-annotations. This technique is based on skeletonization and is targeted at image processing algorithms. Skeletonization separates the structure of a parallel computation from the algorithm's functionality, enabling efficient implementations without requiring architecture knowledge from the programmer. We define a number of skeleton classes, each enabling GPU specific parallelization techniques and optimizations, including automatic thread creation, on-chip memory usage and memory coalescing.Recently, similar skeletonization techniques have been applied to GPUs. Our work uses domain specific skeletons and a finergrained classification of algorithms. Comparing skeleton-based parallelization to existing GPU code generators in general, we potentially achieve a higher hardware efficiency by enabling algorithm restructuring through skeletons.In a set of benchmarks, we show that the presented skeletonbased approach generates highly optimized code, achieving high data throughput. Additionally, we show that the automatically generated code performs close or equal to manually mapped and optimized code. We conclude that skeleton-based parallelization for GPUs is promising, but we do believe that future research must focus on the identification of a finer-grained and complete classification.

show abstract

“…Libraries such as GPUCV [1], NVIDIA Performance Primitives (NPP) and CUVIlib [20] provide GPU implementations for a range of algorithms.…”

Section: B Image Processingmentioning

confidence: 99%

“…It uses the on-chip shared memory to store intermediate results in order to access the off-chip memory coalesced. 1 Parallelism can be higher depending on the algorithm…”

Section: A Pixel To Pixelmentioning

confidence: 99%

Section: E An Illustrating Examplementioning

confidence: 99%

See 1 more Smart Citation

Skeleton-based automatic parallelization of image processing algorithms for GPUs

Nugteren

Corporaal

Mesman

2011

2011 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation

View full text Add to dashboard Cite

show abstract

“…GpuCV [4] and OpenVidia [5] are computer vision libraries that completely hide the underlying GPU architecture. Since they act as black box solutions it is difficult to combine them with existing multimedia applications that use the CPU.…”

Section: Related Workmentioning

confidence: 99%

Stream Processing on GPUs Using Distributed Multimedia Middleware

Repplinger

Slusallek

2010

Parallel Processing and Applied Mathematics

View full text Add to dashboard Cite

Abstract. Available GPUs provide increasingly more processing power especially for multimedia and digital signal processing. Despite the tremendous progress in hardware and thus processing power, there are and always will be applications that require using multiple GPUs either running inside the same machine or distributed in the network due to computational intensive processing algorithms. Existing solutions for developing applications for GPUs still require a lot of hand-optimization when using multiple GPUs inside the same machine and provide in general no support for using remote GPUs distributed in the network. In this paper we address this problem and show that an open distributed multimedia middleware, like the Network-Integrated Multimedia Middleware (NMM), is able (1) to seamlessly integrate processing components using GPUs while completely hiding GPU specific issues from the application developer, (2) to transparently combine processing components using GPUs or CPUs, and (3) to transparently use local and remote GPUs for distributed processing.

show abstract

“…The second problem is addressed by deblurring of the output using median filter. GPU based efficient solutions for data parallel image processing applications have been proposed by many authors [5][6] [7] [8]. Like many image processing applications, Steering Kernel Regression also has inherent data parallelism.…”

Section: Introductionmentioning

confidence: 99%

Median Based Parallel Steering Kernel Regression for Image Reconstruction

Khalandhar¹,

Ram²,

Rao³

et al. 2013

Computer Science &Amp; Information Technology ( CS &Amp; IT )

View full text Add to dashboard Cite

Image reconstruction is a process of obtaining the original image from corrupted data. Applications of image reconstruction include Computer Tomography, radar imaging, weather forecasting etc. Recently steering kernel regression method has been applied for image reconstruction [1]. There are two major drawbacks in this technique. Firstly, it is computationally intensive. Secondly, output of the algorithm suffers form spurious edges (especially in case of denoising). We propose a modified version of Steering Kernel Regression called as Median Based Parallel Steering Kernel Regression Technique. In the proposed algorithm the first problem is overcome by implementing it in on GPUs and multi-cores. The second problem is addressed by a gradient based suppression in which median filter is used.Our algorithm gives better output than that of the Steering Kernel Regression. The results are compared using Root Mean Square Error(RMSE). Our algorithm has also shown a speedup of 21x using GPUs and shown speedup of 6x using multi-cores.

show abstract

GpuCV: A GPU-Accelerated Framework for Image Processing and Computer Vision

Cited by 35 publications

References 7 publications

Skeleton-based automatic parallelization of image processing algorithms for GPUs

Skeleton-based automatic parallelization of image processing algorithms for GPUs

Stream Processing on GPUs Using Distributed Multimedia Middleware

Median Based Parallel Steering Kernel Regression for Image Reconstruction

Contact Info

Product

Resources

About