Paper Info
Title
Efficient exploitation of heterogeneous platforms for images features extraction
Abstract
Image processing algorithms present a necessary tool for various domains related to computer vision, such as video surveillance, medical imaging, pattern recognition, etc. However, these algorithms are hampered by their high consumption of both computing power and memory, which increase significantly when processing large sets of images. In this work, we propose a development scheme enabling an efficient exploitation of parallel (GPU) and heterogeneous platforms (Multi-CPU/Multi-GPU), for improving performance of single and multiple image processing algorithms. The proposed scheme allows a full exploitation of hybrid platforms based on efficient scheduling strategies. It enables also overlapping data transfers by kernels executions using CUDA streaming technique within multiple GPUs. We present also parallel and heterogeneous implementations of several features extraction algorithms such as edge and corner detection. Experimentations have been conducted using a set of high resolution images, showing a global speedup ranging from 5 to 30, by comparison with CPU implementations.
Year
DOI
Venue
2012
10.1109/IPTA.2012.6469569
Image Processing Theory, Tools and Applications
Keywords
Field
DocType
edge detection,feature extraction,graphics processing units,image resolution,parallel architectures,CUDA streaming technique,computer vision,computing power consumption,corner detection,data transfer,edge detection,heterogeneous platform,high resolution image,image feature extraction,image processing algorithm,medical imaging,memory consumption,multiCPU,multiGPU,parallel platform,pattern recognition,scheduling strategy,video surveillance,CUDA streaming,Efficient scheduling,Features extraction,GPU,Heterogeneous architectures
Computer vision,Feature detection (computer vision),Computer science,Edge detection,CUDA,Parallel computing,Feature extraction,Artificial intelligence,General-purpose computing on graphics processing units,Digital image processing,CUDA Pinned memory,Speedup
Conference
ISSN
ISBN
Citations 
2154-5111
978-1-4673-2585-1
2
PageRank 
References 
Authors
0.41
8
2
Name
Order
Citations
PageRank
Sidi Ahmed mahmoudi1369.63
Pierre Manneback2131.45