GPU-friendly multi-view stereo reconstruction using surfel representation and graph cuts
Computer Vision and Image Understanding
High performance predictable histogramming on GPUs: exploring and evaluating algorithm trade-offs
Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units
A code-based analytical approach for using separate device coprocessors in computing systems
ARCS'11 Proceedings of the 24th international conference on Architecture of computing systems
Proceedings of the 49th Annual Design Automation Conference
Image-based structural damage assessment with sensor fusion
Proceedings of the 3rd International Conference on Computing for Geospatial Research and Applications
Three-dimensional thinning algorithms on graphics processing units and multicore CPUs
Concurrency and Computation: Practice & Experience
Journal of Parallel and Distributed Computing
Efficient GPU implementation of the integral histogram
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume Part I
Glinda: a framework for accelerating imbalanced applications on heterogeneous platforms
Proceedings of the ACM International Conference on Computing Frontiers
| Hi-index | 0.00 |
In this paper, we construe key factors in design and evaluation of image processing algorithms on the massive parallel graphics processing units (GPUs) using the compute unified device architecture (CUDA) programming model. A set of metrics, customized for image processing, is proposed to quantitatively evaluate algorithm characteristics. In addition, we show that a range of image processing algorithms map readily to CUDA using multiview stereo matching, linear feature extraction, JPEG2000 image encoding, and nonphotorealistic rendering (NPR) as our example applications. The algorithms are carefully selected from major domains of image processing, so they inherently contain a variety of subalgorithms with diverse characteristics when implemented on the GPU. Performance is evaluated in terms of execution time and is compared to the fastest host-only version implemented using OpenMP. It is shown that the observed speedup varies extensively depending on the characteristics of each algorithm. Intensive analysis is conducted to show the appropriateness of the proposed metrics in predicting the effectiveness of an application for parallel implementation.