Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 8, Issue 10, Pages 4647-4656Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2015.2453411
Keywords
Classification; hyperspectral data; multicore processing; support vector machines (SVMs)
Categories
Funding
- Natural Science Foundation of China [41471356]
- Fundamental Research Funds for the Central Universities [2014QNA33]
- Priority Academic Program Development of Jiangsu Higher Education Institutions
Ask authors/readers for more resources
Support vector machine (SVM) is considered as one of the most powerful classifiers for hyperspectral remote sensing images. However, it has high computational cost. In this paper, we propose a novel two-level parallel computing framework to accelerate the SVM-based classification by utilizing CUDA and OpenMP. For a binary SVM classifier, the kernel function is optimized on GPU, and then a second-order working set selection (WSS) procedure is employed and optimized especially for GPU to reduce the cost of communication between GPU and host. In addition to the parallel binary SVM classifier on GPU as data-processing level parallelization, a multiclass SVM is addressed by a one-against-one approach in OpenMP, and several binary SVM classifiers are run simultaneously to conduct task-level parallelization. The experimental results show that the solver in this framework offered a speedup of 18.5x over the popular LIBSVM software in the training process for data with 200 bands, 13 classes, and 95 597 training samples, and 81.9x in the testing process for data with 103 bands, 9 classes, 1892 support vectors (SVs), and 42 776 testing samples.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available