Accelerated hyperspectral image recursive hierarchical segmentation using GPUs, multicore CPUs, and hybrid CPU/GPU cluster

Hossam, Mohamed; Ebied, Hala M.; Abdelaziz, M.; Tolba, Mohamed F.

doi:10.1007/s11554-014-0464-4

Cited by 11 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a result of the increasing demand for high-performance graphic computing and deep learning computing, the computing power of graphic processing units (GPUs) has made great achievements and been widely applied for general purposes in recent years. Considering the excellent features, e.g., light weight, small size, and low cost, GPUs are widely utilized to improve the computing performance in hyperspectral data applications [19,20,21,22,23,24,34,35,36,37,38,39]. Compute unified device architecture (CUDA) (), introduced by NVidia corporation, provides a development environment for creating high performance GPU-accelerated applications.…”

Section: Multi-gpus-based Parallel Design Of Acoeementioning

confidence: 99%

Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images

Gao

Sun

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

Spectral unmixing is a vital procedure in hyperspectral remote sensing image exploitation. The linear mixture model has been widely utilized to unmix hyperspectral images by extracting a set of pure spectral signatures, called endmembers in hyperspectral jargon, and estimating their respective fractional abundances in each pixel of the scene. Many algorithms have been proposed to extract endmembers automatically, which is a critical step in the spectral unmixing chain. In recent years, the ant colony optimization (ACO) algorithm has been developed for endmember extraction from hyperspectral data, which was regarded as a combinatorial optimization problem. Although the ACO for endmember extraction (ACOEE) can acquire accurate endmember results, its high computational complexity has limited its application in the hyperspectral data analysis. The GPUs parallel computing technique can be utilized to improve the computational performance of ACOEE, but the architecture of GPUs determines that the ACOEE should be redesigned to take full advantage of computing resources on GPUs. In this paper, a multiple sub-ant-colony-based parallel design of ACOEE was proposed, in which an innovative mechanism of local pheromone for sub-ant-colonies is utilized to enable ACOEE to be preferably executed on the multi-GPU system. The proposed method can avoid much synchronization among different GPUs to affect the computational performance improvement. The experiments on two real hyperspectral datasets demonstrated that the computational performance of ACOEE significantly benefited from the proposed methods.

show abstract

Section: Multi-gpus-based Parallel Design Of Acoeementioning

confidence: 99%

Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images

Gao

Sun

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Альтернативным подходом к увеличению производительности может служить также привлечение графических процессоров. В работах [21,22] показано, что их использование позволяет повысить производительность алгоритмов на несколько порядков. Преимущество использования графических процессоров для реализации алгоритма AC заключается в возможности вычислять расстояния между объектами и центрами кластеров одновременно для L разбиений на каждой итерации K-means.…”

Section: рис 3 среднее время выполнения последовательной и параллелunclassified

Centroid averaging algorithm for a clustering ensemble

2017

View full text Add to dashboard Cite

Аннотация В статье рассматривается коллективный подход к решению задачи кластерного анализа. Предложен алгоритм усреднения центроидов, позволяющий построить консенсусное разбиение выборки на кластеры, используя набор разбиений этой выборки любым центроидным алгоритмом. Приведены результаты применения алгоритма к модельным данным и для сегментации гиперспектральных изображений с шумовыми каналами. Рассмотрены некоторые детали реализации в многопоточном окружении, позволяющие увеличить производительность алгоритма. Ключевые слова: кластерный ансамбль, K-means, центроид, анализ гиперспектральных изображений. Цитирование: Татарников, В.В. Алгоритм усреднения центроидов для построения кластерного ансамбля / В.В. Татарников, И.А. Пестунов, В.Б. Бериков // Компьютерная опти

show abstract

“…In recent years, graphic processing unit (GPU)-based highperformance computing technology has been increasingly applied in large-scale computing scenarios, such as mathematical calculations, image processing, computational biology and chemistry and fluid dynamics simulation [49][50][51][52][53][54][55]. Early works on GPU-based processing for RS data have been conducted by numerous researchers [56][57][58][59][60][61][62]. Wei [63] explored a GPU-based implementation of the extended Kalman filter.…”

Section: Introductionmentioning

confidence: 99%

Parallel Computing for Obtaining Regional Scale Rice Growth Conditions Based on WOFOST and Satellite Images

Zhao

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Accelerated hyperspectral image recursive hierarchical segmentation using GPUs, multicore CPUs, and hybrid CPU/GPU cluster

Cited by 11 publications

References 23 publications

Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images

Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images

Centroid averaging algorithm for a clustering ensemble

Parallel Computing for Obtaining Regional Scale Rice Growth Conditions Based on WOFOST and Satellite Images

Contact Info

Product

Resources

About