Hyperspectral Image Analysis Using Cloud-Based Support Vector Machines
Authors:
Open Access
- 24 July 2024
- journal article
- research article
- Published by Springer Nature in SN Computer Science
- Vol. 5 (6) , 1-14
Abstract
Hyperspectral image processing techniques involve time-consuming calculations due to the large volume and complexity of the data. Indeed, hyperspectral scenes contain a wealth of spatial and spectral information thanks to the hundreds of narrow and continuous bands collected across the electromagnetic spectrum. Predictive models, particularly supervised machine learning classifiers, take advantage of this information to predict the pixel categories of images through a training set of real observations. Most notably, the Support Vector Machine (SVM) has demonstrate impressive accuracy results for image classification. Notwithstanding the performance offered by SVMs, dealing with such a large volume of data is computationally challenging. In this paper, a scalable and high-performance cloud-based approach for distributed training of SVM is proposed. The proposal address the overwhelming amount of remote sensing (RS) data information through a parallel training allocation. The implementation is performed over a memory-efficient Apache Spark distributed environment. Experiments are performed on a benchmark of real hyperspectral scenes to show the robustness of the proposal. Obtained results demonstrate efficient classification whilst optimising data processing in terms of training times.Keywords
Funding Information
- European Regional Development Funding (GR21040)
- Spanish Ministerio de Ciencia e Innovación (PID2019-110315RB-I0)
- European Regional Development Funding de la Universidad Nacional del Comahue para el Desarrollo Regional (Ceta-Ciemat)
- Junta de Extremadura (IB20040)
- European Regional Development Fund (0206_RAT_EOS_PC_6_E)
- Universidad de Extremadura
This publication has 44 references indexed in Scilit:
- Temporal difference-guided network for hyperspectral image change detectionInternational Journal of Remote Sensing, 2023
- Local aggregation and global attention network for hyperspectral image classification with spectral-induced aligned superpixel segmentationExpert Systems with Applications, 2023
- Heterogeneous gradient computing optimization for scalable deep neural networksThe Journal of Supercomputing, 2022
- Computer Vision Based Industrial and Forest Fire Detection Using Support Vector Machine (SVM)2022
- Heterogeneous model parallelism for deep neural networksNeurocomputing, 2021
- Training deep neural networks: a static load balancing approachThe Journal of Supercomputing, 2020
- Understanding urban landuse from the above and ground perspectives: A deep learning, multimodal solutionRemote Sensing of Environment, 2019
- Grid based satellite image processing platform for Earth observation application development2009
- Impact of platform heterogeneity on the design of parallel algorithms for morphological processing of high-dimensional image dataThe Journal of Supercomputing, 2007
- Imaging Spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS)Remote Sensing of Environment, 1998