A Survey of GPU Implementations for Hyperspectral Image Classification in Remote Sensing

Abstract Effective classification algorithm is a key to extracting interesting and useful information from hyperspectral images (HSI). Many researchers have worked on developing effective algorithms for HSI classifications and research is still ongoing to improve on the existing algorithms. HSI classification is a complex task due to the nature of the data involved and external factors that affect the accuracy of the classification results. Due to the complexity of this problem and the enormous computing time involved, researchers have focused their work on developing parallel algorithms. GPU-accelerated computing is the use of a graphics processing unit (GPU) together with a CPU to accelerate deep learning and other computing intensive applications. The general purpose graphic processing units have been considered as one of the most common co-processors that can help accelerate parallel applications. Implementation of parallel algorithms on GPU has significantly improved the classification of hyperspectral images. This paper is focused on the study of the available GPU implementations. It examines the performance, summarizes the major developments and concerns in the research work. It also describes the major challenges in GPU implementations for HIS.

[1]  Tao Li,et al.  Cube-CNN-SVM: A Novel Hyperspectral Image Classification Method , 2016, 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI).

[2]  Felix Hueber,et al.  Hyperspectral Imaging Techniques For Spectral Detection And Classification , 2016 .

[3]  Antonio J. Plaza,et al.  Parallel Hyperspectral Unmixing on GPUs , 2014, IEEE Geoscience and Remote Sensing Letters.

[4]  Deyu Meng,et al.  Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network , 2017, IEEE Transactions on Image Processing.

[5]  Bo Du,et al.  Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art , 2016, IEEE Geoscience and Remote Sensing Magazine.

[6]  M. Cochrane.  Using vegetation reflectance variability for species level classification of hyperspectral data , 2000 .

[7]  M. Prabukumar,et al.  Survey on classification methods for hyper spectral remote sensing imagery , 2017, 2017 International Conference on Intelligent Computing and Control Systems (ICICCS).

[8]  David A. Landgrebe,et al.  Signal Theory Methods in Multispectral Remote Sensing , 2003 .

[9]  Jonathan Li,et al.  Bayesian Classification of Hyperspectral Imagery Based on Probabilistic Sparse Representation and Markov Random Field , 2014, IEEE Geoscience and Remote Sensing Letters.

[10]  Jon Atli Benediktsson,et al.  Recent Advances in Techniques for Hyperspectral Image Processing , 2009 .

[11]  David A. Landgrebe.  Multispectral land sensing: where from, where to? , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Helmi Zulhaidi Mohd Shafri,et al.  A review on hyperspectral remote sensing for homogeneous and heterogeneous forest biodiversity assessment , 2010 .

[13]  Jen-Tzung Chien,et al.  Discriminant Waveletfaces and Nearest Feature Classifiers for Face Recognition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Vidya Manian,et al.  Parallel implementation of nonlinear dimensionality reduction methods applied in object segmentation using CUDA in GPU , 2011, Defense + Commercial Sensing.

[15]  Francisco Argüello,et al.  Efficient ELM-Based Techniques for the Classification of Hyperspectral Remote Sensing Images on Commodity GPUs , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Shadi G. Alawneh,et al.  Fast Quadratic Discriminant Analysis Using GPGPU for Sea Ice Forecasting , 2015, 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems.

[17]  I. Renhorn,et al.  Military applications of hyperspectral imagery , 2006, SPIE Defense + Commercial Sensing.

[18]  Liangpei Zhang,et al.  On Combining Multiple Features for Hyperspectral Remote Sensing Image Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Antonio J. Plaza,et al.  Real-Time Implementation of the Vertex Component Analysis Algorithm on GPUs , 2013, IEEE Geoscience and Remote Sensing Letters.

[20]  Gregory Piatetsky-Shapiro,et al.  High-Dimensional Data Analysis: The Curses and Blessings of Dimensionality , 2000 .

[21]  Antonio J. Plaza,et al.  A Hybrid CPU–GPU Real-Time Hyperspectral Unmixing Chain , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  Antonio J. Plaza,et al.  GPU Implementation of an Automatic Target Detection and Classification Algorithm for Hyperspectral Image Analysis , 2013, IEEE Geoscience and Remote Sensing Letters.

[23]  Richard A. Hallett,et al.  Ash decline assessment in emerald ash borer-infested regions: A test of tree-level, hyperspectral technologies , 2008 .

[24]  Kurt Keutzer,et al.  Fast support vector machine training and classification on graphics processors , 2008, ICML '08.

[25]  Stan Z. Li,et al.  Face recognition using the nearest feature line method , 1999, IEEE Trans. Neural Networks.

[26]  Chein-I Chang,et al.  Hyperspectral Imaging , 2003, Springer US.

[27]  Jun Li,et al.  Parallel Spatial–Spectral Hyperspectral Image Classification With Sparse Representation and Markov Random Fields on GPUs , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[28]  Antonio J. Plaza,et al.  GPU Implementation of Composite Kernels for Hyperspectral Image Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[29]  Antonio J. Plaza,et al.  FPGA Implementation of the N-FINDR Algorithm for Remotely Sensed Hyperspectral Image Analysis , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Hong Sun,et al.  Unsupervised Feature Learning Via Spectral Clustering of Multidimensional Patches for Remotely Sensed Scene Classification , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[31]  Tao Li,et al.  GCN: GPU-Based Cube CNN Framework for Hyperspectral Image Classification , 2017, 2017 46th International Conference on Parallel Processing (ICPP).

[32]  John R. Miller,et al.  Hyperspectral Data Segmentation and Classification in Precision Agriculture: A Multi-Scale Analysis , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[33]  Santiago Velasco-Forero,et al.  Accelerating hyperspectral manifold learning using graphical processing units , 2009, Defense + Commercial Sensing.

[34]  Yaohua Luo,et al.  Hyperspectral Remote Sensing Classification Processing Parallel Computing Research Based on GPU , 2012, 2012 International Conference on Computer Science and Electronics Engineering.

[35]  Qian Du,et al.  High Performance Computing for Hyperspectral Remote Sensing , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Dennis K. Peters,et al.  Ice Simulation Using GPGPU , 2012, 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems.

[37]  Bo Du,et al.  GPU Parallel Implementation of Isometric Mapping for Hyperspectral Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[38]  Jocelyn Chanussot,et al.  Introduction to the Issue on Advances in Hyperspectral Data Processing and Analysis , 2015, IEEE J. Sel. Top. Signal Process..

[39]  Antonio J. Plaza,et al.  Real-Time Implementation of the Pixel Purity Index Algorithm for Endmember Identification on GPUs , 2014, IEEE Geoscience and Remote Sensing Letters.

[40]  Kandarpa Kumar Sarma,et al.  Hyperspectral Remote Sensing Classifications: A Perspective Survey , 2016, Trans. GIS.

[41]  Gary A. Shaw,et al.  Hyperspectral Image Processing for Automatic Target Detection Applications , 2003 .

[42]  David A. Landgrebe,et al.  Supervised classification in high-dimensional space: geometrical, statistical, and asymptotical properties of multivariate data , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[43]  Jon Atli Benediktsson,et al.  Very High-Resolution Remote Sensing: Challenges and Opportunities [Point of View] , 2012, Proc. IEEE.

[44]  Teferi D. Tsegaye,et al.  Relationship Between Hyperspectral Reflectance, Soil Nitrate-Nitrogen, Cotton Leaf Chlorophyll, and Cotton Yield: A Step Toward Precision Agriculture , 2003 .

[45]  Jon Atli Benediktsson,et al.  Advances in Spectral-Spatial Classification of Hyperspectral Images , 2013, Proceedings of the IEEE.

[46]  Bo Du,et al.  Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding , 2015, Pattern Recognit..

[47]  Antonio J. Plaza,et al.  GPU implementation of hyperspectral image classification based on weighted Markov random fields , 2016, 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[48]  Jon Atli Benediktsson,et al.  Hyperspectral Unmixing on GPUs and Multi-Core Processors: A Comparison , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[49]  Francisco Argüello,et al.  Spectral–Spatial Classification of Hyperspectral Images Using Wavelets and Extended Morphological Profiles , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[50]  Antonio J. Plaza,et al.  Parallel and Distributed Dimensionality Reduction of Hyperspectral Data on Cloud Computing Architectures , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[51]  J. Benediktsson,et al.  New Frontiers in Spectral-Spatial Hyperspectral Image Classification: The Latest Advances Based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning , 2018, IEEE Geoscience and Remote Sensing Magazine.

[52]  Tao Li,et al.  HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image , 2018, 2018 International Conference on Audio, Language and Image Processing (ICALIP).

[53]  Jun Li,et al.  Parallel Implementation of Sparse Representation Classifiers for Hyperspectral Imagery on GPUs , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[54]  Liang Xiao,et al.  Hyperspectral Image Classification Using Kernel Sparse Representation and Semilocal Spatial Graph Regularization , 2014, IEEE Geoscience and Remote Sensing Letters.

[55]  J. Anthony Gualtieri,et al.  Support vector machines for hyperspectral remote sensing classification , 1999, Other Conferences.

[56]  Gustavo Marrero Callicó,et al.  Accelerating the K-Nearest Neighbors Filtering Algorithm to Optimize the Real-Time Classification of Human Brain Tumor in Hyperspectral Images , 2018, Sensors.

[57]  Zhihui Wei,et al.  GPU Parallel Optimization of Hyperspectral Image Kernel Sparse Representation Classification Based on Spatial-Spectral Graph Regularization , 2016, 2016 International Conference on Advanced Cloud and Big Data (CBD).

[58]  Jon Atli Benediktsson,et al.  Wavelet-Based Classification of Hyperspectral Images Using Extended Morphological Profiles on Graphics Processing Units , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[59]  Qian Du,et al.  GPU Parallel Implementation of Support Vector Machines for Hyperspectral Image Classification , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[60]  Kevin Skadron,et al.  Scalable parallel programming , 2008, 2008 IEEE Hot Chips 20 Symposium (HCS).

[61]  Julien Michel,et al.  Remote Sensing Processing: From Multicore to GPU , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[62]  E. Cloutis,et al.  Review Article Hyperspectral geological remote sensing: evaluation of analytical techniques , 1996 .

[63]  Antonio J. Plaza,et al.  Parallel Hyperspectral Image and Signal Processing [Applications Corner] , 2011, IEEE Signal Processing Magazine.

[64]  Dennis K. Peters,et al.  2D Triangulation of Polygons on CUDA , 2013, 2013 International Conference on High Performance Computing & Simulation (HPCS).

[65]  Thomas Schmid,et al.  Multisensor approach to determine changes of wetland characteristics in semiarid environments (central Spain) , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[66]  Shinpei Kato,et al.  Operating Systems Challenges for GPU Resource Management , 2011 .

[67]  Lena Chang,et al.  Incenter-based nearest feature space method for hyperspectral image classification using GPU , 2014, 2014 20th IEEE International Conference on Parallel and Distributed Systems (ICPADS).

[68]  Jun Li,et al.  GPU Parallel Implementation of Spatially Adaptive Hyperspectral Image Classification , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[69]  Antonio J. Plaza,et al.  A suite of parallel algorithms for efficient band selection from hyperspectral images , 2018, Journal of Real-Time Image Processing.

[70]  John R. Williams,et al.  Parallel multiclass classification using SVMs on GPUs , 2010, GPGPU-3.