Research on Hyperspectral Remote Sensing Image Classification Using Low-Power Heterogeneous Computing Architecture

doi:10.19678/j.issn.1000-3428.0065440

Abstract

Abstract: Hyperspectral image classification algorithms typically need to iteratively process the pixels in the image point by point, which significantly differ in computational complexity and parallelism.However, with the significant improvement of the spatial, spectral, and radiometric resolution for Hyperspectral Remote Sensing(HRS) images, these algorithms cannot fulfill the requirements to timely handle massive datasets.Therefore, a Low-Rank Sparse Subspace Clustering(LRSSC) algorithm based on heterogeneous Central Processing Unit(CPU)+Neural-network Processing Unit(NPU) computing architecture is designed by optimizing the NPU storage and computing integration mode and the implementation steps of the classification algorithm, thus offloading data-intensive computations to the NPU.This study uses NPU data-driven parallel computing with internal Artificial Intelligence(AI) acceleration to support real-time classification of massive hyperspectral data based on machine learning algorithms.Inspired by big.LITTLE computing paradigm, the proposed CPU+NPU computing architecture consists of 8 bit and low-precision bit-width NPUs to improve the overall throughput while reducing energy consumption during graph network inference.The simulations with Pavia University hyperspectral dataset show that compared with the LRSSC algorithms using the CPU computing architecture and heterogeneous CPU+Graphics Processing Unit(GPU) computing architecture, the computational speed of the designed LRSSC algorithm using the heterogeneous CPU+NPU computing architecture is significantly reduced by 3-14 times.

Key words: Hyperspectral Remote Sensing(HRS), image classification algorithm, Low-Rank Sparse Subspace Clustering(LRSSC), low-power heterogeneous computing architecture, Coded Aperture Snapshot Spectral Imaging(CASSI)

摘要： 高光谱图像分类算法通常需要逐点对图像中的像素点进行迭代处理，计算复杂度及并行程度存在较大差异。随着高光谱遥感图像空间、光谱和辐射分辨率的不断提升，这些算法无法满足实时处理海量遥感图像数据的需求。通过分析NPU存储计算一体化模式与遥感图像分类算法的实现步骤，设计低功耗CPU+NPU异构资源计算架构的低秩稀疏子空间聚类（LRSSC）算法，将数据密集型计算转移至NPU，并利用NPU数据驱动并行计算和内置AI加速，对基于机器学习算法的海量遥感数据进行实时分类。受到big.LITTLE计算范式的启发，CPU+NPU异构资源计算架构由8 bit和低精度位宽NPU共同组成以提高整体吞吐量，同时减少图网络推理过程中的能量损耗。实验结果表明，与CPU计算架构和CPU+GPU异构计算架构的LRSSC算法相比，CPU+NPU异构计算架构的LRSSC算法在Pavia University遥感数据集下的计算速度提升了3~14倍。

关键词: 高光谱遥感, 图像分类算法, 低秩稀疏子空间聚类, 低功耗异构计算架构, 编码孔径快照光谱成像

CLC Number:

TP391

LIU Pengfei, ZHU Jianchen, WAN Liangyi, JIANG Bo. Research on Hyperspectral Remote Sensing Image Classification Using Low-Power Heterogeneous Computing Architecture[J]. Computer Engineering, 2022, 48(12): 9-15,23.

刘鹏飞, 朱健晨, 万良易, 江波. 低功耗异构计算架构的高光谱遥感图像分类研究[J]. 计算机工程, 2022, 48(12): 9-15,23.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0065440

http://www.ecice06.com/EN/Y2022/V48/I12/9

Figures/Tables 9

References

[1] 赫晓慧, 宋定君, 李盼乐, 等.融合多尺度特征的遥感影像道路提取方法[J].计算机工程, 2022, 48(8):196-205. HE X H, SONG D J, LI P L, et al.Remote sensing image road extraction method combined with multi-scale features[J].Computer Engineering, 2022, 48(8):196-205.(in Chinese)
[2] 梁文韬, 康雁, 李浩, 等.基于复杂度聚类的自适应遥感场景分类[J].计算机工程, 2020, 46(12):254-261, 269. LIANG W T, KANG Y, LI H, et al.Adaptive remote sensing scene classification based on complexity clustering[J].Computer Engineering, 2020, 46(12):254-261, 269.(in Chinese)
[3] SCHOWENGERDT R A.Remote sensing:models and methods for image processing[M].[S.l.]:Elsevier, 2006.
[4] PAJARES G.Overview and current status of remote sensing applications based on Unmanned Aerial Vehicles(UAVs)[J].Photogrammetric Engineering & Remote Sensing, 2015, 81(4):281-329.
[5] PENG M M, LU Z, ZHAO C Y, et al.Mapping land subsidence and aquifer system properties of the Willcox Basin, Arizona, from InSAR observations and independent component analysis[J].Remote Sensing of Environment, 2022, 271:112894.
[6] WAGNER B, EGERER M.Application of UAV remote sensing and machine learning to model and map land use in urban gardens[J].Journal of Urban Ecology, 2022, 8(1):1-8.
[7] DEREN L, ZHANG L P, XIA G S. Automatic analysis and mining of remote sensing big data[J].Acta Geodaetica et Cartographica Sinica, 2014, 43(12):1211.
[8] 王道累, 杜文斌, 刘易腾, 等.基于密集连接与特征增强的遥感图像检测[J].计算机工程, 2022, 48(6):251-256, 262. WANG D L, DU W B, LIU Y T, et al.Remote sensing images detection based on dense connection and feature enhancement[J].Computer Engineering, 2022, 48(6):251-256, 262.(in Chinese)
[9] 张艳, 杜会娟, 孙叶美, 等.基于改进SSD算法的遥感图像目标检测[J].计算机工程, 2021, 47(9):252-258, 265. ZHANG Y, DU H J, SUN Y M, et al.Object detection in remote sensing images based on improved SSD algorithm[J].Computer Engineering, 2021, 47(9):252-258, 265.(in Chinese)
[10] KUSSUL N, LAVRENIUK M, SKAKUN S, et al.Deep learning classification of land cover and crop types using remote sensing data[J].IEEE Geoscience and Remote Sensing Letters, 2017, 14(5):778-782.
[11] ZHANG Y, ZHENG X T, LU X Q.Pairwise comparison network for remote-sensing scene classification[J].IEEE Geoscience and Remote Sensing Letters, 2022, 19:1-5.
[12] VIDAL R.Subspace clustering[J].IEEE Signal Processing Magazine, 2011, 28(2):52-68.
[13] LUXBURG U.A tutorial on spectral clustering[J].Statistics and Computing, 2007, 17(4):395-416.
[14] ELHAMIFAR E, VIDAL R.Sparse subspace clustering:algorithm, theory, and applications[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11):2765-2781.
[15] STONE J E, GOHARA D, SHI G C.OpenCL:a parallel programming standard for heterogeneous computing systems[J].Computing in Science & Engineering, 2010, 12(3):66-73.
[16] 梁美彦, 任竹云, 李光辉, 等.GPU加速条件下基于相位补偿反投影算法的太赫兹ISAR成像[J].红外与毫米波学报, 2022(2):448-456. LIANG M Y, REN Z Y, LI G H, et al.THz ISAR imaging using GPU-accelerated phase compensated back projection algorithm[J].Journal of Infrared and Millimeter Waves, 2022(2):448-456.(in Chinese)
[17] 钱裳云, 邵志远, 郑然, 等.图数据库中基于GPU的图分析计算方法[J].计算机工程, 2021, 47(6):52-59. QIAN S Y, SHAO Z Y, ZHENG R, et al.GPU-based graph analysis and computation method for graph database[J].Computer Engineering, 2021, 47(6):52-59.(in Chinese)
[18] CASS S.Taking AI to the edge:Google's TPU now comes in a maker-friendly package[J].IEEE Spectrum, 2019, 56(5):16-17.
[19] HICKMANN B, CHEN J, ROTZIN M, et al.Intel Nervana Neural Network Processor-T(NNP-T) fused floating point many-term dot product[C]//Proceedings of the 27th Symposium on Computer Arithmetic.Washington D.C., USA:IEEE Press, 2020:133-136.
[20] WAGADARIKAR A, JOHN R, WILLETT R, et al.Single disperser design for coded aperture snapshot spectral imaging[J].Applied Optics, 2008, 47(10):44-51.
[21] ARCE G R, BRADY D J, CARIN L, et al.Compressive coded aperture spectral imaging:an introduction[J].IEEE Signal Processing Magazine, 2014, 31(1):105-115.
[22] VIDAL R, FAVARO P.Low Rank Subspace Clustering(LRSC)[J].Pattern Recognition Letters, 2014, 43:47-61.
[23] FANG X Z, XU Y, LI X L, et al.Robust semi-supervised subspace clustering via non-negative low-rank representation[J].IEEE Transactions on Cybernetics, 2016, 46(8):1828-1838.
[24] BOYD S, PARIKH N, CHU E, et al.Distributed optimization and statistical learning via the alternating direction method of multipliers[J].Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers, 2011, 3(1):1-122.
[25] MAKANTASIS K, KARANTZALOS K, DOULAMIS A, et al.Deep supervised learning for hyperspectral data classification through convolutional neural networks[C]//Proceedings of IEEE International Geoscience and Remote Sensing Symposium.Washington D.C., USA:IEEE Press, 2015:4959-4962.
[26] ZHAO W Z, DU S H.Spectral-spatial feature extraction for hyperspectral image classification:a dimension reduction and deep learning approach[J].IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8):4544-4554.

Please choose a citation manager

Content to export