Skip to main content

2018 | OriginalPaper | Buchkapitel

Study of Multilevel Parallel Algorithm of KPCA for Hyperspectral Images

verfasst von : Rulin Xu, Chang Gao, Jingfei Jiang

Erschienen in: Theoretical Computer Science

Verlag: Springer Singapore

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Hyperspectral remote sensing image data has been widely used in a variety of applications due to its continuous spectrum and high spectral resolution. However, reducing huge dimensions with high data relevance is time-consuming, and parallel processing is required to accelerate this process. In the previous work, the KPCA (Kernel Principal Component Analysis), a nonlinear dimensionality reduction method was studied, and a parallel KPCA algorithm was proposed based on heterogeneous system with a single GPU, and achieved the desired experimental results. However, as data scale grows, the proposed solution would consume all the available memory on a single node and encounter performance bottleneck. Therefore, to tackle the limitation of insufficient memory caused by the reduction of large-scale hyperspectral data dimension, in this paper the intra-node parallelization using multi-core CPUs and many-core GPUs are exploited to improve the parallel hierarchy of distributed-storage KPCA. Finally, we designed and implemented a multilevel hybrid parallel KPCA algorithm that achieves 2.75–9.27 times speedup compared to the traditional coarse-grained parallel KPCA method on MPI.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Zhang, Z., Zhang, L.: Hyperspectral Remote Sensing. Wuhan University Press, Wuhan (2005). (in Chinese) Zhang, Z., Zhang, L.: Hyperspectral Remote Sensing. Wuhan University Press, Wuhan (2005). (in Chinese)
2.
Zurück zum Zitat Ainsworth, T.L., Bachmann, C.M., Fusina, R.A.: Local intrinsic dimensionality of hyper-spectral imagery from non-linear manifold coordinate. In: IEEE International on Geoscience and Remote Sensing Symposium, pp. 1541–1542 (2007) Ainsworth, T.L., Bachmann, C.M., Fusina, R.A.: Local intrinsic dimensionality of hyper-spectral imagery from non-linear manifold coordinate. In: IEEE International on Geoscience and Remote Sensing Symposium, pp. 1541–1542 (2007)
3.
Zurück zum Zitat Gao, C., Zhou, H., Fang, M.: Parallel Algorithm and Performance Optimization of Kernel Principal Component Analysis on GPUs for Dimensionality Reduction of HIS, HPC China, pp. 611–614 (2016) Gao, C., Zhou, H., Fang, M.: Parallel Algorithm and Performance Optimization of Kernel Principal Component Analysis on GPUs for Dimensionality Reduction of HIS, HPC China, pp. 611–614 (2016)
4.
Zurück zum Zitat Bernabe, S., Lopez, S., Plaza, A., Sarmiento, R.: GPU implementation of an automatic target detection and classification algorithm for hyperspectral image analysis. IEEE Geosci. Remote Sens. Lett. 10(2), 221–225 (2013)CrossRef Bernabe, S., Lopez, S., Plaza, A., Sarmiento, R.: GPU implementation of an automatic target detection and classification algorithm for hyperspectral image analysis. IEEE Geosci. Remote Sens. Lett. 10(2), 221–225 (2013)CrossRef
5.
Zurück zum Zitat Lokman, G., Yilmaz, G.: Anomaly detection and target recognition with hyperspectral images. In: 2014 22nd Signal Processing and Communications Applications Conference (SIU), pp. 1019–1022, 23–25 2014 Lokman, G., Yilmaz, G.: Anomaly detection and target recognition with hyperspectral images. In: 2014 22nd Signal Processing and Communications Applications Conference (SIU), pp. 1019–1022, 23–25 2014
6.
Zurück zum Zitat Agathos, A., Li, J., Petcu, D., Plaza, A.: Multi-GPU implementation of the minimum volume simplex analysis algorithm for hyperspectral unmixing. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 7(6), 2281–2296 (2014)CrossRef Agathos, A., Li, J., Petcu, D., Plaza, A.: Multi-GPU implementation of the minimum volume simplex analysis algorithm for hyperspectral unmixing. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 7(6), 2281–2296 (2014)CrossRef
7.
Zurück zum Zitat Torti, E., Danese, G., Leporati, F., Plaza, A.: A hybrid CPU-GPU real-time hyperspectral unmixing chain. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 9(2), 945–951 (2016)CrossRef Torti, E., Danese, G., Leporati, F., Plaza, A.: A hybrid CPU-GPU real-time hyperspectral unmixing chain. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 9(2), 945–951 (2016)CrossRef
8.
Zurück zum Zitat Sanchez, S., Ramalho, R., Sousa, L., Plaza, A.: Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs. J. Real-Time Image Process. 10, 469–483 (2012)CrossRef Sanchez, S., Ramalho, R., Sousa, L., Plaza, A.: Real-time implementation of remotely sensed hyperspectral image unmixing on GPUs. J. Real-Time Image Process. 10, 469–483 (2012)CrossRef
9.
Zurück zum Zitat Keymeulen, D., Aranki, N., Hopson, B., Kiely, A., Klimesh, M., Benkrid, K.: GPU lossless hyperspectral data compression for space applications. In: 2012 IEEE Aerospace Conference, pp. 1–9, 3–10 March 2012 Keymeulen, D., Aranki, N., Hopson, B., Kiely, A., Klimesh, M., Benkrid, K.: GPU lossless hyperspectral data compression for space applications. In: 2012 IEEE Aerospace Conference, pp. 1–9, 3–10 March 2012
10.
Zurück zum Zitat Santos, L., Magli, E., Vitulli, R., Lopez, J.F., Sarmiento, R.: Highly-parallel GPU architecture for lossy hyperspectral image compression. IEEE Sel. Topics Appl. Earth Obs. Remote Sens. 6(2), 670–681 (2013)CrossRef Santos, L., Magli, E., Vitulli, R., Lopez, J.F., Sarmiento, R.: Highly-parallel GPU architecture for lossy hyperspectral image compression. IEEE Sel. Topics Appl. Earth Obs. Remote Sens. 6(2), 670–681 (2013)CrossRef
11.
Zurück zum Zitat ElMaghrbay, M., Ammar, R., Rajasekaran, S.: Fast GPU algorithms for endmember extraction from hyperspectral images. In: 2012 IEEE Symposium Computers and Communications (ISCC), pp. 000631–000636, 1–4 July 2012 ElMaghrbay, M., Ammar, R., Rajasekaran, S.: Fast GPU algorithms for endmember extraction from hyperspectral images. In: 2012 IEEE Symposium Computers and Communications (ISCC), pp. 000631–000636, 1–4 July 2012
12.
Zurück zum Zitat Fang, M., Zhou, H., Shen, X.: Multilevel parallel algorithm of PCA dimensionality reduction for hyperspectral image on GPU. Dongbei Daxue Xuebao/J. Northeastern Univ. 35(S1), 238–243 (2014). (in Chinese) Fang, M., Zhou, H., Shen, X.: Multilevel parallel algorithm of PCA dimensionality reduction for hyperspectral image on GPU. Dongbei Daxue Xuebao/J. Northeastern Univ. 35(S1), 238–243 (2014). (in Chinese)
13.
Zurück zum Zitat Fang, M., Zhou, H., Zhang, W., Shen, X.: A parallel algorithm of FastICA dimensionality reduction for hyperspectral image on GPU. Dongbei Daxue Xuebao/J. Northeastern Univ. 37(4), 65–70 (2015). (in Chinese) Fang, M., Zhou, H., Zhang, W., Shen, X.: A parallel algorithm of FastICA dimensionality reduction for hyperspectral image on GPU. Dongbei Daxue Xuebao/J. Northeastern Univ. 37(4), 65–70 (2015). (in Chinese)
14.
Zurück zum Zitat Wu, Y., Gao, L., Zhang, B., Zhao, H., Li, J.: Real-time implementation of optimized maximum noise fraction transform for feature extraction of hyperspectral images. J. Appl. Remote Sens. 8(1), 084797 (2014)CrossRef Wu, Y., Gao, L., Zhang, B., Zhao, H., Li, J.: Real-time implementation of optimized maximum noise fraction transform for feature extraction of hyperspectral images. J. Appl. Remote Sens. 8(1), 084797 (2014)CrossRef
15.
Zurück zum Zitat Scholkopf, B., Smola, A.J., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neutral Comput. 1, 1299–1319 (1998)CrossRef Scholkopf, B., Smola, A.J., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neutral Comput. 1, 1299–1319 (1998)CrossRef
Metadaten
Titel
Study of Multilevel Parallel Algorithm of KPCA for Hyperspectral Images
verfasst von
Rulin Xu
Chang Gao
Jingfei Jiang
Copyright-Jahr
2018
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-13-2712-4_8