Skip to main content
Log in

Lossless compression for hyperspectral image using deep recurrent neural networks

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

With the rapid development of hyperspectral remote sensing technology, the spatial resolution and spectral resolution of hyperspectral images are continually increasing, resulting in a continual increase in the scale of hyperspectral data. At present, hyperspectral lossless compression technology has reached a bottleneck. Simultaneously, the rise of deep learning has provided us with new ideas. Therefore, this paper examines the use of deep learning for the lossless compression of hyperspectral images. In view of the differential pulse code modulation (DPCM) method being insufficient for predicting spectral band information, the proposed method, called C-DPCM-RNN, uses a deep recurrent neural network (RNN) to improve the traditional DPCM method and improve the generalization ability and prediction accuracy of the model. The final experimental result shows that C-DPCM-RNN achieves better compression on a set of calibrated AVIRIS test images provided by the Multispectral and Hyperspectral Data Compression Working Group of the Consultative Committee for Space Data Systems in 2006. C-DPCM-RNN overcomes the limits of traditional methods in its performance on uncalibrated AVIRIS test images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Lin CC, Hwang YT (2010) An efficient lossless compression scheme for hyperspectral image using two-stage prediction. IEEE Geosci Remote Sens Lett 7(3):558–562

    Article  Google Scholar 

  2. Aiazzi B, Alba B, Alparone L, et.al (1999) Lossless compression of multi/hyper-spectral imagery based on a 3-D fuzzy prediction. IEEE Geosci Remote Sens Lett 37(5):2287–2294

    Article  Google Scholar 

  3. Rao AK, Bhangava S (1996) Multispectral data compression using bidimentional interband prediction. IEEE Trans Remote Sens 34(2):228–240

    Google Scholar 

  4. Wang L, Wu J, Jiao L, et.al (2006) Lossy-to-lossless hyperspectral image compression based on multiplierless reversible integer TDLT/KLT. IEEE Geosci Remote Sens Lett 6(3):587–591

    Article  Google Scholar 

  5. Saghri JA, Tescher AG, Reagan JT (1995) Transform Coding of Multispectral Imagery. IEEE Signal Process Mag 12(1):32–43

    Article  Google Scholar 

  6. Abousleman GP, Marcellin MW, Hunt BR (1995) Compression of hyperspectral imagery using the 3-D DCT and hybrid DPCM/DCT. IEEE Trans Remote Sens 33(1):26–35

    Article  Google Scholar 

  7. Ma J, Wu CK, Li YS et al (2009) Dual-direction prediction vector quantization for lossless compression for LASIS data. In: Proceedings of IEEE data compression conference, Snowbird, Utah, USA, Mar, pp 458–467

  8. Ryan MJ, Arnold JF (1997) Lossy compression of hyperspectral data using vector quantization. Remote Sens Environ 61(3):419–436

    Article  Google Scholar 

  9. Canta GR, Poggi G (1998) Kronecker-product gain-shape vector quantization for multispectral and hyperspectral image coding. IEEE Trans Image Process 7(5):668–678

    Article  MathSciNet  MATH  Google Scholar 

  10. Wu X, Memon ND (2000) Context-based lossless interband compression—extending CALIC. IEEE Trans Image Process 9(6):994–1001

    Article  Google Scholar 

  11. Magli E, Olmo G, Quacchio E (2004) Optimized onboard lossless and near-lossless compression of hyperspectral data using CALIC. IEEE Geosci Remote Sens Lett 1(1):21–25

    Article  Google Scholar 

  12. Gao ZC, Zhang XL (2011) Lossless compression of hyperspectral images using improved locally averaged inter band scaling lookup tables. In: International conference on wavelet analysis and pattern recognition, pp 91–96

  13. Huang B, Sriraja Y (2006) Lossless compression of hyperspectral imagery via lookup tables with predictor selection. In: Remote sensing. International society for optics and photonics, 2006: 6365, pp 63650L–63650L-8

  14. Abrardo A, Barni M, Magli E et al (2010) Error-resilient and low-complexity onboard lossless compression of hyperspectral images by means of distributed source coding. IEEE Trans Geosci Remote Sens 48(4):1892–1904

    Article  Google Scholar 

  15. Kiely AB, Klimesh MA (2009) Exploiting calibration-induced artifacts in lossless compression of hyperspectral imagery. IEEE Trans Geosci Remote Sens 47(8):2672–2678

    Article  Google Scholar 

  16. Mielikainen J, Toivanen P (2003) Clustered DPCM for the lossless compression of hyperspectral image. IEEE Trans Geosci Remote Sens 41(12):2943–2946

    Article  Google Scholar 

  17. Howard PG, Vitter JS (1987) Arithmetic coding for data compression. Commun ACM 30(6):857–865

    Google Scholar 

  18. Howard PG, Vitter JS (1992) New methods for lossless image compression using arithmetic coding. Inf Process Manage 26(6):765–779

    Article  Google Scholar 

  19. Hao PW, Shi QY (2003) Reversible integer KLT for progressive-to-lossless compression of multiple component images. In: Proceeding of IEEE international conference on image processing, Barcelona, Spain: pp 633–636

  20. Sweldens W (1996) The lifting scheme: a custom design construction of biorthogonal wavelets. J Appl Comput Harmon Anal 3(2):186–200

    Article  MathSciNet  MATH  Google Scholar 

  21. Abousleman GP, Marcellin MW, Hunt BR (1995) Compression of hyperspectral imagery using the 3-D DCT and hybrid DPCM/DCT. IEEE Trans Geosci Remote Sens 33(l):26–34

    Article  Google Scholar 

  22. Tang X, Pearlman WA (2006) Three-dimensional wavelet-based compression of hyperspectral images, hyperspectral data compression. Springer, New York, pp 273–308

    Google Scholar 

  23. Dragotti PL, Poggi G, Ragozini ARP (2000) Compression of multispectral images by three-dimensional SPIHT algorithm. IEEE Trans Geosci Remote Sens 38(1):416–428

    Article  Google Scholar 

  24. Ryan MJ, Pickering MR (2000) An improved M-NVQ algorithm for the compression of hyperspectral data. In: IEEE IGARSS’2000, 2000, pp 600–602

  25. Ryan MI, Arnold JF (1997) The lossless compression of AVIRIS images by vector quantization. IEEE Trans Geosci Remote Sens 35(3):546 ~ 550

    Article  Google Scholar 

  26. Kamano A, Morimoto M, Nagura R (2000) Multispectral image compression using hierarchical vector quantization. IEEERSS, pp 1856–1858

    Google Scholar 

  27. Qian SE (2004) Hyperspectral data compression using a fast vector quantization algorithm. IEEE Trans Geosci Remote Sens 42(8):1791 ~ 1798

    Google Scholar 

  28. Sepp H, Jürgen S (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  29. Felix A, Gers,Jürgen Schmidhuber, F, Cummins (2000) Learning to forget: continual prediction with LSTM. Neural Comput 12(10):2451–2471

    Article  Google Scholar 

  30. Chung J, Gulcehre C, Cho KyungHyun, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. Eprint Arxiv

  31. Weinberger MJ, Seroussi G, Sapiro G (2000) The LOCO-I lossless image compression algorithm: principles and standardization into JPEG-LS. IEEE Trans Image Process 9(8):1309–1324

    Article  Google Scholar 

  32. Aiazzi B, Alparone L, Baronti S (2012) Quality issues for compression of hyperspectral imagery through spectrally adaptive DPCM. In: Satellite data compression. Springer, New York, pp 115–147

    Chapter  MATH  Google Scholar 

  33. Mielikainen J (2006) Lossless compression of hyperspectral images using lookup tables. IEEE Signal Process Lett 13(3):157–160

    Article  Google Scholar 

  34. Slyz M, Zhang L (2005) A block-based inter-band lossless hyperspectral image compressor. In Processing of IEEE data compression conference, pp 427–436

  35. Mielikainen J, Huang B (2012) Lossless compression of hyperspectral images using clustered linear prediction with adaptive prediction length. IEEE Geosci Remote Sens Lett 9(6):1118–1121

    Article  Google Scholar 

  36. Wu J, Kong W, Huang B, Mielikainen J (2015) Lossless compression of hyperspectral imagery via clustered differential pulse code modulation with removal of local spectral outliers. IEEE Signal Process Lett 22(12):2194–2198

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by National Natural Science Foundation of China nos. 61775175 and 61771378, Shenzhen Technology Project (JCYJ20170413152535587, JCYJ 20170307164023599, JSGG20170823091924128).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jiaji Wu.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Luo, J., Wu, J., Zhao, S. et al. Lossless compression for hyperspectral image using deep recurrent neural networks. Int. J. Mach. Learn. & Cyber. 10, 2619–2629 (2019). https://doi.org/10.1007/s13042-019-00937-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-019-00937-2

Keywords

Navigation