To reduce the size of spectral data, compressive sensing imaging systems are developed to sample fewer measurements than the Nyquist-rate ones, from which the original data can be recovered by the optimisation model and algorithm. However, this is not a cheap option for the case where the real-time acquisition of spectral information is required. To solve this problem, the authors propose a novel sensing approach for spectral features by combining the sampling, recovery and feature extraction. Inspired by the spectral feature representation, the sampling (sensing) matrix is designed from the training spectral samples to sense the spectral features of the imaging scene, which can be utilised for classification and recognition directly. Besides, the physical realisation of the sensing matrix for compressive spectral imaging systems is demonstrated by designing new modulation patterns of the digital micro-mirror device. The experimental results on real spectral data show the feasibility of the proposed scheme and the robustness to the quantisation error and the measurement noise. Moreover, the proposed sensing approach can reduce the cost of computation and time greatly by removing the sparse recovery and feature extraction..

References

1. 1)
  - 10. Wagadarikar, A.A., John, R., Willett, R., et al: ‘Single disperser design for coded aperture snapshot spectral imaging’, Appl. Opt., 2008, 47, (10), pp. B44–B51.
2. 2)
  - 18. Tao, M., Yuan, X.: ‘Recovering low-rank and sparse components of matrices from incomplete and noisy observations’, SIAM J. Optim., 2011, 21, (1), pp. 57–81.
3. 3)
  - 7. Baraniuk, R.G., Cevher, V., Duarte, M.F., et al: ‘Model-based compressive sensing’, IEEE Trans. Inf. Theory, 2010, 56, (4), pp. 1982–2001.
4. 4)
  - 13. Ramirez, A., Arguello, H., Arce, G.R., et al: ‘Spectral image classification from optimal coded-aperture compressive measurements’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (6), pp. 3299–3309.
5. 5)
  - 30. Jing, X., Wu, F., Zhu, X., et al: ‘Multi-spectral low-rank structured dictionary learning for face recognition’, Pattern Recognit., 2016, 59, pp. 14–25.
6. 6)
  - 5. Foucart, S., Rauhut, H.: ‘A mathematical introduction to compressive sensing’, Appl. Numer. Harmonic Anal., 2017, 44, pp. 1–22.
7. 7)
  - 9. Galvis, L., Lau, D., Xu, M., et al: ‘Coded aperture design in compressive spectral imaging based on side information’, Appl. Opt., 2017, 56, (22), p. 6332.
8. 8)
  - 32. Cai, T.T., Wang, L.: ‘Orthogonal matching pursuit for sparse signal recovery with noise’, IEEE Trans. Inf. Theory, 2011, 57, (7), pp. 4680–4688.
9. 9)
  - 25. Liu, J., Zhu, J., Yan, F., et al: ‘Random phase modulation and sparse sampling-based optical imaging system’, Opt. Eng., 2010, 49, (4), p. 047002–047002-5.
10. 10)
  - 33. Abdi, H., Williams, L.J.: ‘Principal component analysis’, Wiley Interdiscipl. Rev. Comput. Stat., 2010, 2, (4), pp. 433–459.
11. 11)
  - 20. Chartrand, R., Staneva, V.: ‘Restricted isometry properties and nonconvex compressive sensing’, Inverse Probl., 2010, 24, (3), pp. 657–682.
12. 12)
  - 27. Hyperspectral Remote Sensing Scences. Available at http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes#Pavia_University_scene.
13. 13)
  - 3. Correa, C.V., Hinojosa, C.A., Arce, G.R., et al: ‘Multiple snapshot colored compressive spectral imager’, Opt. Eng., 2017, 56, (4), pp. 1–10.
14. 14)
  - 26. Hyperspectral Remote Sensing Scences. Available at http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes#Salinas-A_scene.
15. 15)
  - 6. Ji, S., Xue, Y., Carin, L.: ‘Bayesian compressive sensing’, IEEE Trans. Signal Process., 2008, 56, (6), pp. 2346–2356.
16. 16)
  - 19. Lu, C., Feng, J., Chen, Y., et al: ‘Tensor robust principal component analysis: exact recovery of corrupted low-rank tensors via convex optimization’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 1063–6919.
17. 17)
  - 1. Asadzadeh, S., Filho, C.R.S.: ‘A review on spectral processing methods for geological remote sensing’, Int. J. Appl. Earth Obs. Geoinf., 2016, 47, pp. 69–90.
18. 18)
  - 31. Melgany, F., Bruzzone, L.: ‘Classification of hyperspectral remote sensing images with support vector machines’, IEEE Trans. Geosci. Remote Sens., 2004, 42, (8), pp. 1778–1790.
19. 19)
  - 22. Dudley, D., Duncan, W.M., Slaughter, J.: ‘Emerging digital micromirror device (DMD) applications’. Proc. SPIE 4985, MOEMS Display and Imaging Systems, San Jose, USA, 2003, 4985, pp. 1–12.
20. 20)
  - 15. Vimala, P., Yamuna, G.: ‘Review of different compressive sensing algorithms and recovery guarantee of iterative orthogonal matching pursuit’, Int. J. Appl. Eng. Res., 2015, 10, (7), pp. 17201–17212.
21. 21)
  - 11. Du, Q., Fowler, J.E.: ‘Hyperspectral image compression using jpeg2000 and principal component analysis’, IEEE Geosci. Remote Sens. Lett., 2007, 4, (2), pp. 201–205.
22. 22)
  - 28. Zhang, L., Wei, W., Zhang, Y., et al: ‘Cluster sparsity field: an internal hyperspectral imagery prior for reconstruction’, Int. J. Comput. Vis., 2018, 126, (8), pp. 797–821. Available at https://doi.org/10.1007/s11263-018-1080-8.
23. 23)
  - 12. Bengio, Y., Paiement, J.F., Vincent, P., et al: ‘Out-of-sample extensions for LLE, IsoMap, MDS, eigenmaps, and spectral clustering’, Adv. Neural. Inf. Process. Syst., 2003, 16, pp. 177–184.
24. 24)
  - 8. Parada-Mayorga, A., Arce, G.R.: ‘Colored coded aperture design in compressive spectral imaging via minimum coherence’, IEEE Trans. Comput. Imag., 2017, 3, (2), pp. 202–216.
25. 25)
  - 23. Lu, M., Shen, X., Han, S.: ‘Ghost imaging via compressive sampling based on digital micromirror device’, Acta Opt. Sin., 2011, 31, (7), p. 0711002.
26. 26)
  - 21. Lorenzo, J.M., Obermeier, R.: ‘Sensing matrix design via mutual coherence minimization for electromagnetic compressive imaging applications’, IEEE Trans. Comput. Imag., 2017, 3, (2), pp. 217–229.
27. 27)
  - 24. Wu, Y., Mirza, I.O., Arce, G.R., et al: ‘Development of a digital micromirror device (DMD)-based snapshot spectral imaging (DMD-SSI) system’. IEEE Photonics Conf. (PHO), Arlington, USA, 2011, pp. 149–150.
28. 28)
  - 2. Qiu, Q., Wu, X., Liu, Z., et al: ‘Survey of supervised classification techniques for hyperspectral images’, Sens. Rev., 2017, 37, (3), pp. 371–382.
29. 29)
  - 29. Li, E., Shafiee, M.J., Kazemzadeh, F., et al: ‘Sparse reconstruction of compressive sensing multi-spectral data using an inter-spectral multi-layered conditional random field model’, IEEE Access, 2016, 4, pp. 5540–5554.
30. 30)
  - 14. AVIRIS NW Indiana's Indian Pines 1992 Dataset. Available at https://engineering.purdue.edu/biehl/MultiSpec/ documentation.html.
31. 31)
  - 4. Fu, C., Don, M.L., Arce, G.R.: ‘Compressive spectral imaging via polar coded aperture’, IEEE Trans. Comput. Imag., 2016, 3, (3), pp. 408–420.
32. 32)
  - 17. Gehm, M.E., John, R., Willett, R., et al: ‘Single-shot compressive spectral imaging with a dual disperser architecture’, Opt. Express, 2007, 15, pp. 14013–14027.
33. 33)
  - 16. Karakus, C., Gurbuz, A.C.: ‘Comparison of iterative sparse recovery algorithms’. IEEE 19th Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey, 2011, pp. 857–860.

Compressive spectral feature sensing

References

Related content