Abstract
Hyperspectral unmixing is an important remote sensing task with applications including material identification and analysis. Characteristic spectral features make many pure materials identifiable from their visible-to-infrared spectra, but quantifying their presence within a mixture is a challenging task due to nonlinearities and factors of variation. In this paper, spectral variation is considered from a physics-based approach and incorporated into an end-to-end spectral unmixing algorithm via differentiable programming. The dispersion model is introduced to simulate realistic spectral variation, and an efficient method to fit the parameters is presented. Then, this dispersion model is utilized as a generative model within an analysis-by-synthesis spectral unmixing algorithm. Further, a technique for inverse rendering using a convolutional neural network to predict parameters of the generative model is introduced to enhance performance and speed when training data is available. Results achieve state-of-the-art on both infrared and visible-to-near-infrared (VNIR) datasets, and show promise for the synergy between physics-based models and deep learning in hyperspectral unmixing in the future.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Azinovic, D., Li, T.M., Kaplanyan, A., Niessner, M.: Inverse path tracing for joint material and lighting estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2447–2456 (2019)
Bandfield, J.L.: Global mineral distributions on mars. J. Geophys. Res. Planets 107(E6), 1–9 (2002)
Bateson, C.A., Asner, G.P., Wessman, C.A.: Endmember bundles: a new approach to incorporating endmember variability into spectral mixture analysis. IEEE Trans. Geosci. Remote Sens. 38(2), 1083–1094 (2000)
Baydin, A.G., Pearlmutter, B.A., Radul, A.A., Siskind, J.M.: Automatic differentiation in machine learning: a survey. J. Mach. Learn. Res. 18(1), 5595–5637 (2017)
Bhojanapalli, S., Kyrillidis, A., Sanghavi, S.: Dropping convexity for faster semi-definite optimization. In: Conference on Learning Theory, pp. 530–582 (2016)
Borsoi, R.A., et al.: Spectral variability in hyperspectral data unmixing: a comprehensive review. arXiv preprint arXiv:2001.07307 (2020)
Burns, R.G.: Crystal field spectra and evidence of cation ordering in olivine minerals. Am. Mineral. J. Earth Planet. Mater. 55(9–10), 1608–1632 (1970)
Chang, C.I.: Hyperspectral Imaging: Techniques for Spectral Detection and Classification, vol. 1. Springer, New York (2003). https://doi.org/10.1007/978-1-4419-9170-6
Chen, F., Zhang, Y.: Sparse hyperspectral unmixing based on constrained lp-l 2 optimization. IEEE Geosci. Remote Sens. Lett. 10(5), 1142–1146 (2013)
Chen, Y., Jiang, H., Li, C., Jia, X., Ghamisi, P.: Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans. Geosci. Remote Sens. 54(10), 6232–6251 (2016)
Cheng, G., Li, Z., Han, J., Yao, X., Guo, L.: Exploring hierarchical convolutional features for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 56(11), 6712–6722 (2018)
Chouzenoux, E., Legendre, M., Moussaoui, S., Idier, J.: Fast constrained least squares spectral unmixing using primal-dual interior-point optimization. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 7(1), 59–69 (2014)
Christensen, P., et al.: Mars global surveyor thermal emission spectrometer experiment: investigation description and surface science results. J. Geophys. Res. Planets 106(E10), 23823–23871 (2001)
Christensen, P.R., et al.: Lauretta: The OSIRIS-REx thermal emission spectrometer (OTES) instrument. Space Sci. Rev. 214(5), 87 (2018)
Combe, J.P., et al.: Analysis of OMEGA/mars express data hyperspectral data using a multiple-endmember linear spectral unmixing model (MELSUM): methodology and first results. Planet. Space Sci. 56(7), 951–975 (2008)
Du, X., Zare, A., Gader, P., Dranishnikov, D.: Spatial and spectral unmixing using the beta compositional model. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 7(6), 1994–2003 (2014)
Duchi, J.C., Ruan, F.: Solving (most) of a set of quadratic equalities: composite optimization for robust phase retrieval. Inf. Infer. J. IMA 8(3), 471–529 (2019)
Engel, J., Hantrakul, L.H., Gu, C., Roberts, A.: DDSP: differentiable digital signal processing. In: International Conference on Learning Representations (2020)
Feely, K.C., Christensen, P.R.: Quantitative compositional analysis using thermal emission spectroscopy: application to igneous and metamorphic rocks. J. Geophys. Res. Planets 104(E10), 24195–24210 (1999)
Gader, P., Zare, A., Close, R., Aitken, J., Tuell, G.: MUUFL Gulfport hyperspectral and LIDAR airborne data set. Tech. rep. REP-2013-57. University Florida, Gainesville, FL, USA0 (2013)
Gkioulekas, I., Levin, A., Zickler, T.: An evaluation of computational imaging techniques for heterogeneous inverse scattering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 685–701. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_42
Gkioulekas, I., Zhao, S., Bala, K., Zickler, T., Levin, A.: Inverse volume rendering with material dictionaries. ACM Trans. Graph. (TOG) 32(6), 162 (2013)
Goudge, T.A., Mustard, J.F., Head, J.W., Salvatore, M.R., Wiseman, S.M.: Integrating CRISM and TES hyperspectral data to characterize a halloysite-bearing deposit in Kashira crater, mars. Icarus 250, 165–187 (2015)
Heinz, D.C., et al.: Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 39(3), 529–545 (2001)
Heylen, R., Parente, M., Gader, P.: A review of nonlinear hyperspectral unmixing methods. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 7(6), 1844–1868 (2014)
Hu, W., Huang, Y., Wei, L., Zhang, F., Li, H.: Deep convolutional neural networks for hyperspectral image classification. J. Sens. 2015, 12 (2015)
Jain, P., Kar, P., et al.: Non-convex optimization for machine learning. Found. Trends Mach. Learn. 10(3–4), 142–336 (2017)
Keshava, N., Mustard, J.F.: Spectral unmixing. IEEE Signal Process. Mag. 19(1), 44–57 (2002)
Klingelhöfer, G., et al.: Jarosite and hematite at Meridiani planum from opportunity’s mössbauer spectrometer. Science 306(5702), 1740–1745 (2004)
Larkin, P.: Infrared and Raman Spectroscopy: Principles and Spectral Interpretation. Elsevier (2017)
Lee, J.D., Simchowitz, M., Jordan, M.I., Recht, B.: Gradient descent converges to minimizers. arXiv preprint arXiv:1602.04915 (2016)
Lee, S., Tien, C.: Optical constants of soot in hydrocarbon flames. In: Symposium (International) on Combustion, vol. 18, pp. 1159–1166. Elsevier (1981)
Li, S., Song, W., Fang, L., Chen, Y., Ghamisi, P., Benediktsson, J.A.: Deep learning for hyperspectral image classification: an overview. IEEE Trans. Geosci. Remote Sens. 57(9), 6690–6709 (2019)
Li, T.M., Aittala, M., Durand, F., Lehtinen, J.: Differentiable monte carlo ray tracing through edge sampling. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 37(6), 222:1–222:11 (2018)
Li, Y., Zhang, H., Shen, Q.: Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens. 9(1), 67 (2017)
Liu, P., Zhang, H., Eom, K.B.: Active deep learning for classification of hyperspectral images. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 10(2), 712–724 (2016)
Loubet, G., Holzschuch, N., Jakob, W.: Reparameterizing discontinuous integrands for differentiable rendering. Trans. Graph. (Proc. SIGGRAPH Asia) 38(6) (2019). https://doi.org/10.1145/3355089.3356510
Lu, G., Fei, B.: Medical hyperspectral imaging: a review. J. Biomed. Opt. 19(1), 010901 (2014)
Moersch, J., Christensen, P.R.: Thermal emission from particulate surfaces: a comparison of scattering models with measured spectra. J. Geophys. Res. Planets 100(E4), 7465–7477 (1995)
Nimier-David, M., Vicini, D., Zeltner, T., Jakob, W.: Mitsuba 2: a retargetable forward and inverse renderer. Trans. Graph. (Proc. SIGGRAPH Asia) 38(6) (2019). https://doi.org/10.1145/3355089.3356498
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024–8035 (2019)
Ramsey, M.S., Christensen, P.R.: Mineral abundance determination: quantitative deconvolution of thermal emission spectra. J. Geophys. Res. Solid Earth 103(B1), 577–596 (1998)
Ramsey, M.S., Christensen, P.R.: Mineral abundance determination: Quantitative deconvolution of thermal emission spectra: application to analysis of martian atmospheric particulates. J. Geophys. Res. Solid Earth 103, 577–596 (2000)
Ravi, N., et al.: Pytorch3D. https://github.com/facebookresearch/pytorch3d (2020)
Roberts, D.A., Gardner, M., Church, R., Ustin, S., Scheer, G., Green, R.: Mapping chaparral in the santa monica mountains using multiple endmember spectral mixture models. Remote Sens. Environ. 65(3), 267–279 (1998)
Rogers, A., Aharonson, O.: Mineralogical composition of sands in meridiani planum determined from mars exploration rover data and comparison to orbital measurements. J. Geophys. Res. Planets 113, E6 (2008)
Salisbury, J.W., D’Aria, D.M., Sabins Jr., F.F.: Thermal infrared remote sensing of crude oil slicks. Remote Sens. Environ. 45(2), 225–231 (1993)
Spitzer, W., Kleinman, D.: Infrared lattice bands of quartz. Phys. Rev. 121(5), 1324 (1961)
Stein, D.: Application of the normal compositional model to the analysis of hyperspectral imagery. In: IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003, pp. 44–51. IEEE (2003)
Sunshine, J.M., Pieters, C.M.: Determining the composition of olivine from reflectance spectroscopy. J. Geophys. Res. Planets 103(E6), 13675–13688 (1998)
Tsai, C.Y., Sankaranarayanan, A.C., Gkioulekas, I.: Beyond volumetric albedo – a surface optimization framework for non-line-of-sight imaging. In: IEEE International Conference Computer Vision and Pattern Recognition (CVPR) (2019)
Wang, F., Decker, J., Wu, X., Essertel, G., Rompf, T.: Backpropagation with callbacks: foundations for efficient and expressive differentiable programming. In: Advances in Neural Information Processing Systems, pp. 10180–10191 (2018)
Wang, F., Zheng, D., Decker, J., Wu, X., Essertel, G.M., Rompf, T.: Demystifying differentiable programming: shift/reset the penultimate backpropagator. In: Proceedings of the ACM on Programming Languages, vol. 3, no. ICFP, pp. 1–31 (2019)
Wenrich, M.L., Christensen, P.R.: Optical constants of minerals derived from emission spectroscopy: application to quartz. J. Geophys. Res. Solid Earth 101(B7), 15921–15931 (1996)
Yang, X., Ye, Y., Li, X., Lau, R.Y., Zhang, X., Huang, X.: Hyperspectral image classification with deep learning models. IEEE Trans. Geosci. Remote Sens. 56(9), 5408–5423 (2018)
Yu, Y., Smith, W.A.: InverseRenderNet: learning single image inverse rendering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3155–3164 (2019)
Zare, A., Gader, P.: Sparsity promoting iterated constrained endmember detection in hyperspectral imagery. IEEE Geosci. Remote Sens. Lett. 4(3), 446–450 (2007)
Zare, A., Gader, P.: Hyperspectral band selection and endmember detection using sparsity promoting priors. IEEE Geosci. Remote Sens. Lett. 5(2), 256–260 (2008)
Zare, A., Ho, K.: Endmember variability in hyperspectral analysis: addressing spectral variability during spectral unmixing. IEEE Signal Process. Mag. 31(1), 95–104 (2013)
Zhang, C., Wu, L., Zheng, C., Gkioulekas, I., Ramamoorthi, R., Zhao, S.: A differential theory of radiative transfer. ACM Trans. Graph. (TOG) 38(6), 1–16 (2019)
Zhang, L., Zhang, L., Du, B.: Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE Geosci. Remote Sens. Mag. 4(2), 22–40 (2016)
Zhang, S., Li, J., Li, H.C., Deng, C., Plaza, A.: Spectral-spatial weighted sparse regression for hyperspectral image unmixing. IEEE Trans. Geosci. Remote Sens. 56(6), 3265–3276 (2018)
Zhao, W., Du, S.: Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Trans. Geosci. Remote Sens. 54(8), 4544–4554 (2016)
Zhou, Y., Rangarajan, A., Gader, P.D.: A Gaussian mixture model representation of endmember variability in hyperspectral unmixing. IEEE Trans. Image Process. 27(5), 2242–2256 (2018)
Acknowledgements
This work was supported by NSF grant IIS-1909192 as well as GPU resources from ASU Research Computing. We thank Dr. Alina Zare, Christopher Haberle, and Dr. Deanna Rogers for their helpful discussions, and Kim Murray (formerly Kim Feely) for providing the laboratory measurements and analysis contributing to this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Janiczek, J., Thaker, P., Dasarathy, G., Edwards, C.S., Christensen, P., Jayasuriya, S. (2020). Differentiable Programming for Hyperspectral Unmixing Using a Physics-Based Dispersion Model. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12372. Springer, Cham. https://doi.org/10.1007/978-3-030-58583-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-58583-9_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58582-2
Online ISBN: 978-3-030-58583-9
eBook Packages: Computer ScienceComputer Science (R0)