Clasificación espectral mediante una configuración óptica dual y redes neuronales profundas
Publicado 2024-11-20
Palabras clave
- clasificación espectral,
- cámara de un solo píxel,
- cámara óptica difractiva,
- máscara de fase multinivel,
- optimización de extremo a extremo
- redes neuronales profundas ...Más
Cómo citar
Derechos de autor 2024 Revista UIS Ingenierías
Esta obra está bajo una licencia internacional Creative Commons Atribución-SinDerivadas 4.0.
Resumen
La clasificación espectral permite etiquetar materiales basándose en información espectral. Las cámaras de un solo píxel (SPC) se utilizan como una solución de bajo costo para adquirir imágenes espectrales, proporcionando información espectral de alta resolución y espacial de baja resolución. Además, las cámaras ópticas difractivas (DOC) basadas en máscaras de fase multinivel (MPM) pueden adquirir características espectrales para realizar tareas de clasificación. Los enfoques tradicionales de clasificación espectral no han incorporado SPC y DOC en una única arquitectura óptica. Este trabajo propone un sistema óptico dual basado en SPC y DOC para la clasificación espectral. Específicamente, el mapa de altura en MPM y los parámetros de la red neuronal profunda se aprenden conjuntamente a partir de la optimización de un extremo a otro (E2E). El método propuesto contiene una capa óptica que describe el sistema dual, una capa de fusión que estima la imagen espectral y una red de clasificación que etiqueta los materiales en conjuntos de datos espectrales. Los resultados de la simulación muestran una mejora de hasta un 3% en las métricas de clasificación en comparación con otras arquitecturas ópticas.
Descargas
Referencias
- Q. Weng, “Thermal infrared remote sensing for urban climate and environmental studies: Methods, applications, and trends,” ISPRS Journal of photogrammetry and remote sensing, vol. 64, no. 4, pp. 335–344, 2009, doi: https://doi.org/10.1016/j.isprsjprs.2009.03.007
- M. J. Khan, H. S. Khan, A. Yousaf, K. Khurshid, and A. Abbas, “Modern trends in hyperspectral image analysis: A review,” Ieee Access, vol. 6, p. 14118–14129, 2018, doi: https://doi.org/10.1109/ACCESS.2018.2812999
- D. Guzzi, A. Barducci, P. Marcoionni, I. Pippi, “An atmospheric correction iterative method for high spectral resolution aerospace imaging spectrometers,” in 2009 IEEE International Geoscience and Remote Sensing Symposium, 2009, doi: https://doi.org/10.1109/IGARSS.2009.5418004
- M. Shimoni, R. Haelterman, C. Perneel, “Hypersectral imaging for military and security applications: Combining myriad processing and sensing techniques,” IEEE Geoscience and Remote Sensing Magazine, vol. 7, no. 2, pp. 101– 117, 2019, doi: https://doi.org/10.1109/MGRS.2019.2902525
- M. H. Tran, B. Fei, “Compact and ultracompact spectral imagers: technology and applications in biomedical imaging,” Journal of biomedical optics, vol. 28, no. 4, pp. 040 901–040 901, 2023, doi: https://doi.org/10.1117/1.JBO.28.4.040901
- L. Huang, R. Luo, X. Liu, and X. Hao, “Spectral imaging with deep learning,” Light: Science & Applications, vol. 11, no. 1, p. 61, 2022, doi: https://doi.org/10.1038/s41377-022-00743-6
- O. Denk, A. Musiienko, K. Žídek, “Differential single-pixel camera enabling low-cost microscopy in near-infrared spectral region,” Optics express, vol. 27, no. 4, pp. 4562–4571, 2019.
- H. Garcia, C. V. Correa, and H. Arguello, “Multi-resolution compressive spectral imaging reconstruction from single pixel measurements,” IEEE Transactions on Image Processing, vol. 27, no. 12, pp. 6174–6184, 2018, doi: https://doi.org/10.1109/TIP.2018.2867273
- A. Jerez, H. Garcia, and H. Arguello, “Single pixel spectral image fusion with side information from a grayscale sensor,” in 2018 IEEE 1st Colombian Conference on Applications in Computational Intelligence (ColCACI), 2018, doi: https://doi.org/10.1109/ColCACI.2018.8484848
- L. Galvis, D. Lau, X. Ma, H. Arguello, G. R. Arce, “Coded aperture design in compressive spectral imaging based on side information,” Applied optics, vol. 56, no. 22, pp. 6332–6340, 2017, doi: https://doi.org/10.1364/AO.56.006332
- M. Imani and H. Ghassemian, “An overview on spectral and spatial information fusion for hyperspectral image classification: Current trends and challenges,” Information fusion, vol. 59, pp. 59–83, 2020, doi: http://dx.doi.org/10.1016/j.inffus.2020.01.007
- C. Hinojosa, K. Sanchez, H. Garcia, and H. Arguello, “C-3spcd: coded aperture similarity constrained design for spatio-spectral classification of single-pixel measurements,” Applied Optics, vol. 61, no. 8, pp. E21–E32, 2022, doi: https://doi.org/10.1364/AO.445326
- J. Bacca, E. Martinez, and H. Arguello, “Computational spectral imaging: a contemporary overview,” JOSA A, vol. 40, no. 4, pp. C115–C125, 2023, doi: https://doi.org/10.1364/JOSAA.482406
- Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep feature extraction and classification of hyperspectral images based on convolutional neural networks,” IEEE transactions on geoscience and remote sensing, vol. 54, no. 10, pp. 6232–6251, 2016, doi: https://doi.org/10.1109/TGRS.2016.2584107
- X. Lin, Y. Rivenson, N. T. Yardimci, M. Veli, Y. Luo, M. Jarrahi, and A. Ozcan, “All-optical machine learning using diffractive deep neural networks,” Science, vol. 361, no. 6406, pp. 1004– 1008, 2018, doi: https://doi.org/10.1126/science.aat8084
- H. Arguello, S. Pinilla, Y. Peng, H. Ikoma, J. Bacca, and G. Wetzstein, “Shift-variant colorcoded diffractive spectral imaging system,” Optica, vol. 8, no. 11, pp. 1424–1434, 2021, doi: https://doi.org/10.1364/OPTICA.439142
- R. Jacome, J. Bacca, and H. Arguello, “Deepfusion: An end-to-end approach for compressive spectral image fusion,” in 2021 IEEE International Conference on Image Processing (ICIP), IEEE, 2021, doi: https://doi.org/10.1109/ICIP42928.2021.9506692
- J. Bacca, T. Gelvez-Barrera, H. Arguello, “Deep coded aperture design: An end-to-end approach for computational imaging tasks,” IEEE Transactions on Computational Imaging, vol. 7, pp. 1148–1160, 2021, doi: https://doi.org/10.48550/arXiv.2105.03390
- L. Li, L. Wang, W. Song, L. Zhang, Z. Xiong, and H. Huang, “Quantization-aware deep optics for diffractive snapshot hyperspectral imaging,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, doi: https://doi.org/10.1109/CVPR52688.2022.01916
- V. Sitzmann, S. Diamond, Y. Peng, X. Dun, S. Boyd, W. Heidrich, F. Heide, and G. Wet- zstein, “End-to-end optimization of optics and image processing for achromatic extended depth of field and super-resolution imaging,” ACM Transactions on Graphics (TOG), vol. 37, no. 4, pp. 1–13, 2018, doi: https://doi.org/10.1145/3197517.3201333
- H. Garcia, C. V. Correa, and H. Arguello, “Optimized sensing matrix for single pixel multiresolution compressive spectral imaging,” IEEE Transactions on Image Processing, vol. 29, pp. 4243–4253, 2020, doi: https://doi.org/10.1109/TIP.2020.2971150
- C. Hinojosa, J. C. Niebles, and H. Arguello, “Learning privacy-preserving optics for human pose estimation,” in Proceedings of the IEEE/CVF international conference on computer vision, 2021, doi: https://doi.org/10.1109/ICCV48922.2021.00257
- M. Born and E. Wolf, Principles of optics: electromagnetic theory of propagation, interference and diffraction of light. Elsevier, 2013.
- E. Vargas, H. Arguello, J. Y. Tourneret, “Spectral image fusion from compressive measurements using spectral unmixing and a sparse representation of abundance maps,” IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 7, pp. 5043–5053, 2019, doi: https://doi.org/10.1109/TGRS.2019.2895822
- S. H. Chan, X. Wang, O. A. Elgendy, “Plugand-play admm for image restoration: Fixedpoint convergence and applications,” IEEE Transactions on Computational Imaging, vol. 3, no. 1, pp. 84–98, 2016, doi: https://doi.org/10.48550/arXiv.1605.01710
- R. Jacome, J. Bacca, H. Arguello, “D 2uf: Deep coded aperture design and unrolling algorithmfor compressive spectral image fusion,” IEEE Journal of Selected Topics in Signal Processing, 2022, doi: https://doi.org/10.1109/JSTSP.2022.3207663