Derechos de autor 2021 Investigación e Innovación en Ingenierías
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Satellite-image fusion using Brovey transform and spectral richness calibration on heterogeneous computing CPU/GPU
Corresponding Author(s) : Andrés Ovidio Restrepo Rodríguez
Investigación e Innovación en Ingenierías,
Vol. 9 Núm. 2 (2021): Julio - Diciembre
Resumen
La fusión de imágenes satelitales proporciona un contexto potencialmente aplicable en el desarrollo de proyectos en diversos campos como agricultura, hidrología, medio ambiente, emergencias producidas por catástrofes naturales como inundaciones e incendios forestales. Sin embargo, cuando se trabajan imágenes con grandes dimensiones el tiempo de respuesta para llevar a cabo esta tarea crece significativamente. Por esta razón, este estudio tiene como propuesta, la implementación de la transformada de Brovey como técnica de fusión de imágenes junto con un ajuste de riqueza espectral sobre una arquitectura de computación heterogénea CPU/GPU utilizando un modelo de procesamiento paralelo masivo, el cual fue implementado mediante CUDA. La evaluación de esta implementación evidenció un Speed-up de hasta 532X en el proceso de fusión de una imagen de 8192 píxeles. En cuanto a calidad de la imagen obtenida, al obtener el coeficiente de correlación entre la imagen fusionada y la pancromática, se obtuvo un promedio de detalle espacial por banda del 0.9714 en un espacio de color (R,G,B).
Palabras clave
Descargar cita
Endnote/Zotero/Mendeley (RIS)BibTeX
- P. Erbao and Z. Guotong, “Image Processing Technology Research of On-Line Thread Processing,” Energy Procedia, vol. 17, pp. 1408–1415, 2012. DOI: https://doi.org/10.1016/j.egypro.2012.02.260.
- V. Solanky and S. K. Katiyar, “Pixel-level image fusion techniques in remote sensing: a review,” Spatial Information Research, vol. 24, no. 4, pp. 475–483, Aug. 2016. DOI: https://doi.org/10.1007/s41324-016-0046-6.
- R. Swathika and T. S. Sharmila, “Image fusion for MODIS and Landsat images using top hat based moving technique with FIS,” Cluster Computing, pp. 1–9, 2018. DOI: https://doi.org/10.1007/s10586-018-1802-2.
- A. Gupta and V. Dey, “A Comparative Investigation of Image Fusion in the Context of Classification,” Journal of the Indian Society of Remote Sensing, vol. 40, no. 2, pp. 167–178, 2012. DOI: https://doi.org/10.1007/s12524-011-0138-7.
- R. J. Medina Daza, C. Pinilla Ruiz, and L. Joyanes Aguilar, “Two-dimensional fast Haar wavelet transform for satellite-image fusion,” Journal of Applied Remote Sensing, vol. 7, no. 1, p. 073698, Sep. 2013. DOI: https://doi.org/10.1117/1.jrs.7.073698.
- C. L. Zhang, Y. P. Xu, Z. J. Xu, J. He, J. Wang, and J. H. Adu, “A Fuzzy Neural Network Based Dynamic Data Allocation Model on Heterogeneous Multi-GPUs for Large-scale Computations,” International Journal of Automation and Computing, vol. 15, no. 2, pp. 181–193, Apr. 2018. DOI: https://doi.org/10.1007/s11633-018-1120-4.
- S. Westerlund and C. Harris, “Performance analysis of GPU-accelerated filter-based source finding for HI spectral line image data,” Experimental Astronomy, vol. 39, no. 1, pp. 95–117, Mar. 2015. DOI: https://doi.org/10.1007/s10686-015-9445-2.
- F. Ye, X. Li, and X. Zhang, “FusionCNN: a remote sensing image fusion algorithm based on deep convolutional neural networks,” Multimedia Tools and Applications, vol. 78, no. 11, pp. 14683–14703, Jun. 2019. DOI: https://doi.org/10.1007/s11042-018-6850-3.
- V. Alvarez-Ramos, V. Ponomaryov, and R. Reyes-Reyes, “Image super-resolution via two coupled dictionaries and sparse representation,” Multimedia Tools and Applications, vol. 77, no. 11, pp. 13487–13511, Jun. 2018. DOI: https://doi.org/10.1007/s11042-017-4968-3.
- A. D. Vaiopoulos, “Developing Matlab scripts for image analysis and quality assessment,” in Earth Resources and Environmental Remote Sensing/GIS Applications II, 2011. DOI: https://doi.org/10.1117/12.897806.
- N. Jindal and K. Singh, “Applicability of fractional transforms in image processing - review, technical challenges and future trends,” Multimedia Tools and Applications, vol. 78, no. 8, pp. 10673–10700, Apr. 2019. DOI: https://doi.org/10.1007/s11042-018-6594-0.
- A. O. R. Rodríguez, D. E. C. Mateus, P. A. G. García, C. E. M. Marín, and R. G. Crespo, “Hyperparameter optimization for image recognition over an AR-Sandbox based on convolutional neural networks applying a previous phase of segmentation by color-space,” Symmetry, vol. 10, no. 12, Dec. 2018. DOI: https://doi.org/10.3390/sym10120743.
- L. Meijie, D. Yongshou, Z. Jie, Z. Xi, M. Junmin, and X. Qinchuan, “PCA-based sea-ice image fusion of optical data by HIS transform and SAR data by wavelet transform”. . DOI: https://doi.org/10.1007/s13131-015.
- X. Zhu and W. Bao, “Investigation of Remote Sensing Image Fusion Strategy Applying PCA to Wavelet Packet Analysis Based on IHS Transform,” Journal of the Indian Society of Remote Sensing, vol. 47, no. 3, pp. 413–425, Mar. 2019. DOI: https://doi.org/10.1007/s12524-018-0930-8.
- X. Li and L. Wang, “On the study of fusion techniques for bad geological remote sensing image,” Journal of Ambient Intelligence and Humanized Computing, vol. 6, no. 1, pp. 141–149, 2015. DOI: https://doi.org/10.1007/s12652-015-0255-1.
- N. Vera, C. Rojas, and J. Peréz, OPENCL PRÁCTICO COMPUTACIÓN HETEROGÉNEA PARALELA. Bogotá: Colección Doctorado en Ingeniería, Universidad Distrital Francisco José de Caldas, 2019.
- W. Cao, C. fu Xu, Z. hua Wang, L. Yao, and H. yong Liu, “CPU/GPU computing for a multi-block structured grid based high-order flow solver on a large heterogeneous system,” Cluster Computing, vol. 17, no. 2, pp. 255–270, 2014. DOI: https://doi.org/10.1007/s10586-013-0332-1.
- C. Lee, W. W. Ro, and J. L. Gaudiot, “Boosting CUDA applications with CPU-GPU hybrid computing,” International Journal of Parallel Programming, vol. 42, no. 2, pp. 384–404, 2014. DOI: https://doi.org/10.1007/s10766-013-0252-y.
- G. He, S. Xing, Z. Xia, Q. Huang, and J. Fan, “Panchromatic and multi-spectral image fusion for new satellites based on multi-channel deep model,” in Machine Vision and Applications, 2018, vol. 29, no. 6, pp. 933–946. DOI: https://doi.org/10.1007/s00138-018-0964-5.
- C. Graca, G. Falcao, I. N. Figueiredo, and S. Kumar, “Hybrid multi-GPU computing: accelerated kernels for segmentation and object detection with medical image processing applications,” Journal of Real-Time Image Processing, vol. 13, no. 1, pp. 227–244, Mar. 2017. DOI: https://doi.org/10.1007/s11554-015-0517-3.
- I. S. Acikgoz, M. Teke, U. Kutbay, and F. Hardalac, “Performance evaluation of pansharpening methods on GPU for RASAT images,” RAST 2015 - Proceedings of 7th International Conference on Recent Advances in Space Technologies, pp. 283–288, 2015. DOI: https://doi.org/10.1109/RAST.2015.7208356.
- A. Asaduzzaman, A. Martinez, and A. Sepehri, “A time-efficient image processing algorithm for multicore/manycore parallel computing,” in Conference Proceedings - IEEE SOUTHEASTCON, 2015, vol. 2015-June, no. June. DOI: https://doi.org/10.1109/SECON.2015.7132924.
- Y. Ma, L. Chen, P. Liu, and K. Lu, “Parallel programing templates for remote sensing image processing on GPU architectures: design and implementation,” Computing, vol. 98, no. 1–2, pp. 7–33, Jan. 2016. DOI: https://doi.org/10.1007/s00607-014-0392-y.
- J. Zhang and K. H. Lim, “Implementation of a covariance-based principal component analysis algorithm with a CUDA-enabled graphics processing unit,” in International Geoscience and Remote Sensing Symposium (IGARSS), 2011. DOI: https://doi.org/10.1109/IGARSS.2011.6049460.
- S. D. Jawak and A. J. Luis, “A Comprehensive Evaluation of PAN-Sharpening Algorithms Coupled with Resampling Methods for Image Synthesis of Very High Resolution Remotely Sensed Satellite Data,” Advances in Remote Sensing, vol. 02, no. 04, pp. 332–344, 2013. DOI: https://doi.org/10.4236/ars.2013.24036.
- M. Lillo-Saavedra, C. Gonzalo, A. Arquero, and E. Martinez, “Fusion of multispectral and panchromatic satellite sensor imagery based on tailored filtering in the Fourier domain,” International Journal of Remote Sensing, vol. 26, no. 6, pp. 1263–1268, Mar. 2005. DOI: https://doi.org/10.1080/01431160412331330239.
- H. Ghassemian, “A review of remote sensing image fusion methods,” Information Fusion, vol. 32. Elsevier B.V., pp. 75–89, 01-Nov-2016. DOI: https://doi.org/10.1016/j.inffus.2016.03.003.
- Z. Liu, E. Blasch, G. Bhatnagar, V. John, W. Wu, and R. S. Blum, “Fusing synergistic information from multi-sensor images: An overview from implementation to performance assessment,” Information Fusion, vol. 42, pp. 127–145, Jul. 2018. DOI: https://doi.org/10.1016/j.inffus.2017.10.010.
- L. Alparone, L. Wald, J. Chanussot, C. Thomas, P. Gamba, and L. M. Bruce, “Comparison of pansharpening algorithms: Outcome of the 2006 GRS-S data-fusion contest,” in IEEE Transactions on Geoscience and Remote Sensing, 2007, vol. 45, no. 10, pp. 3012–3021. DOI: https://doi.org/10.1109/TGRS.2007.904923.
Referencias
P. Erbao and Z. Guotong, “Image Processing Technology Research of On-Line Thread Processing,” Energy Procedia, vol. 17, pp. 1408–1415, 2012. DOI: https://doi.org/10.1016/j.egypro.2012.02.260.
V. Solanky and S. K. Katiyar, “Pixel-level image fusion techniques in remote sensing: a review,” Spatial Information Research, vol. 24, no. 4, pp. 475–483, Aug. 2016. DOI: https://doi.org/10.1007/s41324-016-0046-6.
R. Swathika and T. S. Sharmila, “Image fusion for MODIS and Landsat images using top hat based moving technique with FIS,” Cluster Computing, pp. 1–9, 2018. DOI: https://doi.org/10.1007/s10586-018-1802-2.
A. Gupta and V. Dey, “A Comparative Investigation of Image Fusion in the Context of Classification,” Journal of the Indian Society of Remote Sensing, vol. 40, no. 2, pp. 167–178, 2012. DOI: https://doi.org/10.1007/s12524-011-0138-7.
R. J. Medina Daza, C. Pinilla Ruiz, and L. Joyanes Aguilar, “Two-dimensional fast Haar wavelet transform for satellite-image fusion,” Journal of Applied Remote Sensing, vol. 7, no. 1, p. 073698, Sep. 2013. DOI: https://doi.org/10.1117/1.jrs.7.073698.
C. L. Zhang, Y. P. Xu, Z. J. Xu, J. He, J. Wang, and J. H. Adu, “A Fuzzy Neural Network Based Dynamic Data Allocation Model on Heterogeneous Multi-GPUs for Large-scale Computations,” International Journal of Automation and Computing, vol. 15, no. 2, pp. 181–193, Apr. 2018. DOI: https://doi.org/10.1007/s11633-018-1120-4.
S. Westerlund and C. Harris, “Performance analysis of GPU-accelerated filter-based source finding for HI spectral line image data,” Experimental Astronomy, vol. 39, no. 1, pp. 95–117, Mar. 2015. DOI: https://doi.org/10.1007/s10686-015-9445-2.
F. Ye, X. Li, and X. Zhang, “FusionCNN: a remote sensing image fusion algorithm based on deep convolutional neural networks,” Multimedia Tools and Applications, vol. 78, no. 11, pp. 14683–14703, Jun. 2019. DOI: https://doi.org/10.1007/s11042-018-6850-3.
V. Alvarez-Ramos, V. Ponomaryov, and R. Reyes-Reyes, “Image super-resolution via two coupled dictionaries and sparse representation,” Multimedia Tools and Applications, vol. 77, no. 11, pp. 13487–13511, Jun. 2018. DOI: https://doi.org/10.1007/s11042-017-4968-3.
A. D. Vaiopoulos, “Developing Matlab scripts for image analysis and quality assessment,” in Earth Resources and Environmental Remote Sensing/GIS Applications II, 2011. DOI: https://doi.org/10.1117/12.897806.
N. Jindal and K. Singh, “Applicability of fractional transforms in image processing - review, technical challenges and future trends,” Multimedia Tools and Applications, vol. 78, no. 8, pp. 10673–10700, Apr. 2019. DOI: https://doi.org/10.1007/s11042-018-6594-0.
A. O. R. Rodríguez, D. E. C. Mateus, P. A. G. García, C. E. M. Marín, and R. G. Crespo, “Hyperparameter optimization for image recognition over an AR-Sandbox based on convolutional neural networks applying a previous phase of segmentation by color-space,” Symmetry, vol. 10, no. 12, Dec. 2018. DOI: https://doi.org/10.3390/sym10120743.
L. Meijie, D. Yongshou, Z. Jie, Z. Xi, M. Junmin, and X. Qinchuan, “PCA-based sea-ice image fusion of optical data by HIS transform and SAR data by wavelet transform”. . DOI: https://doi.org/10.1007/s13131-015.
X. Zhu and W. Bao, “Investigation of Remote Sensing Image Fusion Strategy Applying PCA to Wavelet Packet Analysis Based on IHS Transform,” Journal of the Indian Society of Remote Sensing, vol. 47, no. 3, pp. 413–425, Mar. 2019. DOI: https://doi.org/10.1007/s12524-018-0930-8.
X. Li and L. Wang, “On the study of fusion techniques for bad geological remote sensing image,” Journal of Ambient Intelligence and Humanized Computing, vol. 6, no. 1, pp. 141–149, 2015. DOI: https://doi.org/10.1007/s12652-015-0255-1.
N. Vera, C. Rojas, and J. Peréz, OPENCL PRÁCTICO COMPUTACIÓN HETEROGÉNEA PARALELA. Bogotá: Colección Doctorado en Ingeniería, Universidad Distrital Francisco José de Caldas, 2019.
W. Cao, C. fu Xu, Z. hua Wang, L. Yao, and H. yong Liu, “CPU/GPU computing for a multi-block structured grid based high-order flow solver on a large heterogeneous system,” Cluster Computing, vol. 17, no. 2, pp. 255–270, 2014. DOI: https://doi.org/10.1007/s10586-013-0332-1.
C. Lee, W. W. Ro, and J. L. Gaudiot, “Boosting CUDA applications with CPU-GPU hybrid computing,” International Journal of Parallel Programming, vol. 42, no. 2, pp. 384–404, 2014. DOI: https://doi.org/10.1007/s10766-013-0252-y.
G. He, S. Xing, Z. Xia, Q. Huang, and J. Fan, “Panchromatic and multi-spectral image fusion for new satellites based on multi-channel deep model,” in Machine Vision and Applications, 2018, vol. 29, no. 6, pp. 933–946. DOI: https://doi.org/10.1007/s00138-018-0964-5.
C. Graca, G. Falcao, I. N. Figueiredo, and S. Kumar, “Hybrid multi-GPU computing: accelerated kernels for segmentation and object detection with medical image processing applications,” Journal of Real-Time Image Processing, vol. 13, no. 1, pp. 227–244, Mar. 2017. DOI: https://doi.org/10.1007/s11554-015-0517-3.
I. S. Acikgoz, M. Teke, U. Kutbay, and F. Hardalac, “Performance evaluation of pansharpening methods on GPU for RASAT images,” RAST 2015 - Proceedings of 7th International Conference on Recent Advances in Space Technologies, pp. 283–288, 2015. DOI: https://doi.org/10.1109/RAST.2015.7208356.
A. Asaduzzaman, A. Martinez, and A. Sepehri, “A time-efficient image processing algorithm for multicore/manycore parallel computing,” in Conference Proceedings - IEEE SOUTHEASTCON, 2015, vol. 2015-June, no. June. DOI: https://doi.org/10.1109/SECON.2015.7132924.
Y. Ma, L. Chen, P. Liu, and K. Lu, “Parallel programing templates for remote sensing image processing on GPU architectures: design and implementation,” Computing, vol. 98, no. 1–2, pp. 7–33, Jan. 2016. DOI: https://doi.org/10.1007/s00607-014-0392-y.
J. Zhang and K. H. Lim, “Implementation of a covariance-based principal component analysis algorithm with a CUDA-enabled graphics processing unit,” in International Geoscience and Remote Sensing Symposium (IGARSS), 2011. DOI: https://doi.org/10.1109/IGARSS.2011.6049460.
S. D. Jawak and A. J. Luis, “A Comprehensive Evaluation of PAN-Sharpening Algorithms Coupled with Resampling Methods for Image Synthesis of Very High Resolution Remotely Sensed Satellite Data,” Advances in Remote Sensing, vol. 02, no. 04, pp. 332–344, 2013. DOI: https://doi.org/10.4236/ars.2013.24036.
M. Lillo-Saavedra, C. Gonzalo, A. Arquero, and E. Martinez, “Fusion of multispectral and panchromatic satellite sensor imagery based on tailored filtering in the Fourier domain,” International Journal of Remote Sensing, vol. 26, no. 6, pp. 1263–1268, Mar. 2005. DOI: https://doi.org/10.1080/01431160412331330239.
H. Ghassemian, “A review of remote sensing image fusion methods,” Information Fusion, vol. 32. Elsevier B.V., pp. 75–89, 01-Nov-2016. DOI: https://doi.org/10.1016/j.inffus.2016.03.003.
Z. Liu, E. Blasch, G. Bhatnagar, V. John, W. Wu, and R. S. Blum, “Fusing synergistic information from multi-sensor images: An overview from implementation to performance assessment,” Information Fusion, vol. 42, pp. 127–145, Jul. 2018. DOI: https://doi.org/10.1016/j.inffus.2017.10.010.
L. Alparone, L. Wald, J. Chanussot, C. Thomas, P. Gamba, and L. M. Bruce, “Comparison of pansharpening algorithms: Outcome of the 2006 GRS-S data-fusion contest,” in IEEE Transactions on Geoscience and Remote Sensing, 2007, vol. 45, no. 10, pp. 3012–3021. DOI: https://doi.org/10.1109/TGRS.2007.904923.