Abstract
For several decades, the camera spatial resolution is gradually increasing with the CMOS technology evolution. The image sensors provide more and more pixels, generating new constraints for suitable optics. As an alternative, promising solutions propose super-resolution (SR) techniques to reconstruct high-resolution images or video without modifying the sensor architecture. However, most of the SR implementations are far from reaching real-time performance on a low-budget hardware platform. Moreover, convincing state-of-the-art studies reveal that artifacts can be observed in highly textured areas of the image. In this paper, we propose a local adaptive spatial super resolution (LASSR) method to fix this limitation. LASSR is a two-step SR method including a machine learning-based texture analysis and a fast interpolation method that performs a pixel-by-pixel SR. Multiple evaluations of our method are also provided using standard image metrics for quantitative evaluation and also a psycho-visual assessment for a perceptual evaluation. A first FPGA-based implementation of the proposed method is then presented. It enables high-quality 2–4 k super-resolution videos to be performed at 16 fps, using only 13% of the FPGA capacity, opening the way to reach more than 60 fps by executing several parallel instances of the LASSR code on the FPGA.
Similar content being viewed by others
References
Arivazhagan, S., Ganesan, L.: Texture classification using wavelet transform. Pattern Recogn. Lett. 24(9–10), 1513–1521 (2003)
Baker, S., Kanade, T.: Hallucinating faces. In: Proceedings 4th IEEE international conference on automatic face and gesture recognition (Cat. No. PR00580), pp. 83–88 (2000)
Borman, S., Stevenson, R.L.: Super-resolution from image sequences-a review. In: 1998 Midwest symposium on circuits and systems (Cat. No. 98CB36268), pp. 374–378 (1998)
Bowen, Oliver, Bouganis, Christos-Savvas: real-time image super resolution using an FPGA. In: 2008 International conference on field programmable logic and applications, pp. 89–94 (2008)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Chan, R.H., Chan, T.F., Shen, L., Shen, Z.: Wavelet algorithms for high-resolution image reconstruction. SIAM J. Sci. Comput. 24, 1408–1432 (2003)
Chang, C.-C., Lin, C.-J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27:1–27:27 (2011)
Choi, J.-S., Kim, M.: Super-interpolation with edge-orientation-based mapping Kernels for low complex 2 x upscaling. IEEE Trans. Image Process. 25, 469–483 (2016)
Coomans, D., Massart, D.L.: Alternative k-nearest neighbour rules in supervised pattern recognition: part 1. K-nearest neighbour classification by using alternative voting rules. Anal. Chim. Acta 136, 15–27 (1982)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Computer vision—ECCV 2014, 13th European conference, Zurich, pp. 184–199 (2014)
Dubois, J., Mattavelli, M.: Embedded co-processor architecture for CMOS based image acquisition. In: Image processing, 2003. Proceedings 2003 international conference on, volume 2, IEEE, pp. II–591 (2003)
Farsiu, S., Robinson, D., Elad, M., Milanfar, P.: Advances and challenges in super-resolution. Int. J. Imaging Syst. Technol. 14, 47–57 (2004)
Feichtenhofer, C., Fassold, H., Schallauer, P.: A perceptual image sharpness metric based on local edge gradient analysis. IEEE Signal Process. Lett. 20(4), 379–382 (2013)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Comput. Graph. Appl. 22, 56–65 (2002)
Freund, Y., Schapire, R., Abe, N.: A short introduction to boosting. J. Jpn. Soc. Artif. Intell. 14(771–780), 1612 (1999)
Georgis, G., Lentaris, G., Reisis, D.: Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution. J. Real-Time Image Process. pp. 1–28 (2016)
Gohshi, S.: A new signal processing method for video image-reproduce the frequency spectrum exceeding the Nyquist frequency using a single frame of the video image. Springer, New York (2013)
Guan, J., Yang, J., Huang, Y., Li, W.: Maximum a posteriori-based angular superresolution for scanning radar imaging. IEEE Trans. Aerosp. Electron. Syst. 50, 2389–2398 (2014)
Haralick, R.M.: Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)
He, Z., Huang, H., Jiang, M., Bai, Y., Luo, G.: FPGA-based real-time super-resolution system for ultra high definition videos. In: 2018 IEEE 26th annual international symposium on field-programmable custom computing machines (FCCM), Boulder, CO, pp. 181–188 (2018)
Jung, C., Ke, P., Sun, Z., Aiguo, G.: A fast deconvolution-based approach for single-image super-resolution with GPU acceleration. J. Real-Time Image Proc. 14, 501–512 (2018)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 1646–1654 (2016)
Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 1637–1645 (2016)
Kim, Y., Choi, J.-S., Kim, M.: 2X super-resolution hardware using edge-orientation-based linear mapping for real-time 4K UHD 60 fps video applications. IEEE Trans. Circ. Syst. II Express Briefs 65, 1274–1278 (2018)
Kim, Y., Choi, J.-S., Kim, M.: A real-time convolutional neural network for super-resolution on FPGA with applications to 4K UHD 60 fps video services. IEEE Trans. Circ. Syst. Video Technol. pp. 1–1 (2018)
Kronsteiin, D.: Video stream scaler. www.opencores.org (2011)
Li, H., Huang, Y., Kuang, C., Liu, X.: Method of super-resolution based on array detection and maximum-likelihood estimation. Appl. Opt. 55, 9925 (2016)
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp. 1132–1140 (2017)
Madhukar, B.N., Narendra, R.: Lanczos resampling for the digital processing of remotely sensed images. In: V.S. Chakravarthi, Yasha Jyothi M.S., Rekha P. (eds), Proceedings of international conference on VLSI, communication, advanced devices, signals and systems and networking (VCASAN-2013), Springer, India, pp. 403–411 (2013)
Manabe, T., Shibata, Y., Oguri, K.: FPGA implementation of a real-time super-resolution system using a convolutional neural network. In: 2016 International conference on field-programmable technology (FPT), Xi’an, pp. 249–252 (2016)
Martin, Č: Perceptually based image quality assessment and image transformations. Ph.d. thesis, Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University in Prague (2008)
Matsuyama, T., Miura, S.-I., Nagao, M.: Structural analysis of natural textures by Fourier transformation. Comput. Vis. Graph Image Process. 24(3), 347–362 (1983)
Mitéran, J., Jiri Matas, E., Bourennane, M.P., Dubois, J.: Automatic hardware implementation tool for a discrete adaboost-based decision algorithm. EURASIP J. Appl. Sig. Process. 2005, 1035–1046 (2005)
Mosqueron, R., Dubois, J., Mattavelli, M., Mauvilet, D.: Smart camera based on embedded hw/sw coprocessor. EURASIP J. Embedded Syst. 2008(1), 597872 (2008)
Namboodiri, V.P., De Smet, V., Van Gool, L.: Systematic evaluation of super-resolution using classification. In: 2011 Visual communications and image processing (VCIP), IEEE, pp. 1–4 (2011)
Nasrollahi, K., Moeslund, T.B.: Super-resolution: a comprehensive survey. Mach. Vis. Appl. 25, 1423–1468 (2014)
Nguyen, K, Fookes, C., Sridharan, S., Tistarelli, M., Nixon, M.: Super-resolution for biometrics: a comprehensive survey. Pattern Recognit. 78, 23–42 (2018)
van Ouwerkerk, J.D.: Image super-resolution survey. Image Vis. Comput. 24, 1039–1052 (2006)
Park, S.C., Park, M.K., Kang, M.G.: Super-resolution image reconstruction: a technical overview. IEEE Signal Process. Magn. 20, 21–36 (2003)
Pérez, J., Magdaleno, E., Pérez, F., Rodríguez, M., Hernández, D., Corrales, J.: Super-resolution in plenoptic cameras using FPGAs. Sensors 14, 8669–8685 (2014)
Qin, F., He, X., Chen, W., Yang, X., Wei, W.: Video super resolution reconstruction based on subpixel registration and iterative back projection. J. Electron. Imaging 18, 013007 (2009)
Quevedo, E., Sánchez, L., Callicó, G.M., Tobajas, F., de la Cruz, J., de Armas, V., Sarmiento, R.: Super-resolution with selective filter based on adaptive window and variable macro-block size. J. Real Time Image Proc. 15, 389–406 (2018)
Redlich, R., Araneda, L., Saavedra, A., Figueroa, M.: An embedded hardware architecture for real-time super-resolution in infrared cameras. In: 2016 Euromicro conference on digital system design (DSD), pp. 184–191 (2016)
Rhee, S., Kang, M.G.: Discrete cosine transform based regularized high-resolution image reconstruction algorithm. Opt. Eng. 38, 1348–1356 (1999)
Robinson, M.D., Chiu, S.J., Toth, C.A., Izatt, J.A., Lo, J.Y., Farsiu, S.: New applications of super-resolution in medical imaging. In: Milanfar, P. (ed.) Super-resolution imaging, pp. 383–412. CRC Press, Boca Raton (2010)
Sajjadi, M.S.M., Scholkopf, B., Hirsch, M.: Enhancement: single image super-resolution through automated texture synthesis. In: Proceedings of the IEEE international conference on computer vision, pp. 4491–4500 (2017)
Seyid, K., Blanc, S., Leblebici, Y.: Hardware implementation of real-time multiple frame super-resolution. In: 2015 IFIP/IEEE international conference on very large scale integration (VLSI-SoC), Daejeon, pp. 219–224 (2015)
Shen, W., Fang, L., Chen, X., Xu, H.: Projection onto convex sets method in space-frequency domain for super resolution. J. Comput. 9(8), 1959–1966 (2014)
Shocher, A., Cohen, N., Irani, M.: Zero-shot super-resolution using deep internal learning. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, pp. 3118–3126 (2018)
Tsai, R.Y., Huang, T.S.: Multiframe image restoration and registration. In: Tsai, R.Y., Huang, T.S. (eds.) Advances in Computer Vision and Image Processing, pp. 317–339. JAI Press Inc., Stamford (1984)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Berlin (2013)
Wang, Z., Bovik, H.R., Sheikh, A.C., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wang, Z., Chen, J., Steven, C.H.H.: Deep learning for image super-resolution: a survey (2019)
Yang, C.-Y., Ma, C., Yang, M.-H. (2014) Single-image super-resolution: a benchmark. In: David, F., Tomas, P., Bernt, S., Tinne, T. (eds), Computer Vision—ECCV 2014, Springer, Cham, pp. 372–386 (2014)
Yang, D., Li, Z., Xia, Y., Chen, Z.: Remote sensing image super-resolution: challenges and approaches. In: 2015 IEEE international conference on digital signal processing (DSP), pp. 196–200 (2015)
Yang, J., Huang, T.: Image super-resolution: historical overview and future challenges. In: Milanfar, P. (ed.) Super-Resolution Imaging, pp. 1–33. CRC Press, Boca Raton (2010)
Yuan, Y., Yang, X., Wei, W., Li, H., Liu, Y., Liu, K.: A fast single-image super-resolution method implemented with CUDA. J. Real-Time Image Proc. 16, 81–97 (2019)
Yue, L., Shen, H., Li, J., Yuan, Q., Zhang, H., Zhang, L.: Image super-resolution: the techniques, applications, and future. Sig. Process. 128, 389–408 (2016)
Zhang, G.P.: Neural networks for classification: a survey. IEEE Trans. Syst. Man. Cybern. Part C (Appl. Rev.) 30(4), 451–462 (2000)
Zhang, L., Zhang, H., Shen, H., Li, P.: A super-resolution reconstruction algorithm for surveillance images. Sig. Process. 90, 848–859 (2010)
Zhou, F., Yao, R., Liu, B., Qiu, G.: Visual quality assessment for super-resolved images: database and method. IEEE Trans. Image Process. pp. 1–1 (2019)
Acknowledgements
This work was funded by EU Horizon 2020 ECSEL JU research and innovation program under Grant agreement 662222 (EXIST).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Marin, Y., Miteran, J., Dubois, J. et al. An FPGA-based design for real-time super-resolution reconstruction. J Real-Time Image Proc 17, 1769–1785 (2020). https://doi.org/10.1007/s11554-020-00944-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-020-00944-5