Low-cost, low-resolution IR system with super-resolution interpolation of thermal images for industrial applications

• Autorzy: Więcek P. , Sankowski D.
• Języki publikacji: EN

Abstrakty

EN

In this paper authors present application of deep neural networks for super-resolution interpolation of infrared images. A residual neural network with reduced number of layers was used. The transfer learning using RGB visual images was applied in this research. The validation of the network was performed for 32×24 and 160×120 pixels infrared images, with the up-sampling scale factors 2, 3, 4, 5 and 6. Monitoring of high temperature industrial processes like inductive heating and thermal hardening is the main application of proposed methods.

Słowa kluczowe

EN

Super-resolution; residual deep neural networks; image interpolation

• Wydawca: Wydawnictwo PAK
• Czasopismo: Measurement Automation Monitoring
• Rocznik: 2018
• Tom: Vol. 64, No. 4
• Strony: 108--111
• Opis fizyczny: Bibliogr. 18 poz., rys., tab., wykr.

Twórcy

autor

Więcek P.

• Lodz University of Technology, Institute of Applied Computer Science, Stefanowskiego 18/22, 90-537 Łódź, Poland

autor

Sankowski D.

• Lodz University of Technology, Institute of Applied Computer Science, Stefanowskiego 18/22, 90-537 Łódź, Poland

Bibliografia

• [1] Bengio Y., Simard P., and Frasconi P.: Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2):157–166, 1994.
• [2] Glorot X. and Bengio Y.: Understanding the difficulty of training deep feedforward neural networks. In AISTATS, 2010.
• [3] Ioffe S. and Szegedy C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, 2015.
• [4] Lim Sanghyun B., Heewon Kim S., Nah S, Mu Lee K.: Enhanced Deep Residual Networks for Single Image Super-Resolution. IEEE Conference on Computer Vision and Pattern Recognition Workshops, July 21- 26, Honolulu, 2017.
• [5] Li J., Fang F., Mei K., Zhang G.: Multi-scale Residual Network for Image Super-Resolution. 15th European Conference on Computer Vision, Munich, September 8 – 14, 2018.
• [6] Kim J-H., Lee J-S.: Deep Residual Network with Enhanced Upscaling Module for Super-Resolution. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, Salt-Lake City, June 18-22, 2018, pp. 800-808.
• [7] Zhang Y., Li K., Li K., Wang L., Zhong B., Fu Y.: Image Super-Resolution Using Very Deep Residual Channel Attention Networks, 15th European Conference on Computer Vision, Munich, September 8 – 14, 2018.
• [8] Kim J., Lee J, J. K., Lee K. M.: Accurate Image Super-Resolution Using Very Deep Convolutional Networks. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, pp. 1646-1654.
• [9] Zhang X., Li C., Meng Q., Liu S., Zhang Y., Wang J.: Infrared Image Super Resolution by Combining Compressive Sensing and Deep Learning, Sensors (Basel). 2018 Aug; 18(8): 2587.
• [10] https://nl.mathworks.com/help/images/single-image-super-resolution-using-deep-learning.html
• [11] Minkina W., Dudzik S.. Infrared Thermography: Errors and Uncertainties, Willey, 2009, ISBN-13: 9780470747186.
• [12] Maldague X.: Theory and Practice of Infrared Technology for Nondestructive Testing, Willey, 2001, ISBN: 978-0-471-18190-3
• [13] Zgraja J.: Impedance matching in dual-frequency induction heating systems, Przeglad Elektrotechniczny, vol. 94, issue: 4, 2018, pp. 55-58.
• [14] https://data.vision.ee.ethz.ch/cvl/DIV2K/
• [15] https://www.flir.com/products/flir-one-pro/
• [16] https://www.melexis.com/en/product/mlx90640/far-infrared-thermal-sensor-array
• [17] https://www.optris.global/thermal-imager-optris-pi160
• [18] https://botland.com.pl/pl/plytki-zgodne-z-arduino-sparkfun/6858-sparkfun-teensy-32-arm-cortex-m4-zgodny-z-arduino.html

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).