The Generating Super Resolution of Thermal Image based on Deep Learning

Ismail Ismail; Y. Yefriadi; Y. Yuhefizar; Fibriyanti; Zulka Hendri

doi:10.29207/resti.v6i2.3934

Ismail Ismail Politeknik Negeri Padang
Y. Yefriadi Politeknik Negeri Padang
Y. Yuhefizar Politeknik Negeri Padang
Fibriyanti Politeknik Negeri Padang
Zulka Hendri Politeknik Negeri Padang

DOI: https://doi.org/10.29207/resti.v6i2.3934

Keywords: Super resolution, thermal image, deep learning

Abstract

The need for a high resolution to the thermal image is urgent and essential. The high resolution of the thermal image can give accurate information on the heat distribution map of the objects. The accurate heat distribution maps can give accurate temperature information. This accurate temperature measurement is used for measuring many objects such as electric motors, engines, the human body, and so on—this information is used to detect the anomalies of the object to find the damaged parts. The anomalies are considered damaged parts found in solar panels, agricultural fields, buildings, bridges, etc. As the super-resolution of thermal images is very important, generating them is compulsory. The camera for obtaining super-resolution thermal images is rare, not available in the common market. Furthermore, this kind of device is costly too. Therefore not all the users, such as farmers or technicians, can have them. In order to handle the problem, the proposed method has the purpose of generating super-resolution thermal images economically and is more accessible through the deep learning method. The dataset is taken from the solar panel. The results show that the proposed method can handle the low-resolution problem of thermal images.

Downloads

Download data is not yet available.

References

Ismail, H.Kamarul, S.Yondri, Yefriadi, andN.Harun, “The Detecting of damaged Conductors with Guided Image Filter.pdf,” in Ico-Asnitech, International Conf on Applied Sciences, Inf and Technology, 2019.

X.Hu et al., “Towards effective learning for face super-resolution with shape and pose perturbations,” Knowledge-Based Syst., vol. 220, p. 106938, 2021.

J.Valli, A.Garcia-Burgos, L. M.Rooney, B. V.deMelo e Oliveira, R. R.Duncan, andC.Rickman, “Seeing beyond the limit: A guide to choosing the right super-resolution microscopy technique,” J. Biol. Chem., vol. 297, no. 1, p. 100791, 2021.

L.Ren, Z.Pan, J.Cao, andJ.Liao, “Infrared and visible image fusion based on variational auto-encoder and infrared feature compensation,” Infrared Phys. Technol., vol. 117, no. October 2020, p. 103839, 2021.

H.Song andY.Yang, “Super-resolution visualization of subwavelength defects via deep learning-enhanced ultrasonic beamforming: A proof-of-principle study,” NDT E Int., vol. 116, no. July, p. 102344, 2020.

J.Wu, L.Cheng, M.Chen, T.Wang, Z.Wang, andH.Wu, “Super-resolution infrared imaging via multi-receptive field information distillation network,” Opt. Lasers Eng., vol. 145, no. September 2020, p. 106681, 2021.

J.Liu, Y.Liu, H.Wu, J.Wang, X.Li, andC.Zhang, “Single image super-resolution using feature adaptive learning and global structure sparsity,” Signal Processing, vol. 188, p. 108184, 2021.

Y.Zou, L.Zhang, C.Liu, B.Wang, Y.Hu, andQ.Chen, “Super-resolution reconstruction of infrared images based on a convolutional neural network with skip connections,” Opt. Lasers Eng., vol. 146, no. July, p. 106717, 2021.

T. Y.Han, D. H.Kim, S. H.Lee, andB. C.Song, “Infrared image super-resolution using auxiliary convolutional neural network and visible image under low-light conditions,” J. Vis. Commun. Image Represent., vol. 51, no. January, pp. 191–200, 2018.

D. T.Lloyd, A.Abela, R. A.Farrugia, A.Galea, andG.Valentino, “Optically Enhanced Super-Resolution of Sea Surface Temperature Using Deep Learning,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022.

S.Ahmadi, J. C.Hauffen, M.Ziegler, L.Kastner, andP.Jung, “Photothermal-SR-Net: A Customized Deep Unfolding Neural Network for Photothermal Super Resolution Imaging,” IEEE Trans. Instrum. Meas., vol. 71, 2022.

M.Vollmer, “Infrared Thermal Imaging,” Comput. Vis., vol. 21, no. 17, pp. 666–670, 2021.

Y.Cao, F.Wang, Z.He, J.Yang, andY.Cao, “Boosting Image Super-Resolution via Fusion of Complementary Information Captured by Multi-Modal Sensors,” IEEE Sens. J., vol. 22, no. 4, pp. 3405–3416, 2022.

X.Chen, G.Zhai, J.Wang, C.Hu, andY.Chen, “Color guided thermal image super resolution,” VCIP 2016 - 30th Anniv. Vis. Commun. Image Process., vol. 1, pp. 13–16, 2017.

F.Almasri andO.Debeir, “RGB Guided Thermal Super-Resolution Enhancement,” 2018 4th Int. Conf. Cloud Comput. Technol. Appl. Cloudtech 2018, 2018.

Q. M.Liu, R. S.Jia, Y. B.Liu, H.BinSun, J. Z.Yu, andH. M.Sun, “Infrared image super-resolution reconstruction by using generative adversarial network with an attention mechanism,” Appl. Intell., vol. 51, no. 4, pp. 2018–2030, 2021.

H.Gupta andK.Mitra, “Toward Unaligned Guided Thermal Super-Resolution,” IEEE Trans. Image Process., vol. 31, pp. 433–445, 2022.

P.Kansal andS.Nathan, “A multi-level supervision model: A novel approach for thermal image super resolution,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., vol. 2020-June, pp. 426–431, 2020.

K.Prajapati et al., “Channel split convolutional neural network (ChaSNet) for thermal image super-resolution,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., pp. 4363–4372, 2021.

E.Turgay, G.Mikroelektronik, E. E.M, andT.Universitesi, “¨ Unt ¨ Un Termal G Or Ulerde Desen Korumali S Uper ¸ Oz Uk Texture Preserving Super Resolution In Thermal Images Is u g Orta Do ˘,” no. Siu, pp. 578–581, 2011.

W.Jiang andX.Luo, “Research on super-resolution reconstruction algorithm of remote sensing image based on generative adversarial networks,” Proc. 2019 IEEE 2nd Int. Conf. Autom. Electron. Electr. Eng. AUTEEE 2019, pp. 438–441, 2019.

W.Yang, X.Zhang, Y.Tian, W.Wang, J. H.Xue, andQ.Liao, “Deep Learning for Single Image Super-Resolution: A Brief Review,” IEEE Trans. Multimed., vol. 21, no. 12, pp. 3106–3121, 2019.

H.Yu, W.Liu, C.Long, B.Dong, Q.Zou, andC.Xiao, “Luminance Attentive Networks for HDR Image and Panorama Reconstruction,” vol. 40, no. 7, 2021.

U.Sara, M.Akter, andM. S.Uddin, “Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study,” J. Comput. Commun., vol. 07, no. 03, pp. 8–18, 2019.

A.Mittal, R.Soundararajan, andA. C.Bovik, “Making a ‘completely blind’ image quality analyzer,” IEEE Signal Process. Lett., vol. 20, no. 3, pp. 209–212, 2013.