한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

  • 제24권6호
  • /
  • Pages.11-19
  • /
  • 2019
  • /
  • 1598-849X(pISSN)
  • /
  • 2383-9945(eISSN)
한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

Scene-based Nonuniformity Correction by Deep Neural Network with Image Roughness-like and Spatial Noise Cost Functions

  • 투고 : 2019.04.23
  • 심사 : 2019.06.10
  • 발행 : 2019.06.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this paper, a new Scene-based Nonuniformity Correction (SBNUC) method is proposed by applying Image Roughness-like and Spatial Noise cost functions on deep neural network structure. The classic approaches for nonuniformity correction require generally plenty of sequential image data sets to acquire accurate image correction offset coefficients. The proposed method, however, is able to estimate offset from only a couple of images powered by the characteristic of deep neural network scheme. The real world SWIR image set is applied to verify the performance of proposed method and the result shows that image quality improvement of PSNR 70.3dB (maximum) is achieved. This is about 8.0dB more than the improved IRLMS algorithm which preliminarily requires precise image registration process on consecutive image frames.

키워드

CPTSCQ_2019_v24n6_11_f0001.png 이미지

Fig. 2. Block Diagram of the Improved IRLMS

CPTSCQ_2019_v24n6_11_f0002.png 이미지

Fig. 3. Structure of Deep Neural Network Scene based Non-uniformity Correction

CPTSCQ_2019_v24n6_11_f0003.png 이미지

Fig. 6. Structure of Neural Network

CPTSCQ_2019_v24n6_11_f0004.png 이미지

Fig. 7. Activation Function ReLU(Rectified Linear Unit)

CPTSCQ_2019_v24n6_11_f0005.png 이미지

Fig. 8. Cardinal 640

CPTSCQ_2019_v24n6_11_f0006.png 이미지

Fig. 9. Learning Result of Total Cost Function

CPTSCQ_2019_v24n6_11_f0007.png 이미지

Fig. 10. Learning Result of Offset Image by Learning Step

CPTSCQ_2019_v24n6_11_f0008.png 이미지

Fig. 11. PSNR Result

CPTSCQ_2019_v24n6_11_f0009.png 이미지

Fig. 12. Compare the Proposed Results. (a) is 20th frame results, (b) is 440th Frame Results, (c) is 650th Frame Results (In each section, left top: proposed output, left bottom: proposed estimated offset, right top: improved IRLMS output, right bottom: improved IRLMS estimated offset)

CPTSCQ_2019_v24n6_11_f0010.png 이미지

Fig. 13. Proposed Result with two frames. (Top to bottom : proposed output, true image, input image, proposed estimated offset)

CPTSCQ_2019_v24n6_11_f0011.png 이미지

Fig. 1. (a) is Masked phase correlation registration, (b) is Schematic diagram of the overlay of two frames

CPTSCQ_2019_v24n6_11_f0012.png 이미지

Fig. 4. (a) is image with High Roughness, (b) is image with Low Roughness

CPTSCQ_2019_v24n6_11_f0013.png 이미지

Fig. 5. (a) is Image with High Spatial Noise, (b) is Image with Low Spatial Noise

참고문헌

  1. D. A. Scribner, M. Kruer, and J. Killiany, "Infrared focal plane array technology," Proc. IEEE, vol. 79, no. 1, pp. 66-85, Jan 1991. https://doi.org/10.1109/5.64383
  2. A. Friedenberg and I. Goldbatt, "Nonuniformity two-point linear correction errors in infrared focal plane arrays," Opt. Eng. 37(4), pp. 1251-1253, April, 1998. https://doi.org/10.1117/1.601890
  3. O. Riou, S. Berrebi, and P. Bremond, "Nonuniformity correction and thermal drift compensation of thermal infrared camera," Proc. SPIE 5405, pp 294-302, April, 2004.
  4. R. Hardie, F. Baxley, B. Brys, and P. Hytla, "Scene-based nonuniformity correction with reduced ghosting using a gated LMS algorithm," Opt. Express 17, pp. 14918-14933, 2009. https://doi.org/10.1364/OE.17.014918
  5. J. Harris and Y. Chiang, "Minimizing the 'ghosting' artifact in scene-based nonuniformity correction," Proc. SPIE 3377, pp. 106-113, 1998.
  6. Russell C. Hardie, Majeed M. Hayat, Earnest Armstrong, and Brian Yasuda, "Scene-based nonuniformity correction with video sequences and registration," Applied Optics Vol. 39, Issue 8, pp. 1241-1250, 2000. https://doi.org/10.1364/AO.39.001241
  7. Chao Zuo, Qian Chen, Guohua Gu and Xiubao Sui, "Scene-Based Nonuniformity Correction Algorithm Based on Interframe Registration," J Opt Soc Am A Opt Image Sci Vis 28 (6), pp. 1164-1176, Jun, 2011. https://doi.org/10.1364/JOSAA.28.001164
  8. Chao Zuo, Qian Chen, Guohua Gu, Xiubao Sui, and Jianle Ren, "Improved interframe registration based nonuniformity correction for focal plane arrays," ELSEVIER Infrared Physics & Technology Vol 55, Issue 4, pp. 263-269, July 2012. https://doi.org/10.1016/j.infrared.2012.04.002
  9. D. Scribner, K. Sarkady, M. Kruer, J. Caldfield, J. Hunt, M. Colbert, and M. Descour, "Adaptive nonuniformity correction for IR focal plane arrays using neural networks," Proc. SPIE 1541, pp. 100-109, 1991.
  10. Chao Zuo, Yuzhen Zhang, Qian Chen, Guohua Gu, Weixian Qian, Xiubao Sui and Jianle Ren, "A two-frame approach for scene-based nonuniformity correction in array sensors," ELSEVIER Infrared Physics & Technology Vol 60, pp. 190-196, Sep 2013. https://doi.org/10.1016/j.infrared.2013.05.001
  11. Yohann Tendero, Stephane Landeau and Jerome Gilles, "Non-uniformity Correction of Infrared Images by Midway Equalization," Image Processing On Line, pp. 134-146, Jan 2012. https://doi.org/10.5201/ipol.2012.glmt-mire
  12. Lee Jonhho, Ra Jongbeom, "Improvement on a optimization algorithm for non-uniformity correction of infrared videos," Master Thesis, KAIST, Department of Electrical Engineering, 2013.
  13. Kim Seongmin, Bae Yoonsung, Jang Jaeho, and Ra Jongbeom, "Fixed Pattern Noise Reduction in Infrared Videos Based on Joint Correction of Gain and Offset," The Institute of Electronics and Information Engineers, Vol. 49, SP. 2, pp. 35-44, 2012. https://doi.org/10.5573/ieek.2012.49.9.035
  14. Gun-hyo No, Yong-hee Hong, Jin-ho Park, Ho-jin Jhee, "Scene-based Nonuniformity Correction for Neural Network Complemented by Reducing Lense Vignetting Effect and Adaptive Learning rate," Journal of The Korea Society of Computer and Information, Vol. 23 No. 7, pp. 81-90, July 2018. https://doi.org/10.9708/JKSCI.2018.23.07.081
  15. Yong-hee Hong, Keun-Jae Lee, Hong-Rak Kim, Ho-Jin Jhee, "Scene-based Nonuniformity Correction Complemented by Block Reweighting and Global Offset Initialization," Journal of The Korea Society of Computer and Information, Vol. 22 No. 8, pp. 15-23, August 2017. https://doi.org/10.9708/JKSCI.2017.22.08.015
  16. D. L. Perry and E. L. Dereniak, "Linear theory of nonuniformity correction in infrared staring sensors," Opt. Eng. 32, pp. 1854-1859, 1993. https://doi.org/10.1117/12.145601