DOI QR코드

DOI QR Code

SRGAN 기반의 CCTV 영상 화질 개선 기법

Enhancement Method of CCTV Video Quality Based on SRGAN

  • Ha, Hyunsoo (Dept. of Computer Eng., Graduate School, The Catholic University of Korea) ;
  • Hwang, Byung-Yeon (Dept. of Computer Eng., Graduate School, The Catholic University of Korea)
  • 투고 : 2017.11.27
  • 심사 : 2018.02.08
  • 발행 : 2018.09.30

초록

CCTV has been known to possess high level of objectivity and utility. Hence, the government has recently focused on replacing low quality CCTV with higher quality ones or even by adding high resolution CCTV. However, converting all existing low-quality CCTV to high quality can be extremely costly. Furthermore, low quality videos prior to CCTV replacement are likely to be of poor quality and thus not utilized correctly. In order to solve these problems, this paper proposes a method to improve videos quality of images using SRGAN(Super Resolution Generative Advisory Networks). Through experiments, we have proven that it is possible to improve low quality CCTV videos clearly. For this experiment, a total of 4 types of CCTV videos were used and 10,000 images were sampled from each type. Those images could then be used for machine learning. The fact that the pre-process for machine learning has been done manually and the long time that required for machine learning seems to be complementary.

키워드

참고문헌

  1. Y.K. Kwak and T.H. Lim, "A Study on the CCTV Effective Utilization Method for the Crime Prevention and Action," Journal of Korean Association for P ublic Security Adminstration, Vol. 8, No. 2, pp. 119-144, 2011.
  2. S.M. Rho, "Artificial Intelligence Technology R&D Trend by Patent Analysis," Journal of Digital Contents Society, Vol. 18, No. 2, pp. 423-428, 2017. https://doi.org/10.9728/dcs.2017.18.2.423
  3. J.H. Lee and J.S. Yoo, "Generative Adversarial Nets Analysis and Applications," Proceeding of the Korean Society of Broadcast Engineers Conference, pp. 36-39, 2017.
  4. M.S. Ko, H.G. Roh, and K.H. Lee, "GANMOOK: Generative Adversarial Network to Stylize Images Like Ink Wash Painting," Proceeding of the Korea Institute of Information Scientists and Engineers, pp. 793-795, 2017.
  5. C. Ledig, L. Theis, F. Huszar, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, and Z. Wang, "Photo-realistic Single Image Super-resolution Using a Generative Adversarial Network," arXiv P reprint arXiv: 1609.04802, 2016.
  6. J.W. Shin, Y.S. Noh, and S.Y. Park, "Generating Multi-Class Images Using a Generative Adversarial Network," Proceeding of the Korea Institute of Information Scientists and Engineers, pp. 811-813, 2017.
  7. S.J. Hong, S.K. Lee, and S.I. Yang, "An Oversampling Technique Based on Generative Adversarial Network for Solving Imbalance Problem of Game Dataset," Proceeding of the Institute of Electronics Engineers of Korea, pp. 1227-1228, 2017.
  8. J. Jeon and M.C. Kim, "Generative Adversarial Network Based CNN Model for Artifact Reduction on HEVC-encoded Video," Proceeding of The Korean Society of Broadcast Engineers, pp. 192-193, 2017.
  9. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative Adversarial Nets," Advances in Neural Information Processing Systems, pp. 2672-2680, 2014.
  10. S.B. Lee, H.G. Kim, K.S. Shin, and J.H. Nang, "Performance Analysis of Convolution Neural Network and Generative Adversarial Network for Super Resolution," Proceeding of The Korean Society of Broadcast Engineers, pp. 931-933, 2017.
  11. J.W. Kim, J.K. Lee, and K.M. Lee, "Accurate Image Super-resolution Using Very Deep Convolutional Networks," Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, 2016.
  12. D.H. Lee, H.S. Lee, K.J. Lee, and H.J. Lee, "Fast Very Deep Convolutional Neural Network with Deconvolution for Super-Resolution," Journal of Korea Multimedia Society, Vol. 20, No. 11, pp. 1750-1758, 2017. https://doi.org/10.9717/KMMS.2017.20.11.1750
  13. J.M. Choi and D.J. Kang, "Super-resolution for License Plate Using Generative Adversarial Networks," Proceeding of Institute of Control Robotics and Systems, pp. 262-263, 2017.
  14. J.M. Choi and D.J. Kang, "Deep Super-resolution Method via Generative Adversarial Networks for License Place Image Enhancement," Journal of Institute of Control Robotics and Systems, Vol. 29, No. 8, pp. 635-643, 2017.
  15. K.V. Suresh, G.M. Kumar, and A.N. Rajagopalan, "Super-resolution of License Plates in Real Traffic Videos," IEEE Transactions on Intelligent Transportation Systems, Vol. 8, No. 2, pp. 321-331, 2007. https://doi.org/10.1109/TITS.2007.895291