Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Single-Image Dehazing based on Scene Brightness for Perspective Preservation

  • Young-Su Chung (Department of Intelligent Robot Engineering, Pukyong National University) ;
  • Nam-Ho Kim (School of Electrical Engineering, Pukyong National University)
  • Received : 2023.07.27
  • Accepted : 2023.09.25
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Bad weather conditions such as haze lead to a significant lack of visibility in images, which can affect the functioning and reliability of image processing systems. Accordingly, various single-image dehazing (SID) methods have recently been proposed. Existing SID methods have introduced effective visibility improvement algorithms, but they do not reflect the image's perspective, and thus have limitations that distort the sky area and nearby objects. This study proposes a new SID method that reflects the sense of space by defining the correlation between image brightness and haze. The proposed method defines the haze intensity by calculating the airlight brightness deviation and sets the weight factor of the depth map by classifying images based on the defined haze intensity into images with a large sense of space, images with high intensity, and general images. Consequently, it emphasizes the contrast of nearby images where haze is present and naturally smooths the sky region to preserve the image's perspective.

Keywords

References

  1. L. F. Shi, B. H. Chen, S. C. Huang, A. O. Larin, O. S. Seredin, A. V. Kopylov, and S. Y. Kuo, "Removing haze particles from single image via exponential inference with support vector data description," IEEE Transactions on Multimedia, vol. 20, no. 9, pp. 2503-2512, Sep. 2018. DOI: 10.1109/TMM.2018.2807593.
  2. S. C. Raikwar, and S. Tapaswi, "Lower bound on transmission using non-linear bounding function in single image dehazing," IEEE Transactions on Image Processing, vol. 29, pp. 4832-4847, 2020. DOI: 10.1109/TIP.2020.2975909.
  3. T. K. Kim, J. K. Paik, and B. S. Kang,""Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering," IEEE Transactions on Consumer Electronics, vol. 44, no. 1, pp. 82-87, 1998. DOI: 10.1109/30.663733.
  4. Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar, "Instant dehazing of images using polarization," in Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, USA, pp. 325-332, 2001. DOI: 10.1109/CVPR.2001.990493.
  5. K. He, J. Sun, and X. Tang, "Single image haze removal using dark channel prior," in 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, pp. 1956-1963, 2009. DOI:10.1109/CVPR.2009.5206515.
  6. K. He, J. Sun, and X. Tang, "Guided image filtering," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, Jun. 2013. DOI: 10.1109/TPAMI.2012.213.
  7. Z. Li, J. Zheng, Z. Zhu, W. Yao, and S. Wu, "Weighted guided image filtering," IEEE Transactions on Image Processing, vol. 24, no. 1, pp. 120-129, Jan. 2015. DOI: 10.1109/TIP.2014.2371234.
  8. J. P. Tarel, and N. Hautiere, "Fast visibility restoration from a single color or gray level image," in 2009 IEEE 12th International Conference on Computer Vision, Kyoto: Japan, pp. 2201-2208, 2009. DOI: 10.1109/ICCV.2009.5459251.
  9. Q. Zhu, J. Mai, and L. Shao, "A fast single image haze removal algorithm using color attenuation prior," IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 3522-3533, Nov. 2015. DOI:10.1109/TIP.2015.2446191.
  10. L. Liu, G. Cheng and J. Zhu, "Improved single haze removal algorithm based on color attenuation prior," in 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence, Chongqing, China, pp. 1166-1170, Dec. 2021. DOI: 10.1109/ICIBA52610.2021.9687882.
  11. D. Berman, T. Treibitz and S. Avidan, "Single image dehazing using haze-lines," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 3, pp. 720-734, Mar. 2020. DOI: 10.1109/TPAMI.2018.2882478.
  12. N. Dat, S. Lee, G. D. Lee, and B. Kang, "Single-image visibility restoration: A machine learning approach and its 4K-capable hardware accelerator," Sensors, vol. 20, no. 20, pp. 5795, Oct. 2020. DOI: 10.3390/s20205795.
  13. S. G. Narasimhan, and S. K. Nayar, "Vision and the At mosphere," International Journal of Computer Vision, vol. 48, no. 3, pp. 233-254, 2002. DOI: 10.1023/A:1016328200723.
  14. Y. S. Chung, and N. H. Kim, "Saturation-based airlight color restoration of hazy images," Applied Sciences, vol. 13, no. 22, pp. 12186. Nov. 2023. DOI: 10.3390/app132212186.
  15. T. Huang, G. Yang, and G. Tang, "A fast two-dimensional median filtering algorithm," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 27, no. 1, pp. 13-18, Feb. 1979. DOI: 10. 1109/TASSP.1979.1163188. https://doi.org/10.1109/TASSP.1979.1163188
  16. R. M. Haralick, and L. G. Shapiro, Computer and Robot Vision, 1st ed., United States, Boston: MA, 1992.
  17. B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, and Z. Wang, "Benchmarking single-image dehazing and beyond," IEEE Transactions on Image Processing, vol. 28, no. 1, pp. 492-505, Jan. 2019. DOI: 10.1109/TIP.2018.2867951.
  18. C. O. Ancuti, C. Ancuti, M. Sbert, and R. Timofte, "Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images," in 2019 IEEE International Conference on Image Processing, Taipei: Taiwan, pp. 1014-1018, 2019. DOI: 10.1109/ICIP.2019.8803046.
  19. L. K. Choi, J. You, and A. C. Bovik, LIVE Image Defogging Database, 2015. [Online], Available: http://live.ece.utexas.edu/research/fog/fade_defade.html.
  20. Y. S. Chung, and N. H. Kim, "High density salt and pepper noise removal using clustering," Journal of the Korea Institute of Information and Communication Engineering, vol. 27, no. 5, pp. 635-642, May 2023. DOI: 10.6109/jkiice.2023.27.5.635.
  21. S. Lloyd, "Least squares quantization in PCM," IEEE Transactions on Information Theory, vol. 28, no. 2, pp. 129-137, Mar. 1982. DOI:10.1109/TIT.1982.1056489.
  22. C. O. Ancuti, C. Ancuti, R. Timofte, and C. De Vleeschouwer, "OHAZE: A dehazing benchmark with real hazy and haze-free outdoor images," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, pp. 867-8678, 2018. DOI: 10.1109/CVPRW.2018.00119.
  23. C. Ancuti, C. O. Ancuti, R. Timofte, and C. D. Vleeschouwer, "IHAZE: A dehazing benchmark with real hazy and haze-free indoor images," arXiv preprint:1804.05091, Apr. 2018. DOI: 10.48550/arXiv.1804.05091.
  24. Y. S. Chung, and N. H. Kim, "Salt and pepper noise removal algorithm based on euclidean distance weight," Journal of the Korea Institute of Information and Communication Engineering, vol. 26, no. 11, pp.1637-1643, Nov. 2022. DOI: /10.6109/jkiice.2022.26.11.1637
  25. B. W. Cheon, and N. H. Kim, "Improvement of low-light image using illuminance and fuzzy function," Journal of the Korea Institute of Information and Communication Engineering, vol. 27, no. 12, pp.1508-1515. Dec. 2023. DOI: 10.6109/jkiice.2023.27.12.1508.