Acta Photonica Sinica, Volume. 48, Issue 3, 310001(2019)

An Adaptive Multiscale Transmission Estimation Dehazing Algorithm

YANG Yan*, LI Yi-fei, and YUE Hui
Author Affiliations
  • [in Chinese]
  • show less

    Aiming at the inaccurate transmission estimation in the sky region of the dark channel prior, three Gaussian functions of different scales are used to act on the RGB channels of the hazy image to obtain a "pseudo" dehazing image respectively; Secondly, the adaptive parameter is obtained by using a mixed channel of the hazy image, the parameter together with the minimum filter act on the "pseudo" dehazing image, and then the joint bilateral filter is used to eliminate the texture effect to get the accurate transmission; Finally, using the local atmospheric light estimation method, combined with the atmospheric scattering model to restore the haze-free image. The experimental results show that the method not only reduces the time complexity, but also has obvious image details and good brightness. It also has a good dehazing effect for large-area sky areas and improves the color distortion of the sky area.

    Tools

    Get Citation

    Copy Citation Text

    YANG Yan, LI Yi-fei, YUE Hui. An Adaptive Multiscale Transmission Estimation Dehazing Algorithm[J]. Acta Photonica Sinica, 2019, 48(3): 310001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Aug. 31, 2018

    Accepted: --

    Published Online: Apr. 2, 2019

    The Author Email: Yan YANG (1275022532@qq.com)

    DOI:10.3788/gzxb20194803.0310001

    Topics