Frontiers in Neurorobotics (Jan 2023)

Study on the enhancement method of online monitoring image of dense fog environment with power lines in smart city

  • Meng Zhang,
  • Zhitao Song,
  • Jianfei Yang,
  • Mingliang Gao,
  • Yuanchao Hu,
  • Chi Yuan,
  • Zhipeng Jiang,
  • Wei Cheng

DOI
https://doi.org/10.3389/fnbot.2022.1104559
Journal volume & issue
Vol. 16

Abstract

Read online

In this research, an image defogging algorithm is proposed for the electricity transmission line monitoring system in the smart city. The electricity transmission line image is typically situated in the top part of the image which is rather thin in size. Because the electricity transmission line is situated outside, there is frequently a sizable amount of sky in the backdrop. Firstly, an optimized quadtree segmentation method for calculating global atmospheric light is proposed, which gives higher weight to the upper part of the image with the sky region. This prevents interference from bright objects on the ground and guarantees that the global atmospheric light is computed in the top section of the image with the sky region. Secondly, a method of transmission calculation based on dark pixels is introduced. Finally, a detail sharpening post-processing based on visibility level and air light level is introduced to enhance the detail level of electricity transmission lines in the defogging image. Experimental results indicate that the algorithm performs well in enhancing the image details, preventing image distortion and avoiding image oversaturation.

Keywords