Systems Engineering and Electronics ›› 2021, Vol. 43 ›› Issue (5): 1169-1175.doi: 10.12305/j.issn.1001-506X.2021.05.02

• Electronic Technology • Previous Articles     Next Articles

Dehazing algorithm based on reconstructed dark channel with quadratic sinusoidal attenuation

Wei MEI*(), Xin LI()   

  1. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, China
  • Received:2020-05-22 Online:2021-05-01 Published:2021-04-27
  • Contact: Wei MEI E-mail:meiweihello@163.com;su_xinli@aliyun.com

Abstract:

Aiming at the defects such as the failure of the dark channel algorithm in the sky area and the halo phenomenon caused by the minimum filter, a dehazing algorithm based on the quadratic sinusoidal attenuation of the reconstructed dark channel is proposed. Firstly, the reconstruction dark channel is obtained by using image segmentation to reconstruct the original image. Then the hazy density weight function is designed to approximate the hazy density in the scene to obtain the weight coefficient, and then combining weighting coefficient to perform quadratic sinusoidal attenuation on the reconstructed dark channel to obtain the initial transmission. In order to obtain more precise transmission, the transmission is optimized by combining histogram equalization and fast-guided filtering. Finally, the haze-free image is restored by the atmospheric scattering model. Experimental results show that the proposed algorithm can effectively deal with the sky area, suppress the halo, restore the details of the image, and has appropriate the brightness and saturation.

Key words: image dehazing, sinusoidal attenuation, transmission

CLC Number: 

[an error occurred while processing this directive]