An improved dark channel defogging algorithm based on the HSI colour space. Issue 3 (15th December 2021)

• Record Type: Journal Article
• Authors: Cui, Yani; Zhi, Shuaiqing; Liu, Wenjin; Deng, Jiaxian; Ren, Jia
• Is Part Of: IET image processing. Volume 16:Issue 3(2022)
• Page Start: 823
• Page End: 838
• Publication Date: 2021-12-15
• Subjects: Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12389
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: When the traditional dark channel prior (DCP) algorithm is used for image defogging, it faces some problems such as unsatisfactory restoration of the target edge details, distortion in large‐scale and high‐brightness sky regions. To solve these problems, this paper proposes an improved dark channel defogging algorithm based on the HSI colour space, named the IDCP algorithm. First, an asymmetric mean filter window is used to obtain the modified dark channel image to improve the grey value mutation in the traditional dark channel image. Based on this work, an improved global atmospheric transmittance calculation method is proposed, which effectively improves the inapplicability of the dark channel prior in large‐scale and high‐brightness sky regions. Finally, the Laplacian operator is used to sharpen the image to enhance the target edge information. Simulation results show that the proposed algorithm can effectively solve the distortion phenomenon caused by the traditional DCP algorithm when handling large‐scale and high‐brightness sky regions, improve the target edge details, and restore the true colour of the image scene.