An improved color consistency optimization method based on the reference image contaminated by clouds

ABSTRACT

Optimizing color consistency across multiple images is a crucial step in creating accurate digital orthophoto maps (DOMs). However, current color balance methods that rely on a reference image are susceptible to cloud and cloud shadow interference, making it challenging to ensure color fidelity and a uniform color transition between images. To address these issues, an improved method for color consistency optimization has been proposed to enhance image quality using optimized low-resolution reference images. Initially, the original image is utilized to reconstruct areas affected by clouds or cloud shadows on the reference image. For seamless cloning, a Poisson blending algorithm is employed to minimize color differences between reconstructed and other regions. Subsequently, based on a weighting approach, the high-frequency information obtained through Gaussian and bilateral filtering is superimposed to smooth the image boundary and ensure color continuity between images. Finally, local linear models are constructed to correct image color based on the optimized reference and down-sampled images. To validate the robustness of this approach, we tested it on two challenging datasets covering a wide area. Compared to state-of-the-art methods, our approach offers significant advantages in both quantitative indicators and visual quality.

KEYWORDS:

• Color consistency optimization
• remote sensing
• Poisson blending
• boundary smoothing

Acknowledgments

The authors would like to express gratitude to the anonymous reviewers for their valuable comments and suggestions, which helped improve the quality of this paper. The authors would like to thank the Land Satellite Remote Sensing Application Center, Ministry of Natural Resources of P.R. China, for providing ZY3-01/02 satellite imagery.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Additional information

Funding

This study was supported in part by the National Natural Science Foundation of China under Grants 42241164, 41871325, and the National Key R&D Program of China under Grant 2018YFB0505400.