Remote Sensing Image Color Correction Method Based on Automatic Piecewise Polynomial Method

摘要

In the process of remote sensing image restoration, color correction is very important. The polynomial algorithmcolor correction method based on standard color card is the most commonly used method. However, the traditional polynomial fitting method needs to determine the most appropriate combination of polynomials, and only one polynomial function fitting method is used. So it is difficult to guarantee high accuracy and good generalization performance at the same time. In order to solve the above problems effectively, this paper proposes an automatic piecewise polynomial fitting method. This study established the mapping between collected RGB value and standard RGB value through the calibration of the X-rite Color Checker, and represented the color difference by computing $Delta E$ in CIELab color space. This improved algorithm adopts the idea of segmentation to select the most suitable function in different intervals, and the interval of segmentation is automatically determined by the chromatic aberration standard. The experimental results show that this algorithm has high correction accuracy and this algorithm is more adaptable to photos under different lighting conditions.