基于解系数矩阵的背景颜色校正

Background Color Correction Based on Coefficient Matrix

数码相机等图像采集设备受系统参数、拍摄条件等的影响,与真实背景间出现偏色、失真现象,给迷彩伪装自动配色带来较大误差。为解决这一误差,基于自制98块绿色色板,通过将数码相机成像设备采集的色板色度值作为自变量,将测试光谱获取的真实颜色色度值作为因变量,构建系数矩阵方程,求解矩阵系数,应用该系数矩阵对背景进行颜色校正。结果表明,数码设备采集的图像颜色信息经过系数矩阵校正后,与真实背景颜色的平均色差ΔE;小于3,满足伪装性能要求,这为高融合迷彩伪装背景颜色复制技术提供了坚实的基础。

System parameters and shooting conditions influence digital cameras and other image acquisition equipments.With a real background,a partial color and distortion phenomenon results in a large error in automatic color matching.In this study,we made 98 green swatches.The chromaticity value of swatch acquired using digital camera imaging equipment was considered an independent variable,whereas the true color chromaticity value obtained from the test spectrum was considered a dependent variable.Then,a coefficient matrix equation was constructed and solved.The resulting coefficient matrix was used for background color correction.The results show the image color information obtained by digital equipment after the application of the correction coefficient matrix.In addition,the average color difference with real background color is less than 3,which meets the requirements of camouflage performance and lay the foundation for the high fusion camouflage background color reproduction technology.