基于小波融合的SOFC燃烧室火焰图像增强方法

SOFC Combustor Flame Image Enhancement Method Based on Wavelet Fusion

当固体氧化物燃料电池系统因某些原因未全额功率运行时,燃烧室会进行不充分燃烧。火焰图像会具有亮度高、对比度低等特点,不利于图像特征的提取与系统分析。针对此问题,提出了一种基于小波融合的固体氧化物燃料电池燃烧室火焰图像增强方法。首先,利用感知启发的变分框架,提升颜色混合区域的对比度,实现图像预增强;然后,利用提出的细节保持模块进行二次图像增强;最后,利用小波融合方法将已有的增强图像进行融合,获得最终图像。实验结果表明,相比于传统方法,提出的方法不仅可有效保持图像的细节信息,而且可显著增强图像的对比度,提高图像质量。

When the solid oxide fuel cell system is under full power operation for some reason,the combustion chamber will conduct insufficient combustion.The flame image will have high brightness and low contrast,which is adverse to image feature ex⁃traction and system analysis.To solve this problem,a flame image enhancement method of solid oxide fuel cell combustion chamber based on wavelet fusion is proposed.Firstly,the perceptually inspired variational framework is applied to enhance the contrast of the color mixing region and realize the image pre-enhancement.Then,the proposed detail preserving module is utilized for secondary image enhancement.Finally,the wavelet fusion method is applied to fuse the enhanced images to obtain the final image.The experi⁃mental results show that compared with the traditional methods,the proposed method can effectively preserve the details of the im⁃age and significantly enhance the image contrast to improve the image quality.