摘要
针对现有偏振去雾算法鲁棒性不强和图像增强效果有限的问题,提出一种基于多尺度奇异值分解的图像融合去雾算法。首先,利用偏振测量信息的冗余特性,采用最小二乘法,提高了传统偏振图像去雾算法中偏振信息的准确度;然后,从传统偏振图像去雾算法的局限性出发,定性分析了偏振图像融合去雾的可行性,并提出了一种基于多尺度奇异值分解的偏振图像融合去雾算法;最后,设计了不同能见度条件下的验证实验并进行了量化评价。结果表明,与经典偏振图像去雾算法相比,该算法不需要进行人工参数调节,具有较强的自适应性和鲁棒性,能够有效改善传统算法中出现的光晕以及天空区域过曝的问题,图像信息熵与平均梯度最大可分别提高18.9%和38.4%,有效地增强了复杂光照条件下的视觉成像质量,具有较广泛的应用前景。
Aiming at the problems that the robust of existing polarization defogging algorithms is poor and image enhancement abilities are limited,an image fusion defogging algorithm based on Multi-scale Singular Value Decomposition(MSVD)is proposed.Firstly,considering the redundancy in polarization measurement information,the least square method is used to improve the accuracy of the polarization information in the traditional defogging algorithm for polarized images;then,with respect to the limitations of that algorithm,a qualitative analysis of the feasibility of image fusion defogging is implemented,and a polarized image fusion defogging algorithm based on multi-scale singular value decomposition is proposed.Finally,a verification experiment under different visibility conditions is designed and quantified.The results show that compared with the classic polarized image defogging algorithm,this algorithm does not require manual parameter adjustment,it has strong adaptability and robustness,and can effectively improve the halos and overexposure of sky areas that occur in the traditional algorithm.The image information entropy and the average gradient can be increased by 18.9%and 38.4%respectively,which effectively improves the quality of visual imaging under complex lighting conditions.The proposed algorithm has great application prospects.
作者
周文舟
范晨
胡小平
何晓峰
张礼廉
ZHOU Wen-zhou;FAN Chen;HU Xiao-ping;HE Xiao-feng;ZHANG Li-lian(College of Intelligence Science and Technology,National University of Defense Technology,Changsha 410072,China)
出处
《中国光学》
EI
CAS
CSCD
北大核心
2021年第2期298-306,共9页
Chinese Optics
基金
国家自然科学基金面上项目(No.61773394)
国防科技大学科研计划项目(No.ZK18-03-24)。
