摘要
雾霾天气下拍摄的图像往往会因空气中的气溶胶粒子散射而降质,并因此影响后续的室外计算机视觉系统的应用。为此,研究者提出了大量方法来复原雾霾图像的质量。文中归纳总结了图像去雾霾方法的研究现状,重点研究和分析了基于图像增强和基于物理模型这两大类方法,深入探讨了其中一些已被广泛认可的经典算法的优劣,并分析了几种雾霾天气复原图像客观评价的方法。最后,提出了图像去雾霾算法未来的几种研究思路,并展望了未来的发展趋势。
Images captured under haze are always degraded due to the suspending aerosols in air,which can also affect their applications in the outdoor computer vision system.Then researchers proposed a lot of algorithms for image restoration.Current image dehazing algorithms were analyzed,including two categories of image enhancement based and physical model based.Then the advantages and disadvantages of several highly applied algorithms were discussed,and some quantity evaluation methods were introduced.Finally,some possible study ways and the trend of development were given.
出处
《计算机科学》
CSCD
北大核心
2017年第11期1-8,共8页
Computer Science
基金
国家自然科学基金(61472302
U1404620
61672409)
模式识别国家重点实验室开放课题基金(201600031)
中央高校基本科研业务费专项资金(JB150317)
陕西省自然科学基金(2010JM8027)
航空科学基金(2015ZC31005)资助
关键词
图像去雾霾
图像增强
大气散射模型
暗通道
机器学习
hnage dehazing , Image enhancement , Atmospheric scattering model , Dark channel prior , Machine learning