基于质量评价最优的无人机航拍图像去雾方法

doi:10.3969/j.issn.1000-1093.2022.01.016

摘要/Abstract

摘要： 无人机是现代化战争的重要信息侦察手段，雾气严重影响到无人机拍摄图像的质量，对侦察识别的执行能力起到妨碍作用。为提高雾气环境下无人机航拍图像有效利用性，针对无人机航拍图像的特点及特殊应用背景，提出一种质量评价最优的无人机航拍图像去雾方法。通过将信息熵、标准差和图像傅里叶振幅3种图像质量评价参数相结合，建立图像质量综合评价函数；给定不同的大气透射率值，求解相应的去雾图像，以去雾图像的质量评价函数值作为择优标准。研究结果表明：该方法计算复杂度低、操作简单、简便易行，易于操作与实现；所获得的去雾图像视觉效果清晰、结果误差小。

关键词: 无人机航拍图像, 图像处理, 图像去雾, 质量评价, 图像傅里叶振幅

Abstract: UAV is an important means of information reconnaissance in modern warfare. The fog seriously affects the quality of UAV aerial images and hinders the ability to perform reconnaissance and recognition. In order to improve the effective utilization of UAV aerial images in the foggy environment，an image dehazing method based on the optimum of UAV aerial image quality evaluation is proposed according to the characteristics and special application background of UAV aerial images.A comprehensive image quality evaluation function is established by combining three image quality evaluation parameters，such as information entropy，standard deviation and image Fourier amplitude. Different atmospheric transmittance values are given，the corresponding dehazing image is solved，and the quality evaluation function value of dehazing image is used as the screening standard. The experimental verification shows that the image dehazing method based on the optimum of UAV aerial image quality evaluation has low computational complexity and simple operation. And the obtained dehazing image has clear visual effects and small result errors.

Key words: UAVaerialimage, imageprocessing, imagedehazing, qualityevaluation, imageFourieramplitude

中图分类号:

V279⁺.2

姜雨彤，宋海平，王光辉. 基于质量评价最优的无人机航拍图像去雾方法[J]. 兵工学报, 2022, 43(1): 148-158.

JIANG Yutong， SONG Haiping， WANG Guanghui. Image Dehazing Based on the Optimum of UAV Aerial Image Quality Evaluation[J]. Acta Armamentarii, 2022, 43(1): 148-158.

参考文献

［1］杨棕源，唐友喜.无人机监测图像独立分量分析增强关键技术[D].成都：电子科技大学，2012.
YANG Z Y，TANG Y X.Key technologies for independent component analysis and enhancement of UAV monitoring images[D].Chengdu:University of Electronic Science and Technology of China，2012.(in Chinese)
[2] 孔庆红.基于暗原色先验的无人机航拍图像去雾算法研究与实现[D].青岛：中国海洋大学，2014.
KONG Q H.The defog algorithm on research and implementation of UAV aerial images based on dark channel prior[D].Qingdao:Ocean University of China，2014.(in Chinese)
[3] 黄宇晴，丁文锐，李红光.基于图像增强的无人机侦察图像去雾方法[J].北京航空航天大学学报，2017，43(3): 592-601.
HUANG Y Q，DING W R，LI H G. Haze removal method for UAV reconnaissance images based on image enhancement[J].Journal of Beijing University of Aeronautics and Astronautics，2017，43(3):592-601.(in Chinese)
[4] 刘春辉，齐越，丁文锐.基于大气光鲁棒估计的无人机图像去雾方法[J].北京航空航天大学学报，2017，43(6): 1105-1111.
LIU C H，QI Y，DING W R.A haze remove method for unmanned aerial vehicle images defogging method based on robust estimation of atmospheric light[J].Journal of Beijing University of Aeronautics and Astronautics，2017，43(6): 1105-1111.(in Chinese)
[5] 李春明，姜雨彤，宋海平，等.基于光学厚度代理模型的雾浓度估计及图像去雾[J].兵工学报，2019，40(7):1425-1433.
LI C M，JIANG Y T，SONG H P，et al.Research on optical depth surrogate model-based method for estimating fog density and removing fog effect from images[J].Acta Armamentarii，2019，40(7): 1425-1433.(in Chinese)
[6] 李力，金伟其，黄有为，等.一种低对比度可见光超视距成像的实时图像增强方法[J].兵工学报，2010，31(2): 242-247.
LI L，JIN W Q，HUANG Y W，et al. Real-time image enhancement processing methods of low contrast visible light over-the-horizon imaging[J].Acta Armamentarii，2010，31(2): 242-247. (in Chinese)
[7] ANCUTI， CODRUTA O，COSMIN A.Single image dehazing by multi-scale fusion[J].IEEE Transactions on Image Processing，2013，22(8): 3271-3282.
[8] 李从利，张思雨，韦哲，等.基于深度卷积生成对抗网络的航拍图像去厚云方法[J].兵工学报，2019，40(7):1434-1442.
LI C L，ZHANG S Y，WEI Z，et al. Thick cloud removal for aerial images based on deep convolutional generative adversarial networks[J].Acta Armamentarii，2019，40(7):1434-1442.(in Chinese)
[9] ENGIN D, GENA, EKENEL H K.Cycle-Dehaze:enhanced CycleGAN for single image dehazing[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City,UT,US:IEEE,2018.
[10] 李成超，于占江，李一全，等.微小零件显微检测图像的清晰度评价[J].半导体光电，2020，41(1):103-107，113.
LI C C，YU Z J，LI Y Q，et al.Sharpness evaluation of microsco- pic detection image for micro parts[J].Semiconductor Optoelectronics，2020，41(1):103-107，113.(in Chinese)
[11] HAJGHASSEM H，ZARIE M，POURMOHAMMAD A.Image contrast enhancement using triple clipped dynamic histogram equalization based on standard deviation[J].IET Image Processing，2019，13(7):1081-1089.
[12] KIM J H，JANG W D，SIM J Y，et al.Optimized contrast enhancement for real-time image and video dehazing[J].Journal of Visual Communication and Image Representation，2013，24(3): 410- 425.
[13] HE K M，SUN J，TANG X O.Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2011，33(12):2341-2353.
[14] ZHU Q S，MAI J M，SHAO L.A fast single image haze removal algorithm using color attenuation prior[J].IEEE Transactions on Image Processing，2015，24(11):3522-3533.
[15] WANG Z，BOVIK A C，SHEIKH H R，et al. Image quality assessment: from error visibility to structural similarity[J].IEEE Transactions on Image Processing，2004，13(4): 600-612.
[16] MATKOVIAC＇U2 K，NEUMANN L，NEUMANN A，et al.Global contrast factor - a new approach to image contrast[C]∥Proceedings of the 1st Eurographics Conference on Computational Aesthetics in Graphics，Visualization and Imaging.Girona，Spain:Institució Catalana de Recercai Estudis Avanats，2005:159-167.

[1]	宋雨, 王亚林, 杜博军, 王军, 董兴法. 基于改进最大类间方差法的靶板重孔检测[J]. 兵工学报, 2022, 43(4): 924-930.
[2]	李春明，姜雨彤，宋海平，纪超，郭猛，朱琳. 基于光学厚度代理模型的雾浓度估计及图像去雾[J]. 兵工学报, 2019, 40(7): 1425-1433.
[3]	覃若琳，蒋晓刚，金良安，高可心. 基于Hough变换的水中气泡群特征参数提取方法研究[J]. 兵工学报, 2019, 40(12): 2504-2512.
[4]	李从利, 薛松, 陆文骏, 袁广林, 秦晓燕. 弹载侦察图像质量评价方法研究[J]. 兵工学报, 2017, 38(1): 64-72.
[5]	王延海，王晓曼，李玉山，景文博，王子赫. 基于图像透视畸变校正的调炮速度测量方法[J]. 兵工学报, 2016, 37(8): 1517-1523.
[6]	谭克，邹丽娜. 正态分布转换算法在声纳图像处理中的应用[J]. 兵工学报, 2016, 37(6): 1052-1057.
[7]	吴坚业，张拴勤，殷德飞. 数码假彩色成像技术研究[J]. 兵工学报, 2015, 36(9): 1722-1726.
[8]	潘越，徐煕平，张帆，姜肇国，乔杨，李艳荻. 图像处理前照灯检测仪校准器自动检定系统[J]. 兵工学报, 2015, 36(5): 861-868.
[9]	孙晶, 郑庆余, 徐文骥, 黄帅, 刘新. 非对称等离子体弧温度场三维重建[J]. 兵工学报, 2014, 35(7): 1097-1102.
[10]	张玉珍，孙佳嵩，陈钱，顾国华，冯世杰，. 基于相位一致性的结构相似度图像融合质量评价方法[J]. 兵工学报, 2013, 34(12): 1514-1520.
[11]	宋义刚，肖亮，韦志辉，黄丽丽. 光学遥感图像变量分裂迭代快速复原算法[J]. 兵工学报, 2012, 33(3): 283-289.
[12]	辛德胜，张剑家，王少君，王兆欣, 王洪喆. 半导体激光夜视图像处理技术研究[J]. 兵工学报, 2011, 32(12): 1439-1442.
[13]	安宝林，杨耿，薛晋生. 基于CCD成像技术的枪械射击准确度验收系统[J]. 兵工学报, 2010, 31(2): 239-241.
[14]	李力₁, 金伟其₁, 黄有为₁, 王霞₁, 孙悦₂, 吴允刚₂. 一种低对比度可见光超视距成像的实时图像增强方法[J]. 兵工学报, 2010, 31(2): 242-247.
[15]	焦继超₁，赵保军₁，周刚₂. 一种傅里叶—梅林变换空间图像快速配准算法[J]. 兵工学报, 2010, 31(12): 1551-1556.