基于图像增强的无人机侦察图像去雾方法

黄宇晴; 丁文锐; 李红光

doi:10.13700/j.bh.1001-5965.2016.0169

基于图像增强的无人机侦察图像去雾方法

doi: 10.13700/j.bh.1001-5965.2016.0169

1.
北京航空航天大学电子信息工程学院, 北京 100083
2.
北京航空航天大学无人驾驶飞行器设计研究所, 北京 100083

基金项目:

国家自然科学基金 61601014

详细信息

作者简介:
黄宇晴, 女, 硕士研究生。主要研究方向:图像处理

李红光, 男, 博士, 工程师。主要研究方向:图像处理

通讯作者:
李红光, E-mail:lihongguang@buaa.edu.cn

中图分类号: TP391
计量
- 文章访问数: 1294
- HTML全文浏览量: 59
- PDF下载量: 906
- 被引次数: 0
出版历程
- 收稿日期: 2016-03-07
- 录用日期: 2016-04-29
- 网络出版日期: 2017-03-20

Haze removal method for UAV reconnaissance images based on image enhancement

1.
School of Electronic and Information Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
2.
Research Institute of Unmanned Aerial Vehicle, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

Funds:

National Natural Science Foundation of China 61601014

More Information

Corresponding author: LI Hongguang, E-mail:lihongguang@buaa.edu.cn

摘要

摘要:
针对无人机（UAV）雾霾天气下的侦察图像，并考虑无人机自身特性，提出了一种新的基于图像增强的无人机侦察图像去雾方法。该方法从图像处理的角度，通过对图像分别进行白平衡处理和对比度增强处理，基于图像融合和自动色阶处理，最终得到复原图像。选取无人机侦察图像进行去雾，并从主观和客观对实验结果进行评价，本方法得到的去雾图像的图像评价指标均有明显提高；同时与其他典型的去雾方法相比，综合评价指标提升，证明本方法可以得到良好的去雾效果。
- 白平衡 /
- 对比度增强 /
- K-means算法 /
- HSV颜色空间 /
- 自动色阶
Abstract:
On account of the unmanned aerial vehicle (UAV) reconnaissance images under the hazy weather conditions, considering the characteristics of UAV itself, this paper proposes a novel method for dehazing UAV reconnaissance images based on image enhancement. Through automatic white balance and contrast enhancement for images respectively, the final restored image can be obtained based on image fusion and auto levels. Then we choose UAV reconnaissance images for haze removal and evaluate the result of the experiment from the perspective of subjective and objective. The experimental results show that the image evaluation indexes of dehazing images are improved obviously. Compared with other typical haze removal methods, the comprehensive index of the image restored by the proposed method increases, which proves that the proposed method can obtain excellent dehazing effect.
- white balance /
- contrast enhancement /
- K-means algorithm /
- HSV color space /
- auto levels

HTML全文

图 1 本文去雾方法流程图

Figure 1. Proposed dehazing method flowchart

下载: 全尺寸图片幻灯片

图 2 大气散射模型示意图

Figure 2. Schematic diagram of atmospheric scattering model

下载: 全尺寸图片幻灯片

图 3 自动色阶算法流程图

Figure 3. Auto levels algorithm flowchart

下载: 全尺寸图片幻灯片

图 4 不同方法的去雾效果

Figure 4. Dehazing results of different methods

下载: 全尺寸图片幻灯片

图 5 综合评价指标比较

Figure 5. Comparison of comprehensive evaluation index

下载: 全尺寸图片幻灯片

表 1 图像融合权重对应雾浓度级别

Table 1. Image fusion weights and their corresponding grades of haze concentration

雾气浓度级别	对比度权重	白平衡权重
0	0	1
1	0.2	0.8
2	0.4	0.6
3	0.6	0.4
4	0.8	0.2

下载: 导出CSV

表 2 去雾前后的标准差和信息熵

Table 2. Standard deviation and information entropy before and after dehazing

序号	标准差		信息熵
序号	原图	去雾后	原图	去雾后
1	21.817 700	55.956 15	4.114 371	5.231 381
2	23.575 430	53.351 33	3.709 058	4.910 504
3	9.018 065	43.797 79	3.350 642	5.034 718
4	6.289 762	30.208 87	3.024 568	4.867 457
5	16.996 810	36.074 45	4.505 224	5.264 960
6	10.341 110	23.898 56	3.451 581	4.779 376
7	18.149 810	41.873 90	4.587 965	5.440 413

下载: 导出CSV

表 3 去雾前后的CNI和CCI

Table 3. CNI and CCI before and after dehazing

序号	CNI		CCI
序号	原图	去雾后	原图	去雾后
1	0.458 457	0.564 170	65.952 55	167.536 70
2	0.545 394	0.624 008	100.782 20	157.108 10
3	0.463 714	0.597 543	45.798 24	162.026 30
4	0.450 407	0.522 387	38.751 14	136.424 70
5	0.435 621	0.520 872	23.266 67	48.885 40
6	0.422 680	0.417 078	12.794 68	27.341 50
7	0.468 173	0.492 878	26.322 86	40.960 57

下载: 导出CSV

表 4 不同方法的综合评价指标比较

Table 4. Comparison of comprehensive evaluation index among different methods

序号	原图 (a)	自适应直方图均衡 (b)	自适应色阶对比度 (c)	多尺度Retinex (d)	均值滤波 (e)	高斯滤波 (f)	暗通道先验 (g)	本文方法 (h)
1	1.001 3	1.935 004	2.522 596	2.076 970	2.174 849	2.384 549	2.831 008	2.542 759
2	1.096 2	2.180 398	3.255 074	2.170 184	1.738 967	2.488 135	2.566 417	2.636 486
3	0.398 5	1.167 745	1.740 431	2.200 087	0.486 920	1.058 386	2.026 381	2.268 815
4	0.171 5	0.618 922	1.463 787	2.015 525	0.242 398	0.994 793	2.240 572	1.948 523
5	0.931 4	1.983 790	2.130 797	2.185 008	1.619 569	1.962 495	2.030 415	2.020 827
6	0.319 6	1.073 086	1.533 132	2.008 388	0.676 075	0.858 428	0.910 497	1.157 127
7	1.050 4	2.015 479	2.038 903	2.097 325	2.669 215	2.004 094	2.214 031	2.440 271

下载: 导出CSV

参考文献(36)

[1]	FITZGERALD J A S J.An alternative algorithm for adaptive histogram equalization[J].Graphical Models & Image Processing, 1996, 58(2):180-185.
[2]	REZA A M.Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement[J].Journal of VLSI Signal Processing Systems, 2004, 38(1):35-44. doi: 10.1023/B:VLSI.0000028532.53893.82
[3]	翟艺书, 刘晓鸣, 涂雅瑗, 等.一种改进雾天降质图像的清晰化算法[J].大连海事大学学报, 2007, 33(3):55-58. http://www.cnki.com.cn/Article/CJFDTOTAL-DLHS200703011.htm ZHAI Y S, LIU X M, TU Y Y, et al.An improved fog-degraded image clearness algorithm[J].Journal of Dalian Maritime University, 2007, 33(3):55-58(in Chinese). http://www.cnki.com.cn/Article/CJFDTOTAL-DLHS200703011.htm
[4]	SEOW M J, ASARI V K.Ratio rule and homomorphic filter for enhancement of digital colour image[J].Neurocomputing, 2006, 69(7-9):954-958. doi: 10.1016/j.neucom.2005.07.003
[5]	RUSSO R.An image enhancement technique combining sharpening and noise reduction[J].IEEE Transactions on Instrumentation & Measurement, 2002, 51(4):824-828. https://www.researchgate.net/publication/220409046_An_image_enhancement_technique_combining_sharpening_and_noise_reduction
[6]	ZHOU J, ZHOU F.Single image dehazing motivated by Retinex theory[C]//2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA).Piscataway, NJ:IEEE Press, 2013:243-247.
[7]	ANSIA S, ASWATHY A L.Single image haze removal using white balancing and saliency map[J].Procedia Computer Science, 2015, 46:12-19. doi: 10.1016/j.procs.2015.01.042
[8]	SUN Y B, XIAO L, WEI Z H, et al.Method of defogging image of outdoor scenes based on PDE[J].Journal of System Simulation, 2007, 19(16):3739-3744.
[9]	ZHAI Y S, LIU X M, TU Y Y.Contrast enhancement algorithm for fog-degraded image based on fuzzy logic[J].Computer Applications, 2008, 28(3):662-664. doi: 10.3724/SP.J.1087.2008.00662
[10]	OAKLEY J P.Improving image quality in poor visibility conditions using a physical model for contrast degradation[J].IEEE Transactions on Image Processing, 1998, 7(2):167-179. doi: 10.1109/83.660994
[11]	NARASIMHAN S G, NAYAR S K.Chromatic framework for vision in bad weather[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway, NJ:IEEE Press, 2002:598-605.
[12]	NARASIMHAN S G, NAYAR S K.Vision and the atmosphere[J].International Journal of Computer Vision, 2002, 48(3):233-254. doi: 10.1023/A:1016328200723
[13]	KOPF J, NEUBERT B, CHEN B, et al.Deep photo:Model-based photograph enhancement and viewing[J].ACM Transactions on Graphics (TOG), 2008, 27(5):32-39.
[14]	TAN R T.Visibility in bad weather from a single image[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2008, CVPR 2008.Piscataway, NJ:IEEE Press, 2008:1-8.
[15]	FATTAL R.Single image dehazing[J].ACM Transactions on Graphics (TOG).New York:ACM, 2008, 27(3):1-9.
[16]	HE K, SUN J, TANG X.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353. doi: 10.1109/TPAMI.2010.168
[17]	LIU Q, CHEN M Y, ZHOU D H.Single image haze removal via depth-based contrast stretching transform[J].Science China Information Sciences, 2014, 58(1):1-17. https://www.researchgate.net/publication/271917786_Single_image_haze_removal_via_depth-based_contrast_stretching_transform
[18]	WENG C C, CHEN H, FUH C S.A novel automatic white balance method for digital still cameras[J].Images & Recognition, 2006, 4(12):3801-3804.
[19]	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 & Image Representation, 2013, 24(3):410-425.
[20]	MCCARTNEY E J.Optics of the atmosphere:Scattering by molecules and particles[J].Wiley, 1976, 14(7):698-699. https://www.researchgate.net/publication/259942105_Optics_of_the_Atmosphere_-_Scattering_by_Molecules_and_Particles
[21]	PELI E.Contrast in complex images[J].Journal of the Optical Society of America A Optics & Image Science, 1990, 7(10):2032-2040. https://www.researchgate.net/publication/20925175_Contrast_in_complex_images
[22]	ANCUTI C, ANCUTI C O, HABER T, et al.Enhancing underwater images and videos by fusion[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway, NJ:IEEE Press, 2012:81-88.
[23]	GUO F, TANG J, CAI Z X.Single image defogging based on fusion strategy[J].Journal on Communications, 2014, 35(7):199-207. http://en.cnki.com.cn/Article_en/CJFDTOTAL-TXXB201407024.htm
[24]	FANG S, DENG R, CAO Y, et al.Effective single underwater image enhancement by fusion[J].Journal of Computers, 2013, 8(4):904-911. https://www.researchgate.net/publication/276240250_Effective_Single_Underwater_Image_Enhancement_by_Fusion
[25]	ALSABTI K, RANKA S, SINGH V.An efficient k-means clustering algorithm[J/OL]//Electrical Engineering and Computer Science, 1997:43.http://surface.syr.edu/eecs/43.
[26]	CHOI D H, JANG I H, MI H K, et al.Color image enhancement using single-scale retinex based on an improved image formation model[C]//6th European Signal Processing Conference, EUSIPCO 2008, 2008:1-5.
[27]	QIN X J, WANG H L, DU Y C, et al.Structured light image enhancement algorithm based on retinex in HSV color space[J].Journal of Computer-Aided Design & Computer Graphics, 2013, 25(4):488-493. https://www.researchgate.net/publication/286978621_Structured_light_image_enhancement_algorithm_based_on_retinex_in_HSV_color_space
[28]	DING J B.Proficient in photoshop CS Chinese version[M].Beijing:Tsinghua University Press, 2004:55-60.
[29]	刘信. 基于FPGA水下图像像质增强实时化研究[D]. 大连: 大连海事大学, 2013: 10-12. LIU X.The research of underwater image quality real-time enhancenment based on FPGA[D].Dalian:Dalian Maritime University, 2013:10-12(in Chinese).
[30]	GUO F, CAI Z X.Objective assessment method for the clearness effect of image defogging algorithm[J].Acta Automatica Sinica, 2012, 38(9):1410-1419.. doi: 10.3724/SP.J.1004.2012.01410
[31]	Image Shop.Image enhancement of local adaptive auto tone/contrast[EB/OL].(2013-10-30)[2015-07-14].http://www.cnblogs.com/Imageshop/p/3395968.html.
[32]	LIU Q, CHEN M, ZHOU D.Fast haze removal from a single image[C]//Control and Decision Conference (CCDC).Piscataway, NJ:IEEE Press, 2013:3780-3785.
[33]	HANUMANTHARAJU M C, RAVISHANKAR M, RAMESHBABU D R.Natural color image enhancement based on modified multiscale retinex algorithm and performance evaluation using wavelet energy[M]//THAMPI S M, ABRAHAM A, PAL S K.Recent Advances in Intelligent Informatics.Berlin:Springer, 2014:83-92.
[34]	YENDRIKHOVSKI S N, BLOMMAERT F J J, DE RIDDER H. Perceptually optimal color reproduction[C]//Proceedings of Human Vision and Electronic Imaging Ⅲ. Bellingham, WA:SPIE, 1998:274-281.
[35]	李青, 郑南宁, 张雪涛, 等.车载摄像机的一种简易标定方法[J].机器人, 2003, 25(s1):626-630. http://www.cqvip.com/QK/90986X/2003z1/1000351647.html LI Q, ZHENG N N, ZHANG X T, et al.A simple calibration approach for camera on-based vehicle[J].Robot, 2003, 25(s1):626-630. http://www.cqvip.com/QK/90986X/2003z1/1000351647.html
[36]	JOURLIN M, PINOLI J C.Logarithmic image processing:The mathematical and physical framework for the representation and processing of transmitted images[J].Advances in Imaging and Electron Physics, 2001, 115(1):129-196.