智能视频监控中海面舰船目标检测算法研究
|
摘要
我国具有辽阔的海岸线，海域十分广阔，因此，海事视频自动监测具有重要的现实意义和应用价值。在军用方面，可以维护海洋权益、加强海域监管、减少海事纠纷等；在民用方面，海面目标的自动检测技术可以高效实现港口、海湾等的海上交通管制、事故船只救援报警、海洋环境监测、海洋专属经济区保护，并对非法捕鱼、污染物倾倒、非法走私偷渡等起到强有力的监管作用。在海事智能视频监控方面，目前面临的难点就是当摄像机安装在晃动的海洋浮标或运动的海事船上时，如何实现在各种海况下快速地检测出运动的舰船目标，这是实现海域智能监测的关键技术之一。为此，本文对海洋动态视频监控中舰船目标快速检测算法以及海上雾天图像清晰化处理算法进行了深入研究，完成的主要研究工作如下：
（1）提出了一种基于小波域视觉注意力模型的海面舰船目标快速检测算法。根据人类视觉观测特点，即大尺度下注重目标的轮廓，小尺度下注重目标的细节，首先利用利用提升小波变换在小波域建立了双尺度视觉选择注意模型，然后在粗分辨率低频子带上分别利用相位谱法和梯度法建立视觉显著图，并对两者进行有效融合形成综合视觉显著图，最后通过小波反变换得到原始高分辨率图像的视觉显著图，由此实现海面目标区域的检测与提取。实验结果表明：提出的算法能够快速、准确地实现海面舰船目标的自动检测，可用于基于海洋浮标的海事智能监测。
（2）提出了一种基于海面背景纹理模型的舰船目标检测算法。根据海面纹理具有均匀性和一致性的特点，该算法首先在离散余弦变换（DCT）域提取图像子块的能量特征，实现了天空背景和海天线的快速检测。然后，对于海天线以下的海面区域，在DCT域提取图像子块的纹理特征向量，并利用自适应模糊C均值聚类方法建立了海面背景的混合纹理模型。最后，利用建立的海面纹理模型，实现了海面背景与舰船目标的分割。实验结果表明：提出的算法可以快速、鲁棒实现舰船目标的检测，尤其适合于高海况下基于运动监视平台的海事监测。
（3）提出了一种基于轮廓波变换（Contourlet）的海上雾天图像清晰化处理算法。该算法首先将RGB图像转换为YUV图像，对亮度Y图像根据雾天成像物理模型，利用Contourlet变换将图像低频成分和高频成分有效分离；然后在低频子带上利用双边滤波技术实现了散射光成分的有效估计与去除，并消除了散射光去除过程引起的“光晕效应”；对Contourlet变换后的高频子带，进行自适应阈值去噪和纹理细节的增强处理；对Contourlet反变换重建后的亮度Y图像再进行直方图均衡化处理，以实现图像整体对比度的增强；最后将亮度Y图像的处理结果与颜色分量U、V合成得到清晰化的雾天彩色图像。实验结果表明：提出的算法既能显著降低处理时间；又能有效提高雾天图像的清晰度。
China possesses a long coastline, so it is necessary to develop automatic monitoring andsurveillance system for its maritime space. In military area, it is of great significance forsafeguarding the maritime rights and interests, strengthening supervision and management ofimportant sea areas, and reducing the maritime disputes and so on. In civil area, it has manyapplications such as marine traffic management in port or bay, ocean environment monitoring,protection of exclusive economical zones, searching and rescuing of ships from wrecks, andtaking measures against illegal activities such as illegal fishing, smuggling, and immigration.Currently, the major impediment to intelligent video maritime monitoring is how to fast androbustlydetecttheseasurfacetargetsundervariousseastatesforbuoy-basedorship-basedvisualsurveillance, which isoneofthekeytechnologies for intelligent maritime visualmonitoring. Toovercometheabove-mentionedobstacle,thisthesisinvestigatesthefastshipdetectionalgorithmsandrestorationalgorithmofseafogdegradedimagesfordynamicmaritimevisualsurveillanceindepth,andhasaccomplishedthefollowingresearchwork.
(1) A fast algorithm to detect sea surface ship targets based on the visual selective attentionmechanism in wavelet domain is proposed in the dissertation. According to the characteristics ofhumanvisualobservation,that is,thecontoursofobjectsishighlightedat largescaleandthedetailsof object is focused at small scale, a two-scale visual attention model is first established in thewaveletdomainbyusing liftingwavelettransform.Thentwo visualsaliencemapsaregeneratedbyemploying the phase spectrum method and gradient based method on the low-pass subband ofwavelet domain withcoarseresolutionrespectively, and asynthetic visualsalience map isobtainedby effective combination of the both obtained salient maps. Finally, the high resolution visualsaliencymapoforiginalimageisgeneratedbyinversewavelettransform,andtheseasurfaceobjectregionsareextracted fromthe final saliency map. Theexperimentalresults showthat theproposedalgorithm can detect the maritime targets quickly and accurately, so it can be used for maritimebuoy-basedintelligentmonitoring.
(2) A novel algorithm for ship target detection based on texture model of sea surface ispresented inthedissertation. Accordingtothe factthatthetexture featureofseasurface isbasicallyuniform and consistent, a segmentation strategy from simple to complex is introduced in theproposed algorithm. Firstly, the simple sky background and horizon are obtained quickly using anenergyfeatureinDCTdomainofimageblocks.Secondly, inordertoseparateshiptargetsfromthecomplex sea background belowthe horizon, a newtexture Gaussian mixture modelofsea surfacebased on imageblocks inDCTdomain isdeveloped,then fromtheconstructed seasurface model,ship targets are segmented fromsea background. The experimentalresults showthat the proposedalgorithm can detect ship targets robustly and satisfy the real-time requirement of visual maritimesurveillance from non-stationary platforms, especially suitable for sea background with high sea state.
(3) A visibility improving algorithm for sea fog images based on contourlet transform isdeveloped. Firstly, the RGB color space is transformed to the YUV color space. Then, for theluminance component Y, from physical formation model of fog images, the low frequencycomponent and the high frequency component is separated effectively from contourlet transform.Secondly,theamountofmediascattering light isestimatedandremovedbyusingadaptivebilateralfiltering on the low-pass subband of contourlet transform, thereby simultaneously eliminating thehalo effect;and forthe high-passsubbandsofcontourlet transform,thenoise is filtered byadaptivethresholding and thetexturedetails areenhanced adaptively. Thirdly, thereconstructed Yimage byinverse contourlet transform is further enhanced through histogram equalization to improve theglobalcontrast.Finally,thevisibilityenhancedimageisobtainedbycombinationtheresultedimageofYcomponentandthechrominancecomponentsofUandV. Theexperimentalresultsshowthatthe proposed algorithm can significantly reduce the processing time and effectively improve thevisibilityoffogdegradedimages.
（1）提出了一种基于小波域视觉注意力模型的海面舰船目标快速检测算法。根据人类视觉观测特点，即大尺度下注重目标的轮廓，小尺度下注重目标的细节，首先利用利用提升小波变换在小波域建立了双尺度视觉选择注意模型，然后在粗分辨率低频子带上分别利用相位谱法和梯度法建立视觉显著图，并对两者进行有效融合形成综合视觉显著图，最后通过小波反变换得到原始高分辨率图像的视觉显著图，由此实现海面目标区域的检测与提取。实验结果表明：提出的算法能够快速、准确地实现海面舰船目标的自动检测，可用于基于海洋浮标的海事智能监测。
（2）提出了一种基于海面背景纹理模型的舰船目标检测算法。根据海面纹理具有均匀性和一致性的特点，该算法首先在离散余弦变换（DCT）域提取图像子块的能量特征，实现了天空背景和海天线的快速检测。然后，对于海天线以下的海面区域，在DCT域提取图像子块的纹理特征向量，并利用自适应模糊C均值聚类方法建立了海面背景的混合纹理模型。最后，利用建立的海面纹理模型，实现了海面背景与舰船目标的分割。实验结果表明：提出的算法可以快速、鲁棒实现舰船目标的检测，尤其适合于高海况下基于运动监视平台的海事监测。
（3）提出了一种基于轮廓波变换（Contourlet）的海上雾天图像清晰化处理算法。该算法首先将RGB图像转换为YUV图像，对亮度Y图像根据雾天成像物理模型，利用Contourlet变换将图像低频成分和高频成分有效分离；然后在低频子带上利用双边滤波技术实现了散射光成分的有效估计与去除，并消除了散射光去除过程引起的“光晕效应”；对Contourlet变换后的高频子带，进行自适应阈值去噪和纹理细节的增强处理；对Contourlet反变换重建后的亮度Y图像再进行直方图均衡化处理，以实现图像整体对比度的增强；最后将亮度Y图像的处理结果与颜色分量U、V合成得到清晰化的雾天彩色图像。实验结果表明：提出的算法既能显著降低处理时间；又能有效提高雾天图像的清晰度。
China possesses a long coastline, so it is necessary to develop automatic monitoring andsurveillance system for its maritime space. In military area, it is of great significance forsafeguarding the maritime rights and interests, strengthening supervision and management ofimportant sea areas, and reducing the maritime disputes and so on. In civil area, it has manyapplications such as marine traffic management in port or bay, ocean environment monitoring,protection of exclusive economical zones, searching and rescuing of ships from wrecks, andtaking measures against illegal activities such as illegal fishing, smuggling, and immigration.Currently, the major impediment to intelligent video maritime monitoring is how to fast androbustlydetecttheseasurfacetargetsundervariousseastatesforbuoy-basedorship-basedvisualsurveillance, which isoneofthekeytechnologies for intelligent maritime visualmonitoring. Toovercometheabove-mentionedobstacle,thisthesisinvestigatesthefastshipdetectionalgorithmsandrestorationalgorithmofseafogdegradedimagesfordynamicmaritimevisualsurveillanceindepth,andhasaccomplishedthefollowingresearchwork.
(1) A fast algorithm to detect sea surface ship targets based on the visual selective attentionmechanism in wavelet domain is proposed in the dissertation. According to the characteristics ofhumanvisualobservation,that is,thecontoursofobjectsishighlightedat largescaleandthedetailsof object is focused at small scale, a two-scale visual attention model is first established in thewaveletdomainbyusing liftingwavelettransform.Thentwo visualsaliencemapsaregeneratedbyemploying the phase spectrum method and gradient based method on the low-pass subband ofwavelet domain withcoarseresolutionrespectively, and asynthetic visualsalience map isobtainedby effective combination of the both obtained salient maps. Finally, the high resolution visualsaliencymapoforiginalimageisgeneratedbyinversewavelettransform,andtheseasurfaceobjectregionsareextracted fromthe final saliency map. Theexperimentalresults showthat theproposedalgorithm can detect the maritime targets quickly and accurately, so it can be used for maritimebuoy-basedintelligentmonitoring.
(2) A novel algorithm for ship target detection based on texture model of sea surface ispresented inthedissertation. Accordingtothe factthatthetexture featureofseasurface isbasicallyuniform and consistent, a segmentation strategy from simple to complex is introduced in theproposed algorithm. Firstly, the simple sky background and horizon are obtained quickly using anenergyfeatureinDCTdomainofimageblocks.Secondly, inordertoseparateshiptargetsfromthecomplex sea background belowthe horizon, a newtexture Gaussian mixture modelofsea surfacebased on imageblocks inDCTdomain isdeveloped,then fromtheconstructed seasurface model,ship targets are segmented fromsea background. The experimentalresults showthat the proposedalgorithm can detect ship targets robustly and satisfy the real-time requirement of visual maritimesurveillance from non-stationary platforms, especially suitable for sea background with high sea state.
(3) A visibility improving algorithm for sea fog images based on contourlet transform isdeveloped. Firstly, the RGB color space is transformed to the YUV color space. Then, for theluminance component Y, from physical formation model of fog images, the low frequencycomponent and the high frequency component is separated effectively from contourlet transform.Secondly,theamountofmediascattering light isestimatedandremovedbyusingadaptivebilateralfiltering on the low-pass subband of contourlet transform, thereby simultaneously eliminating thehalo effect;and forthe high-passsubbandsofcontourlet transform,thenoise is filtered byadaptivethresholding and thetexturedetails areenhanced adaptively. Thirdly, thereconstructed Yimage byinverse contourlet transform is further enhanced through histogram equalization to improve theglobalcontrast.Finally,thevisibilityenhancedimageisobtainedbycombinationtheresultedimageofYcomponentandthechrominancecomponentsofUandV. Theexperimentalresultsshowthatthe proposed algorithm can significantly reduce the processing time and effectively improve thevisibilityoffogdegradedimages.
引文
[1] Collins R., Lipton Alan., Kanade Takeo. Asystemfor video surveillance and monitoring: VSAM final report.CamegieMellonUniversity:TechnicalReportCMU,2000.
[2]ValeraM.,VelastinS.A..Intelligentdistributedsurveillancesystemsareview[J].IEEEProceedingofVision,Image,andSignalProcessing2005,152(2):192-204.
[3]袁国武.智能视频监控中的运动目标检测和跟踪算法研究[D].云南大学,2012.
[4]姜明新.智能视频监控中的目标跟踪技术研究[D].大连理工大学,2013.
[5]郭玲.智能视频监控中运动目标检测的算法研究[D].华南理工大学,2013.
[6] W. Wanniarachchi, D. Sonnadara, M. K. Jayananda. License plate identification based on image processingtechniques.InternationalConferenceonIndustrialandInformationSystems.2007.
[7] Zhang Yanhang, Su Xiaohong, Ma Peijun. Multi-Hough transform track initiation for detecting target withconstantacceleration.2008InternationalSymposiumonInformationScienceandEngineering.2008.
[8]KimMY,KumarS,PavlovicV,RowleyH.Facetrackingandrecognitionwithvisualconstraintsinreal-worldvideos.Proceedingsofthe26thIEEEConferenceonComputerVisionandPatternRecognition.2008.
[9]王明芬.基于形状外观的运动船只识别与跟踪技术研究[D].厦门大学,2008.
[10]洪虹,李文耀.基于背景重构的运动对象越界侦测方法[J].电视技术,2012,36(7):123-126.
[11]夏丽.基于视频检测技术的车流量统计算法研究[D].武汉理工大学,2012.
[12]北京博睿视科技有限责任公司[online].http://www.bravevideo.com/.2011-9-12.
[13] Liu Bin, Wang Yuanyuan, Wang Weiqi. Spectrogram enhancement algorithm: A soft threshold-basedapproach[J].UltrasoundinMedicalandBiology,1999,25(5):839-846.
[14]KimmelR,EladM,ShakedD,etal.AvariationframeworkforRetinex[J].InternationalJournal ofComputerVision,2003,52(1):7-23.
[15]HoDongSeok,JoonLyou.Digitalimagestabilizationusingsimpleestimationoftherotationalandtranslationalmotion.ProceedingsofSPIEtheInternationalSocietyforOpticalEngineering,2005.
[16]CollinsR.T.,LiptonA.,KanadeT.,etal.ASystemforvideosurveillanceandmonitoring.VSAMfinalreport,CarnegieMellonUniversity:TechnicalReportCMU-RI-TR-00-12,2000.
[17]GilmoreJ.F.,GarrenD.A..AirborneVideoSurveillance.SPIEProceedings ofAutomaticTargetRecognition,1998,3371:2-10.
[18] Johnson, Sun, Bobick. Predicting LargePopulation Data Cumulative MatchCharacteristic Performance fromSmall Population Data. Proceedings of4th nternational Conference on Audio-and Video-BasedBiometricPersonAuthentication,UniversityofSurrey,Guildford,UK,2003.
[19]焦波.面向智能视频监控的运动目标检测与跟踪方法研究[D].国防科技大学,2009.
[20]HarituogluI.,HatweodD.,DavisL.,W4:Real-timesurveillanceofpeopleandtheiractivities,IEEETransactiononPatternAnalysisandMachineIntelligence,2000,22(8):809-830.
[21]赵克栋.视频监控系统设计与工程应用[D].北京邮电大学,2009.
[22]黄凯奇,谭铁牛.视觉认知计算模型综述[J].模式识别与人工智能,2013,26(10):951-958.
[23]储珺,杜立辉,汪凌峰,等.基于局部背景感知的目标跟踪[J].自动化学报,2012,28(12):1985-1995.
[24]2012-2017年中国视频监控设备市场发展状况及投资前景预测报告。
[25] Haritaoglu, I, Harwood, D, Davis, S. Real time surveillance of people and their activities [J].IEEETransactionsonPatternAnalysisandMachineIntelligence,2000,22(8).
[26]StaufferC,GrimsonE.LearningPatternsofActivityUsingRealTimeTracking[J].IEEETransactionsonPatternRecognitionandMachineIntelligence(TPAMI),2000,22(8):747-757.
[27]ElgammalA,HarwoodD,DavisL.NonparametricModelforBackgroundSubtraction.In: ProceedingsofInternationalConferenceonComputerVision[C],Kerkira,Greece,1999:751-767.
[28]HanB,ComaniciuD,DavisL.SequentialKernelDensityApproximationthroughModePropagation:ApplicationstoBackgroundModeling[C].Proc.ACCVAsianConf.onComputerVision,2004.
[29]邱德润,朱明旱,伍宗富.一种基于帧间差分与背景差分的运动目标检测新方法[J].湖南文理学院学报:自然科学版,2007,19(1):81-82.
[30]SimonDenman,VinodChandran,SridhaSridharan.Anadaptiveopticalflowtechniqueforpersontrackingsystems[J].PatternRecognitionLetters,2007,28(10):1232-1239.
[31]DavidsonM,VanKoningsveld,MdeDruif,etal.TheCoastViewproject:Developingvideo-derivedCoastalStateIndicatorsinsupportofcoastalzonemanagement[J].CoastalEngineering,2007,54(6-7):463-475.
[32] Holland K T, Puleo J A and Kooney T N. Quantification of swash flows using video-based particle imagevelocimetry.CoastalEngineering,2001,44:65-77.
[33] Holland K. T. Application of the Linear Dispersion Relation with Respect to Depth Inversion and RemotelySensedImagery,IEEETrans.Geosci.RemoteSens.,2001,39:2060-2072.
[34]刘彦飞.基于图像的海冰监测方法研究[D].大连理工大学,2009.
[35]杨明.基于信息融合的海洋溢油识别系统研究[D].上海交通大学,2012.
[36]FefilatyevS.,GoldgofD,ShreveM,etal,2012,Detectionandtrackingofshipsinopenseawithrapidlymovingbuoy-mountedcamera,OceanEngineering,54:1-12.
[37] Holman R., Stanley J.. The history and technical capabilities of Argus [J]. Coastal Engineering,2007,54:477-491.
[38]KBryan,THume,GPayne.TheCam-Erafinalreport,CommissionedResearchReportsYearPublished.2000,www.smf.govt.nz/results/508_final.pdf.
[39]TheCoastViewProject.www.TheCoastViewProject.org.
[40] ChickadelC. C., HolmanR. A., andFreilichM. H. An opticaltechniquefor the measurement oflongshorecurrents.JournalofGeophysicalResearch,2003,108(C11):doi:10.1029/2003JC001774issn:0148-0227.
[41]B.Weissling,S.Ackley,P.Wagner,H.Xie.EISCAM-Digitalacquisitionandprocessingforseaiceparametersformship,2009,57:49-60.
[42]李明兵.基于视频的海上运动目标检测技术研究[D].国家海洋技术中心,2012.
[43]齐占辉,张锁平.一种波浪爬高的视频测量方法[J].海洋技术,2010,29(1):24-27.
[44]胡亚丽.近岸视频观测方法研究[D].中国海洋大学,2013.
[45]FefilatyevS..Detectionofmarinevehicles inimagesand videoof opensea[D].Florida:University ofSouthFlorida,2008.
[46] Selvi M, Kumar S. Sea Object Detection Using Shape and Hybrid Color Texture Classification [J].CommunicationsinComputerandInformationScience,2011,204:19-31.
[47]许飞燕.多平台船载雷达系统的数据处理技术研究[D].哈尔滨工业大学,2013.
[48] Can T, Karali AO, Aytac, T. Detection and tracking of sea-surface targets in infrared and visual band videosusing the bag-of–features technique with scale-invariant feature transform[J]. Applied Optics,2011,50(33):6302-6312.
[49]李积俊.基于数学形态学的海面红外舰船目标检测算法研究[D].山东大学,2012.
[50] Alexander Borghgraef, Olivier Barnich, Fabian Lapierre, et al. An evaluation of pixel-based methods for thedetectionoffloatingobjectsontheseasurface[J].EURASIPJournalonAdvancesinSignalProcessing,2010,978451-978461.
[51] Wu-Chih Hu, Ching-Yu Yang, Deng-Yuan Huang. Robust real-time ship detection and tracking for visualsurveillanceofcageaquaculture[J].VisualCommunicationandImageRepresentation,2011,3(9):543-556.
[52] Wentao Zhang, Yuanzhou Zheng. Intelligent ship-bridge collision avoidance algorithm research based on amodifiedGaussianMixtureModel.2011InternationalConferenceonMultimediaTechnology,ICMT2011,p6414-6419,2011,2011International Conference on Multimedia Technology, ICMT2011; DOI:10.1109/ICMT.2011.6003101.
[53]张明杰,李翠华,刘明业.基于高斯混合模型的海面运动目标检测[J].计算机工程与应用,2005,41(5):27-29.
[54]王明芬,李翠华,余强力.基于融合邻域信息的海面运动目标检测[J].厦门大学学报(自然科学版),2007,46(5):641-645.
[55]李敏,范新南,张学武,等.基于视觉认知机理的复杂动态背景下目标提取[J].光电子·激光,2012,23(2):0366-0373.
[56]HouXD,ZhangLQ.Saliencydetection:Aspectralresidualapproach[C].IEEEComputerSocietyConferenceonComputerVisionandPatternRecognition.LosAlamitos,CA,USA:IEEEComputerSociety,2007:1-8.
[57] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis [J]. IEEETransactionsonPatternAnalysisandMachineIntelligence,1998,20(11):1254-1259.
[58]叶聪颖,李翠华.基于HIS的视觉注意力模型及其在船只检测中的应用[J].厦门大学学报(自然科学版),2005,44(4):484-488.
[59]李崇飞,高颖慧,卢凯,等.基于相位谱和调谐幅度谱的显著性检测方法[J].中国图象图形学报,2012,17(7):821-827.
[60]任蕾,施朝健,冉鑫.应用改进频率调谐的海上小目标检测方法［J］.中国图象图形学报,2012,17(3):365-369.
[61]王金武,姚志均,于乃昭.基于相位谱和频率调谐的海上场景显著性检测[J].计算机应用,2013,33(S1):211-213.
[62] ArshadN, MoonW S, and KimJ N,2011. Anadaptive moving ship detection andtrackingbased on edgeinformation and morphological operations, Proceedings of SPIE, International Conference on Graphic andImageProcessing,8285-8290.
[63]BoumaH,DeLangeDJ,VanDenBroekSP,etal.Automaticdetectionofsmallsurfacetargetswithelectro-optical sensors in a harbor environment [J]. SPIE Passive Sensing and Data Processing,2008,7114:813-820.
[64]A.A.W.Smith,M.K.Teal,P.Voles.Thestatisticalcharacterizationoftheseaforthesegmentationofmaritimeimages[C].ConferenceonVideo/ImageProcessingandMultimediaCommunications,2003,489-494.
[65] P. Voles, M. Teal, J. Sanderson. Target identification in a complex maritime scene[C]. IEEE Colloquium onMotionAnalysisandTracking,London,UK:1999,15/1-15/4.
[66]何四华,杨绍清,石爱国,等.基于图像序列区域混沌特征的海面舰船目标检测算法[J].交通运输工程学报,2009,9(1):73-76.
[67]王立地,黄莎白,史泽林.基于有向分维的海面运动目标自动检测方法[J].模式识别与人工智能,2004,17(14):486-450.
[68] M.Roser, F. Moosmann. Classification of weather situations on single color images. IEEE IntelligentVehiclesSymposium.Eindhoven:IEEEComputerSociety,2010,11:798-803
[69]游谦.雾天退化图像的清晰方法研究[D].昆明理工大学,2013.
[70]郭璠，蔡自兴，谢斌，唐琎.图像去雾技术研究综述与展望.计算机应用，2010,30(9):2417-2421.
[71]朱凯军，周焰，兰祖送.基于区域分割的雾天图像增强算法.计算机测量与控制，2006,14(5):661-663.
[72]刘治群,汪荣贵,杨万挺,胡琼. POSH算法及其在雾景图像清晰化中的应用研究.计算机技术与应用发展，2008,468-473.
[73] Land, E.H, Recentadvances inthe Retinex theoryand some implications for corticalcomputations:Colorvisionandthenaturalimage.Proc.Nat.Acad.Sci.USA,1983,80,5163–5169.
[74]李菊霞.雾天条件下的多尺度Retinex图像增强算法[J].计算机科学,2012,40(3):299-303.
[75] Jobson, D.J., Rahman, Z., and Woodell, G.A. Properties and performance of the center/surround Retinex.IEEETransactiononImageProcessing,1997,6(3),451–462.
[76] Jobson, D.J., Brahman, Z., and Woodall, G.A., A multi-scale Retinex for bridging the gap between colorimagesandthehumanobservationofscenes.IEEETransactiononImageProcessing,1997,6(7):965-976.
[77]芮义斌,李鹏,孙锦涛.一种图像去薄雾方法[J].计算机应用,2006,26(1):154-156.
[78] Kaiming He, JianSun, Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior. IEEEConferenceonComputerVisionandPatternReeognition,2009,1956-963.
[79]张洪坤,薛模根,周浦城.基于非线性扩散均值滤波的Retinex雾天图像清晰化算法[J].图学学报，2013,34（2）：47-51.
[80]汪荣贵,傅剑锋,杨志学,等.基于暗原色先验模型的Retinex算法[J].电子学报，2013,41(6):1189-1195.
[81]OakleyJP,SoutherlyBL.Improvingimagequalityinpoorvisibilityconditionsusingmodalfordegradation[J].IEEETransactionsonImageProcessing,1988,7(2):167-179.
[82] Narasimhan S G, Nayar S K. Removing weather effects from monochrome images[C]. Proceedings ofIEEEConferenceonComputerVisionandPatternRecognition,2001,2:186-193.
[83]NarasimhanSG,NayaritSK.ContrastRestorationofWeatherDegradedImages[J],IEEETransactionsonPatternAnalysisandMachineIntelligence,2003,25(6):713-724.
[84] Srinivasa G. Narasimhan, shree K. Nayar. Removing Weather Effects from Monochrome Images.ProceedingsoftheIEEEComputerSocietyConferenceonComputerVisionandPatternReeognition,2001,2:186-93.
[85] Robby T. Tan, Nikolas Peterson, Lars Peterson. Visibility Enhancement for Roads with Foggy or HazyScenes.Proceedingsofthe2007IEEEIntelligentVehiclesSymposiumIstanbul,2007,19-24.
[86]PeterCarr,RichardHartley.ImprovedSingleImageDebasingusingGeometry.DigitalImageComputing:TechniquesandApplieations,2009,103-110.
[87] R. Fattal. Single image dehiscing. International Conference on Computer Graphics and InteractiveTechniquesarchiveACMSIGGRAPH,2008.
[88]孙玉宝,肖亮,韦志辉,等.基于偏微分方程的户外图像去雾方法[J].系统仿真学报，2007,19（16）：3739-3745.
[89]郭珈,王孝通,胡程鹏,等.基于单幅图像景深和大气散射模型的去雾方法[J].中国图像图形学报,2012,17(1):27-32.
[90]张孝仙,黄智才,赵元洪.遥感数字图像处理.浙江大学出版社,1997,135-145.
[91]文山,李葆青.图像的色彩空间研究.六盘水师范高等专科学校学报,2005,17(6):15-18.
[92]刘怀强,基于视频的车辆检测与跟踪技术研究[D].中国海洋大学,2006.
[93]叶晓东,朱兆达.中值滤波的快速算法.信号处理,1997,13(3):227-230.
[94]何东晓.智能视频监控中的运动目标检测方法研究[D].中国海洋大学，2008.
[95]刘佳旭.基于DSP的水下视频压缩编码系统研究[D].青岛：中国海洋大学，2010.
[96]葛中峰.水下视频图像复原与拼接方法研究[D].中国海洋大学,2012.
[97] Sweldens W. The lifting scheme: a custom-design construction of biorthogonal wavelets. Applied andcomputationalharmonicanalysis,1998:186-200.
[98]王文锦.基水下视频图像高效压缩编码方法研究[D].青岛：中国海洋大学，2010.
[99]小野定康.JPEG2000技术.北京：科学出版社，2004,117~127.
[100]谢凤英,赵丹培.VisualC++数字图像处理.北京:电子工业出版社,2008,161-165.
[101]Ahmed,N.,Natarajan,T.,andRae,K.R.[1974].“DiscreteCosineTransforms.”IEEETrans.Comp.,vol.C-23,pp.90-93.
[102]ZHAOShan,LIUJing.ImageRetrievalinDCTCompressedDomain[J].JournalofBeijingUniversityofPostsandTelecommunications,2008,31(5):5-8.
[103]王欢,邢丽冬,钱志余,等.基于改进的高斯混合模型的运动物体检测[J].2012,22(12):139-141.
[104]杨浩，张磊，何潜等.基于自适应模糊C均值算法的电力负荷分类研究[J].电力系统保护与控制，2010，38（16）：111-114.
[105]游谦.雾天退化图像的清晰方法研究[D].昆明理工大学,2013.
[106]KimJ.Y,KimL.S.,HwangS.H.,Anadvancedcontrastenhancementusingpartiallyoverlappedsub-blockhistogramequalization.CircuitsandSystemsforVideoTechnology,2002,11(4),475-484.
[107]艾明晶,戴隆忠,曹庆华.雾天环境下自适应图像增强去雾方法研究,计算机仿真,2009,26(7):244-247.
[108]RussoF.AnImageenhancementtechniquecombiningsharpeningandnoisingreduction[J].IEEETransactionsonInstrumentationandMeasurement,2002,51(4),824-828.
[109]JishajohnandM.Wilsey. EnhancementofWeatherDegradedVideoSequencesUsingWaveletFusion.7thIEEEInternationalConferenceCyberneticIntelligentSystems,2008,l-6.
[110]ErikssonB.Automaticimagede-weatheringusingcurvelet—basedvanishingpointdetection[J],
[2010-01-20].http://homepages,care.wise.edu/beriksso/cs766.pdf.
[111]黄黎红.一种基于单尺度Retinex的雾天降质图像增强新算法[J].应用光学，2010,31（5）：728-733.
[112]陈先桥.雾天交通场景中退化图像的增强方法研究(D).武汉:武汉理工大学,2008.
[113]盛裴轩,毛节泰,李建国等.大气物理学.北京:北京大学出版社,2003.
[114]翟艺书.雾天降质图像的清晰化技术研究(D).大连海事大学,2008.
[115]E.J.Meeariney.OpticsoftheAtmosphere:ScatteringByMoleculesandParticles.JohnWileyAndSOnS,1975.
[116]]N.KoPeika,GeneralWavelengthDependenceofImagingThroughTheAtmosphere,AppliedOPtics,20(9),1981.
[117]向静波,苏秀琴,陆陶.基于Contourlet变换和形态学的图像增强方法[J].光子学报,2009,38(1):224-227.
[118] DOMN, VET TERLIM. Contourlets:a directional multi-resolution imagerepresentation[C]. IEEEInt.ConfonImageProcessing,Rochester,2002,1(9):357-360.
[119] M. Wilscy and Jisha John. A novel wavelet fusion method for contrast correction and visibilityenhancementofcolorimage.ProceedingsoftheWorldCongressonEngineering,2008.
[120]Donohod,L.Denoisingbysoftthresholding[J].IEEETransonIT,1995,41(3):613-627.
[121] Lakhwinder KAUR，Savita GUPTA，R.C. CHAUHAN. Image Demonizing using WaveletThresholding[A].Proceedings oftheThirdIndianConferenceonComputerVision,Graphics&ImageProcessing[C]. Ahmadabad,India：AlliedPublishersPrivateLimited，2002，11：1522-1531.
[122]徐华南,刘哲,胡钢. Contourlet变换及其在图像去噪中的应用研究[J].计算机应用研究,2009,26(2):401-405.
[123]宋凯,沈红,刘昶.多尺度Retinex灰度图像增强算法[J].辽宁大学学报,2008,35(1):46-48.
[124]郭璠.图像去雾方法和评价及其应用研究[D].中南大学,2011.
[125]朱虹等.数字图像处理基础.北京:科学出版社,2005:32-33
[2]ValeraM.,VelastinS.A..Intelligentdistributedsurveillancesystemsareview[J].IEEEProceedingofVision,Image,andSignalProcessing2005,152(2):192-204.
[3]袁国武.智能视频监控中的运动目标检测和跟踪算法研究[D].云南大学,2012.
[4]姜明新.智能视频监控中的目标跟踪技术研究[D].大连理工大学,2013.
[5]郭玲.智能视频监控中运动目标检测的算法研究[D].华南理工大学,2013.
[6] W. Wanniarachchi, D. Sonnadara, M. K. Jayananda. License plate identification based on image processingtechniques.InternationalConferenceonIndustrialandInformationSystems.2007.
[7] Zhang Yanhang, Su Xiaohong, Ma Peijun. Multi-Hough transform track initiation for detecting target withconstantacceleration.2008InternationalSymposiumonInformationScienceandEngineering.2008.
[8]KimMY,KumarS,PavlovicV,RowleyH.Facetrackingandrecognitionwithvisualconstraintsinreal-worldvideos.Proceedingsofthe26thIEEEConferenceonComputerVisionandPatternRecognition.2008.
[9]王明芬.基于形状外观的运动船只识别与跟踪技术研究[D].厦门大学,2008.
[10]洪虹,李文耀.基于背景重构的运动对象越界侦测方法[J].电视技术,2012,36(7):123-126.
[11]夏丽.基于视频检测技术的车流量统计算法研究[D].武汉理工大学,2012.
[12]北京博睿视科技有限责任公司[online].http://www.bravevideo.com/.2011-9-12.
[13] Liu Bin, Wang Yuanyuan, Wang Weiqi. Spectrogram enhancement algorithm: A soft threshold-basedapproach[J].UltrasoundinMedicalandBiology,1999,25(5):839-846.
[14]KimmelR,EladM,ShakedD,etal.AvariationframeworkforRetinex[J].InternationalJournal ofComputerVision,2003,52(1):7-23.
[15]HoDongSeok,JoonLyou.Digitalimagestabilizationusingsimpleestimationoftherotationalandtranslationalmotion.ProceedingsofSPIEtheInternationalSocietyforOpticalEngineering,2005.
[16]CollinsR.T.,LiptonA.,KanadeT.,etal.ASystemforvideosurveillanceandmonitoring.VSAMfinalreport,CarnegieMellonUniversity:TechnicalReportCMU-RI-TR-00-12,2000.
[17]GilmoreJ.F.,GarrenD.A..AirborneVideoSurveillance.SPIEProceedings ofAutomaticTargetRecognition,1998,3371:2-10.
[18] Johnson, Sun, Bobick. Predicting LargePopulation Data Cumulative MatchCharacteristic Performance fromSmall Population Data. Proceedings of4th nternational Conference on Audio-and Video-BasedBiometricPersonAuthentication,UniversityofSurrey,Guildford,UK,2003.
[19]焦波.面向智能视频监控的运动目标检测与跟踪方法研究[D].国防科技大学,2009.
[20]HarituogluI.,HatweodD.,DavisL.,W4:Real-timesurveillanceofpeopleandtheiractivities,IEEETransactiononPatternAnalysisandMachineIntelligence,2000,22(8):809-830.
[21]赵克栋.视频监控系统设计与工程应用[D].北京邮电大学,2009.
[22]黄凯奇,谭铁牛.视觉认知计算模型综述[J].模式识别与人工智能,2013,26(10):951-958.
[23]储珺,杜立辉,汪凌峰,等.基于局部背景感知的目标跟踪[J].自动化学报,2012,28(12):1985-1995.
[24]2012-2017年中国视频监控设备市场发展状况及投资前景预测报告。
[25] Haritaoglu, I, Harwood, D, Davis, S. Real time surveillance of people and their activities [J].IEEETransactionsonPatternAnalysisandMachineIntelligence,2000,22(8).
[26]StaufferC,GrimsonE.LearningPatternsofActivityUsingRealTimeTracking[J].IEEETransactionsonPatternRecognitionandMachineIntelligence(TPAMI),2000,22(8):747-757.
[27]ElgammalA,HarwoodD,DavisL.NonparametricModelforBackgroundSubtraction.In: ProceedingsofInternationalConferenceonComputerVision[C],Kerkira,Greece,1999:751-767.
[28]HanB,ComaniciuD,DavisL.SequentialKernelDensityApproximationthroughModePropagation:ApplicationstoBackgroundModeling[C].Proc.ACCVAsianConf.onComputerVision,2004.
[29]邱德润,朱明旱,伍宗富.一种基于帧间差分与背景差分的运动目标检测新方法[J].湖南文理学院学报:自然科学版,2007,19(1):81-82.
[30]SimonDenman,VinodChandran,SridhaSridharan.Anadaptiveopticalflowtechniqueforpersontrackingsystems[J].PatternRecognitionLetters,2007,28(10):1232-1239.
[31]DavidsonM,VanKoningsveld,MdeDruif,etal.TheCoastViewproject:Developingvideo-derivedCoastalStateIndicatorsinsupportofcoastalzonemanagement[J].CoastalEngineering,2007,54(6-7):463-475.
[32] Holland K T, Puleo J A and Kooney T N. Quantification of swash flows using video-based particle imagevelocimetry.CoastalEngineering,2001,44:65-77.
[33] Holland K. T. Application of the Linear Dispersion Relation with Respect to Depth Inversion and RemotelySensedImagery,IEEETrans.Geosci.RemoteSens.,2001,39:2060-2072.
[34]刘彦飞.基于图像的海冰监测方法研究[D].大连理工大学,2009.
[35]杨明.基于信息融合的海洋溢油识别系统研究[D].上海交通大学,2012.
[36]FefilatyevS.,GoldgofD,ShreveM,etal,2012,Detectionandtrackingofshipsinopenseawithrapidlymovingbuoy-mountedcamera,OceanEngineering,54:1-12.
[37] Holman R., Stanley J.. The history and technical capabilities of Argus [J]. Coastal Engineering,2007,54:477-491.
[38]KBryan,THume,GPayne.TheCam-Erafinalreport,CommissionedResearchReportsYearPublished.2000,www.smf.govt.nz/results/508_final.pdf.
[39]TheCoastViewProject.www.TheCoastViewProject.org.
[40] ChickadelC. C., HolmanR. A., andFreilichM. H. An opticaltechniquefor the measurement oflongshorecurrents.JournalofGeophysicalResearch,2003,108(C11):doi:10.1029/2003JC001774issn:0148-0227.
[41]B.Weissling,S.Ackley,P.Wagner,H.Xie.EISCAM-Digitalacquisitionandprocessingforseaiceparametersformship,2009,57:49-60.
[42]李明兵.基于视频的海上运动目标检测技术研究[D].国家海洋技术中心,2012.
[43]齐占辉,张锁平.一种波浪爬高的视频测量方法[J].海洋技术,2010,29(1):24-27.
[44]胡亚丽.近岸视频观测方法研究[D].中国海洋大学,2013.
[45]FefilatyevS..Detectionofmarinevehicles inimagesand videoof opensea[D].Florida:University ofSouthFlorida,2008.
[46] Selvi M, Kumar S. Sea Object Detection Using Shape and Hybrid Color Texture Classification [J].CommunicationsinComputerandInformationScience,2011,204:19-31.
[47]许飞燕.多平台船载雷达系统的数据处理技术研究[D].哈尔滨工业大学,2013.
[48] Can T, Karali AO, Aytac, T. Detection and tracking of sea-surface targets in infrared and visual band videosusing the bag-of–features technique with scale-invariant feature transform[J]. Applied Optics,2011,50(33):6302-6312.
[49]李积俊.基于数学形态学的海面红外舰船目标检测算法研究[D].山东大学,2012.
[50] Alexander Borghgraef, Olivier Barnich, Fabian Lapierre, et al. An evaluation of pixel-based methods for thedetectionoffloatingobjectsontheseasurface[J].EURASIPJournalonAdvancesinSignalProcessing,2010,978451-978461.
[51] Wu-Chih Hu, Ching-Yu Yang, Deng-Yuan Huang. Robust real-time ship detection and tracking for visualsurveillanceofcageaquaculture[J].VisualCommunicationandImageRepresentation,2011,3(9):543-556.
[52] Wentao Zhang, Yuanzhou Zheng. Intelligent ship-bridge collision avoidance algorithm research based on amodifiedGaussianMixtureModel.2011InternationalConferenceonMultimediaTechnology,ICMT2011,p6414-6419,2011,2011International Conference on Multimedia Technology, ICMT2011; DOI:10.1109/ICMT.2011.6003101.
[53]张明杰,李翠华,刘明业.基于高斯混合模型的海面运动目标检测[J].计算机工程与应用,2005,41(5):27-29.
[54]王明芬,李翠华,余强力.基于融合邻域信息的海面运动目标检测[J].厦门大学学报(自然科学版),2007,46(5):641-645.
[55]李敏,范新南,张学武,等.基于视觉认知机理的复杂动态背景下目标提取[J].光电子·激光,2012,23(2):0366-0373.
[56]HouXD,ZhangLQ.Saliencydetection:Aspectralresidualapproach[C].IEEEComputerSocietyConferenceonComputerVisionandPatternRecognition.LosAlamitos,CA,USA:IEEEComputerSociety,2007:1-8.
[57] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis [J]. IEEETransactionsonPatternAnalysisandMachineIntelligence,1998,20(11):1254-1259.
[58]叶聪颖,李翠华.基于HIS的视觉注意力模型及其在船只检测中的应用[J].厦门大学学报(自然科学版),2005,44(4):484-488.
[59]李崇飞,高颖慧,卢凯,等.基于相位谱和调谐幅度谱的显著性检测方法[J].中国图象图形学报,2012,17(7):821-827.
[60]任蕾,施朝健,冉鑫.应用改进频率调谐的海上小目标检测方法［J］.中国图象图形学报,2012,17(3):365-369.
[61]王金武,姚志均,于乃昭.基于相位谱和频率调谐的海上场景显著性检测[J].计算机应用,2013,33(S1):211-213.
[62] ArshadN, MoonW S, and KimJ N,2011. Anadaptive moving ship detection andtrackingbased on edgeinformation and morphological operations, Proceedings of SPIE, International Conference on Graphic andImageProcessing,8285-8290.
[63]BoumaH,DeLangeDJ,VanDenBroekSP,etal.Automaticdetectionofsmallsurfacetargetswithelectro-optical sensors in a harbor environment [J]. SPIE Passive Sensing and Data Processing,2008,7114:813-820.
[64]A.A.W.Smith,M.K.Teal,P.Voles.Thestatisticalcharacterizationoftheseaforthesegmentationofmaritimeimages[C].ConferenceonVideo/ImageProcessingandMultimediaCommunications,2003,489-494.
[65] P. Voles, M. Teal, J. Sanderson. Target identification in a complex maritime scene[C]. IEEE Colloquium onMotionAnalysisandTracking,London,UK:1999,15/1-15/4.
[66]何四华,杨绍清,石爱国,等.基于图像序列区域混沌特征的海面舰船目标检测算法[J].交通运输工程学报,2009,9(1):73-76.
[67]王立地,黄莎白,史泽林.基于有向分维的海面运动目标自动检测方法[J].模式识别与人工智能,2004,17(14):486-450.
[68] M.Roser, F. Moosmann. Classification of weather situations on single color images. IEEE IntelligentVehiclesSymposium.Eindhoven:IEEEComputerSociety,2010,11:798-803
[69]游谦.雾天退化图像的清晰方法研究[D].昆明理工大学,2013.
[70]郭璠，蔡自兴，谢斌，唐琎.图像去雾技术研究综述与展望.计算机应用，2010,30(9):2417-2421.
[71]朱凯军，周焰，兰祖送.基于区域分割的雾天图像增强算法.计算机测量与控制，2006,14(5):661-663.
[72]刘治群,汪荣贵,杨万挺,胡琼. POSH算法及其在雾景图像清晰化中的应用研究.计算机技术与应用发展，2008,468-473.
[73] Land, E.H, Recentadvances inthe Retinex theoryand some implications for corticalcomputations:Colorvisionandthenaturalimage.Proc.Nat.Acad.Sci.USA,1983,80,5163–5169.
[74]李菊霞.雾天条件下的多尺度Retinex图像增强算法[J].计算机科学,2012,40(3):299-303.
[75] Jobson, D.J., Rahman, Z., and Woodell, G.A. Properties and performance of the center/surround Retinex.IEEETransactiononImageProcessing,1997,6(3),451–462.
[76] Jobson, D.J., Brahman, Z., and Woodall, G.A., A multi-scale Retinex for bridging the gap between colorimagesandthehumanobservationofscenes.IEEETransactiononImageProcessing,1997,6(7):965-976.
[77]芮义斌,李鹏,孙锦涛.一种图像去薄雾方法[J].计算机应用,2006,26(1):154-156.
[78] Kaiming He, JianSun, Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior. IEEEConferenceonComputerVisionandPatternReeognition,2009,1956-963.
[79]张洪坤,薛模根,周浦城.基于非线性扩散均值滤波的Retinex雾天图像清晰化算法[J].图学学报，2013,34（2）：47-51.
[80]汪荣贵,傅剑锋,杨志学,等.基于暗原色先验模型的Retinex算法[J].电子学报，2013,41(6):1189-1195.
[81]OakleyJP,SoutherlyBL.Improvingimagequalityinpoorvisibilityconditionsusingmodalfordegradation[J].IEEETransactionsonImageProcessing,1988,7(2):167-179.
[82] Narasimhan S G, Nayar S K. Removing weather effects from monochrome images[C]. Proceedings ofIEEEConferenceonComputerVisionandPatternRecognition,2001,2:186-193.
[83]NarasimhanSG,NayaritSK.ContrastRestorationofWeatherDegradedImages[J],IEEETransactionsonPatternAnalysisandMachineIntelligence,2003,25(6):713-724.
[84] Srinivasa G. Narasimhan, shree K. Nayar. Removing Weather Effects from Monochrome Images.ProceedingsoftheIEEEComputerSocietyConferenceonComputerVisionandPatternReeognition,2001,2:186-93.
[85] Robby T. Tan, Nikolas Peterson, Lars Peterson. Visibility Enhancement for Roads with Foggy or HazyScenes.Proceedingsofthe2007IEEEIntelligentVehiclesSymposiumIstanbul,2007,19-24.
[86]PeterCarr,RichardHartley.ImprovedSingleImageDebasingusingGeometry.DigitalImageComputing:TechniquesandApplieations,2009,103-110.
[87] R. Fattal. Single image dehiscing. International Conference on Computer Graphics and InteractiveTechniquesarchiveACMSIGGRAPH,2008.
[88]孙玉宝,肖亮,韦志辉,等.基于偏微分方程的户外图像去雾方法[J].系统仿真学报，2007,19（16）：3739-3745.
[89]郭珈,王孝通,胡程鹏,等.基于单幅图像景深和大气散射模型的去雾方法[J].中国图像图形学报,2012,17(1):27-32.
[90]张孝仙,黄智才,赵元洪.遥感数字图像处理.浙江大学出版社,1997,135-145.
[91]文山,李葆青.图像的色彩空间研究.六盘水师范高等专科学校学报,2005,17(6):15-18.
[92]刘怀强,基于视频的车辆检测与跟踪技术研究[D].中国海洋大学,2006.
[93]叶晓东,朱兆达.中值滤波的快速算法.信号处理,1997,13(3):227-230.
[94]何东晓.智能视频监控中的运动目标检测方法研究[D].中国海洋大学，2008.
[95]刘佳旭.基于DSP的水下视频压缩编码系统研究[D].青岛：中国海洋大学，2010.
[96]葛中峰.水下视频图像复原与拼接方法研究[D].中国海洋大学,2012.
[97] Sweldens W. The lifting scheme: a custom-design construction of biorthogonal wavelets. Applied andcomputationalharmonicanalysis,1998:186-200.
[98]王文锦.基水下视频图像高效压缩编码方法研究[D].青岛：中国海洋大学，2010.
[99]小野定康.JPEG2000技术.北京：科学出版社，2004,117~127.
[100]谢凤英,赵丹培.VisualC++数字图像处理.北京:电子工业出版社,2008,161-165.
[101]Ahmed,N.,Natarajan,T.,andRae,K.R.[1974].“DiscreteCosineTransforms.”IEEETrans.Comp.,vol.C-23,pp.90-93.
[102]ZHAOShan,LIUJing.ImageRetrievalinDCTCompressedDomain[J].JournalofBeijingUniversityofPostsandTelecommunications,2008,31(5):5-8.
[103]王欢,邢丽冬,钱志余,等.基于改进的高斯混合模型的运动物体检测[J].2012,22(12):139-141.
[104]杨浩，张磊，何潜等.基于自适应模糊C均值算法的电力负荷分类研究[J].电力系统保护与控制，2010，38（16）：111-114.
[105]游谦.雾天退化图像的清晰方法研究[D].昆明理工大学,2013.
[106]KimJ.Y,KimL.S.,HwangS.H.,Anadvancedcontrastenhancementusingpartiallyoverlappedsub-blockhistogramequalization.CircuitsandSystemsforVideoTechnology,2002,11(4),475-484.
[107]艾明晶,戴隆忠,曹庆华.雾天环境下自适应图像增强去雾方法研究,计算机仿真,2009,26(7):244-247.
[108]RussoF.AnImageenhancementtechniquecombiningsharpeningandnoisingreduction[J].IEEETransactionsonInstrumentationandMeasurement,2002,51(4),824-828.
[109]JishajohnandM.Wilsey. EnhancementofWeatherDegradedVideoSequencesUsingWaveletFusion.7thIEEEInternationalConferenceCyberneticIntelligentSystems,2008,l-6.
[110]ErikssonB.Automaticimagede-weatheringusingcurvelet—basedvanishingpointdetection[J],
[2010-01-20].http://homepages,care.wise.edu/beriksso/cs766.pdf.
[111]黄黎红.一种基于单尺度Retinex的雾天降质图像增强新算法[J].应用光学，2010,31（5）：728-733.
[112]陈先桥.雾天交通场景中退化图像的增强方法研究(D).武汉:武汉理工大学,2008.
[113]盛裴轩,毛节泰,李建国等.大气物理学.北京:北京大学出版社,2003.
[114]翟艺书.雾天降质图像的清晰化技术研究(D).大连海事大学,2008.
[115]E.J.Meeariney.OpticsoftheAtmosphere:ScatteringByMoleculesandParticles.JohnWileyAndSOnS,1975.
[116]]N.KoPeika,GeneralWavelengthDependenceofImagingThroughTheAtmosphere,AppliedOPtics,20(9),1981.
[117]向静波,苏秀琴,陆陶.基于Contourlet变换和形态学的图像增强方法[J].光子学报,2009,38(1):224-227.
[118] DOMN, VET TERLIM. Contourlets:a directional multi-resolution imagerepresentation[C]. IEEEInt.ConfonImageProcessing,Rochester,2002,1(9):357-360.
[119] M. Wilscy and Jisha John. A novel wavelet fusion method for contrast correction and visibilityenhancementofcolorimage.ProceedingsoftheWorldCongressonEngineering,2008.
[120]Donohod,L.Denoisingbysoftthresholding[J].IEEETransonIT,1995,41(3):613-627.
[121] Lakhwinder KAUR，Savita GUPTA，R.C. CHAUHAN. Image Demonizing using WaveletThresholding[A].Proceedings oftheThirdIndianConferenceonComputerVision,Graphics&ImageProcessing[C]. Ahmadabad,India：AlliedPublishersPrivateLimited，2002，11：1522-1531.
[122]徐华南,刘哲,胡钢. Contourlet变换及其在图像去噪中的应用研究[J].计算机应用研究,2009,26(2):401-405.
[123]宋凯,沈红,刘昶.多尺度Retinex灰度图像增强算法[J].辽宁大学学报,2008,35(1):46-48.
[124]郭璠.图像去雾方法和评价及其应用研究[D].中南大学,2011.
[125]朱虹等.数字图像处理基础.北京:科学出版社,2005:32-33