基于机器视觉路面状态识别关键技术研究
|
摘要
本文采用数码照像机作为前端成像系统,通过对所获取反射图像进行特征提取和分析,对高速公路表面气象状态信息进行监测和识别。针对基于机器视觉的路面状态识别的关键技术与方法,进行了深入研究,研制出摄像型路面状态传感器,为高速公路路面环境提供安全保障;为减少由于光源色温变化带来的光照变化对路面图像识别的影响,提出基于监督颜色恒常性的亮度调整方法,提高了图像的正确识别率;对颜色特征参数提取方法进行研究,并提出基于自适应BP网络的路面图像颜色特征识别方法,提高了路面图像的正确识别率;深入研究纹理特征参数提取方法,结合小波包变换和隐马尔可夫模型的优点,提出WPHMT路面状态识别方法,解决了路面状态难以建模的问题。通过从实际路面环境中获取的图像数据进行验证,证明了所提出算法的鲁棒性和可行性。应用本文所提出的WPHMT识别方法,可提高路面状态的正确识别率8.6%;引入颜色特征参数,采用自适应BP神经网络实现对路面状态的识别,并取得不低于前一种方法的正确识别率。
The transportation meteorological observation system (RWIS) studies have been become an emerging research application domain. They gradually receive great attention at home and abroad. In recent years, along with the increasing intelligence transportation system (ITS) development, real-time monitor, accuracy and robustness on the various RWIS measurement elements face the new requests. Among them, as one of impact road safety key factors, road condition monitor and identification can not only safeguard the safe driving, but raise the overall transportation system's operational efficiency. Moreover, it enhances ITS intelligence management level. As it is difficult for the special working environment to model the road conditions, the problem of low recognition rate on road condition sensors has always existed and limited its research and application development. In China, although many stations and major highway junctions have been installed video surveillance equipment, road conditions and other important information as security for the highway still needed to get through the human-computer interaction. Some road status information even rely on manual monitoring of access. In this situation, the meteorological service can hardly satisfy intelligent transportation systems (ITS) requiring the use of accurate weather requirements. It is important for automatic road condition recognition to reduce traffic accident, enhances ITS decision-making effectiveness.
This article intends to meet highway safety management actual need and meteorological technical instrument demand. It has conducted the deep research regarding the key technologies which have severely affected the correct recognition's rate for road condition. These include the road image calibration problems because of the light source, the condition characteristic parameter extraction problems and the pattern recognition methods used for different characteristic parameters. And these methods were used to conduct training and test the images acquired from the physical highway environment. The correction algorithms based on the monitoring color constancy were studied and implemented. The color and texture feature extraction methods and their identification methods of road surface image were studied in-depth. As the result, these have greatly reduced the light source stability requirements, improved road condition recognition method robustness, enhanced road condition identification accuracy. Acquired advances were involved in this work:
1. The road condition image sensor was designed. To conduct research in road condition recognition methods, a CCD camera was selected as the front-end access to means of images. Based on the Windows XP operating system, MATLAB 7.6 and Visual Basic 6.0 design language were adapted to develop the road condition image sensor and its software. At present, it can recognize four kinds of road states.
2. Based on the surveillance color constant, one kind newly intensity illumination correction method under low light conditions was proposed. The illumination adjustment problem caused by light color temperature change in road images was solved. According to the human vision contrast resolution's limit rule, the parabola function was used to take brightness gain function. Image brightness values were mapped into the best recognition scope defined by experiments. As a result, stability request for the recognition algorithm in environmental illumination change was obviously reduced. The recognition algorithm robustness hereafter was guaranteed effectively.
3. According to the road surface reflection image characteristic, for the first time, the color feature was extracted to segment the road surface reflection image. To segment color road surface images, the segment effect was satisfying using B/R of RGB color system. Following, was that of the H image of the HIS system. The segment precision was obviously higher than the traditional one of using texture gradation matrix.
4. The wavelet packet texture features from road images were analyzed and extracted. The road surface reflection image signals mainly concentrate in the intermediate frequency and high frequency band. Thus, wavelet packet analysis method was employed and the texture details were retained effectively.
5. A new road condition recognition method based on wavelet-HMM was put forward. Through wavelet packet decomposition, the fast training and the likelihood algorithms were used to extract image wavelet packet sub-band energy as texture features. And they were input into HMM to be trained to take HMM parameters so that the road condition classifiers were established and road surface condition recognition was come true. In the method, the wavelet coefficient relevance was considered. And the inaccurate question in describing wavelet coefficient distribution with the standard gaussian distribution was corrected.
6. On the basis of extracting the information in two kind of colored models to form feature vectors, a improved BP neural network recognition algorithm was proposed. It combined with both additional momentum method and the auto-adapted study rate. Based on this, a misalignment recognition model was established and applied in the road condition recognition experiments. The experimental result indicated that this model can distinguish the road surface meteorology condition accurately.
In the simulation experiments the both of road recognition methods all successfully recognized the four kinds of road condition.
The transportation meteorological observation system (RWIS) studies have been become an emerging research application domain. They gradually receive great attention at home and abroad. In recent years, along with the increasing intelligence transportation system (ITS) development, real-time monitor, accuracy and robustness on the various RWIS measurement elements face the new requests. Among them, as one of impact road safety key factors, road condition monitor and identification can not only safeguard the safe driving, but raise the overall transportation system's operational efficiency. Moreover, it enhances ITS intelligence management level. As it is difficult for the special working environment to model the road conditions, the problem of low recognition rate on road condition sensors has always existed and limited its research and application development. In China, although many stations and major highway junctions have been installed video surveillance equipment, road conditions and other important information as security for the highway still needed to get through the human-computer interaction. Some road status information even rely on manual monitoring of access. In this situation, the meteorological service can hardly satisfy intelligent transportation systems (ITS) requiring the use of accurate weather requirements. It is important for automatic road condition recognition to reduce traffic accident, enhances ITS decision-making effectiveness.
This article intends to meet highway safety management actual need and meteorological technical instrument demand. It has conducted the deep research regarding the key technologies which have severely affected the correct recognition's rate for road condition. These include the road image calibration problems because of the light source, the condition characteristic parameter extraction problems and the pattern recognition methods used for different characteristic parameters. And these methods were used to conduct training and test the images acquired from the physical highway environment. The correction algorithms based on the monitoring color constancy were studied and implemented. The color and texture feature extraction methods and their identification methods of road surface image were studied in-depth. As the result, these have greatly reduced the light source stability requirements, improved road condition recognition method robustness, enhanced road condition identification accuracy. Acquired advances were involved in this work:
1. The road condition image sensor was designed. To conduct research in road condition recognition methods, a CCD camera was selected as the front-end access to means of images. Based on the Windows XP operating system, MATLAB 7.6 and Visual Basic 6.0 design language were adapted to develop the road condition image sensor and its software. At present, it can recognize four kinds of road states.
2. Based on the surveillance color constant, one kind newly intensity illumination correction method under low light conditions was proposed. The illumination adjustment problem caused by light color temperature change in road images was solved. According to the human vision contrast resolution's limit rule, the parabola function was used to take brightness gain function. Image brightness values were mapped into the best recognition scope defined by experiments. As a result, stability request for the recognition algorithm in environmental illumination change was obviously reduced. The recognition algorithm robustness hereafter was guaranteed effectively.
3. According to the road surface reflection image characteristic, for the first time, the color feature was extracted to segment the road surface reflection image. To segment color road surface images, the segment effect was satisfying using B/R of RGB color system. Following, was that of the H image of the HIS system. The segment precision was obviously higher than the traditional one of using texture gradation matrix.
4. The wavelet packet texture features from road images were analyzed and extracted. The road surface reflection image signals mainly concentrate in the intermediate frequency and high frequency band. Thus, wavelet packet analysis method was employed and the texture details were retained effectively.
5. A new road condition recognition method based on wavelet-HMM was put forward. Through wavelet packet decomposition, the fast training and the likelihood algorithms were used to extract image wavelet packet sub-band energy as texture features. And they were input into HMM to be trained to take HMM parameters so that the road condition classifiers were established and road surface condition recognition was come true. In the method, the wavelet coefficient relevance was considered. And the inaccurate question in describing wavelet coefficient distribution with the standard gaussian distribution was corrected.
6. On the basis of extracting the information in two kind of colored models to form feature vectors, a improved BP neural network recognition algorithm was proposed. It combined with both additional momentum method and the auto-adapted study rate. Based on this, a misalignment recognition model was established and applied in the road condition recognition experiments. The experimental result indicated that this model can distinguish the road surface meteorology condition accurately.
In the simulation experiments the both of road recognition methods all successfully recognized the four kinds of road condition.
引文
[1]秦大河.气象事业发展战略研究[M].北京:气象出版社,2004:34-36.
[2]Overview,U.S.Department of Transportation.Safety Facts 1997[R].NHSTA,1998.
[3]包左军,汤筠筠,李长城等.公路交通安全与气象影响[M].人民交通出版社,2008年11月第一版:1-12.
[4]曾胜.路面性能评价与分析方法研究[D].中南大学,2003,6:17-19.
[5]诸昌铃.智能交通系统[J].自动化信息,2003(4):13-17.
[6]Johnson.Christine M The Future of ITS[C].Keynote Presentation.ITS Ameria 11th Annual Meeting,2001,Miami,Florida(powerpoint file available at http://www.itsa.org / press.html on Aug 9,2001).
[7]王印海,魏恒等.智能交通系统的发展现状及标准化进程.ITS通讯.2001(3):8-16.
[8]Horsleg J.Overview of ISTEA and MIS[C].Conference on Majo Investment Studies in Transportation:Sep.1996.
[9]K Thirumalai.Rural ITS Applications for Snow Mainenance and Winter-Hazard Mitigation.Proceedings of ITSC,1999,1:465-468.
[10]Harold Brodsky,Hakkert Shalcm.Risk of a road accident in rainy weather[J].Accident Analysis and Prevention,1998,20:161-176.
[11]杨志清.服务于安全运营管理的高速公路网信息系统[D].同济大学,2008,6:3.
[12]王笑京.智能运输系统体系框架研究[J],交通与计算机,2001,19(4):4-7.
[13]冯民学.高速公路交通气象监测智能化预警系统研究[D].南京:南京信息工程大学博士论文,2005,6:11.
[14]章澄昌.产业工程气象学[M].北京:气象出版社,1997.
[15]Jonas Norrman.Slipperiness on road-an expert system classification.Meteorology[J].2000,7(8):27-46.
[16]周须文.气象条件对高速公路路面抗滑性能的影响与预报探讨[J].北 京:中国气象学会年会会议录,2007:189-194.
[17]Xianming Shi,Rodde.Larson.Vehicle-Based Sensor Technologies for Winter Maintenance[J].A Critical Review:2006,10:14-18.
[18]王柏林,胡玉峰,李佳.移动式自动气象站设计及其在应急气象环境监测服务中的应用.气象科技,2006,34(5):628-631.
[19]黎健,魏丽,傅敏宁,等译.美国交通气象信息国家需要评估报告[R].美国联邦气象协调办公室.北京:气象出版社,2008:155-168.
[20]Brinkman,Charles Philip.Highway Ice Detection[J].Transportation Engineering,1977,47(11):34-36.
[21]G Fudger.Sensor Applications in Road Tunnels[J].Proceedings of Sensors in Highway and Civil Engineering,1981:46-62.
[22]Sato Tsutomu,Amakasu Shuji,Honda Syozo,and et al.National Technical Report,1978,24(3):526-538.
[23]J Shao.Fuzzy Categorization of Weather Conditions for Thermal Mapping.Journal Applied Meteorology,1999,39:1784-1790.
[24]J Shao,C Swanson,R Petterson,and et al.Variation of winter road surface temperature due to topography and application of thermal mapping.Meterology Application,1997,131-137
[25]Panu Partanen,Ville Haavisto,Taisto Havvasoja.Laboratory and Field Test Reault from a Pavement Sensor DRS 511.(article file available at attp://www.vaisala.com)
[26]H Rudolf,G Wanielik,A J Sieber,et al.Road condition recognition using microwaves.Proceedings of Intelligent Transportation System,1997,4(5):996-999.
[27]Kamal Sarabandi,S Eric Li and Adib Nashashibi.Modeling and Measurement of Scattering from Road Surfaces at Millimeter-Wave Frequencies.IEEE Transactions on Antennas and Propagation,1997,45(1):1679- 1688.
[28]T Paulsen,P Schmokkel.Laser Road Surface Sensor-LASS.Proceedings of the 12~(th) SIRWEC Conference,Germany,2004:324-328.
[29]Y Chen.Image analysis applied to black ice detection[C].Proceedings of SPIE - The International Society for Optical Engineering,1991,
[30]K Ueda,I Horiba,K Iedaga,et al.A detecting method of wet condition on road using image processing[J].Tran.IPSJ,1994,35(6):1072-1078.
[31]S Yoda,H Okabe,J Takagi,et al.Road surface recognition sensor using an optical spatial filter[J].Proc.Intelligent vehicle'95 Symp,1995:253-257.
[32]M Kawana,Masuo Kawana,Isao Yamazaki.The Application of Visible Image Road Surface Sensors to Winter Road Management,Society of Automotive Engineers of Japan,2005,3888:1-11.
[33]B S Anis,K Majdi,B Jacques,et al.Characterization of road microtexture by means of image analysis[J].Laboratoire Signal,Image at Communications(SIC),2007:4129-4140.
[34]浦毅彬.水体反射光谱特性及其在黑河试验场的初步应用[M].遥感基础试验与应用.北京:能源出版社,1986:68-79.
[35]H S Philip,M D Shirly.Remote Sensing[M].The Quantitative Approach.New York:Mc Graw-Hill,Inc,1998,226-227.
[36]徐存禄.图像纹理分析的新方法及其应用[D].上海复旦学,2005,12:15-17.
[37]王辉.灰度共生纹理矩阵木材表面纹理模式识别方法的研究[D].东北林业大学,2007,6:91-99.
[38]章毓晋.图像分割[M].科学出版社,2001:43-66,122-135.
[39]Park,Jaehyun,Kurz,et al.Unsupervised segmentation of texture images[J].Information Sciences,1996,92(1-4):255-267.
[40]周峰.纹理分析中若干问题的研究[D].北京大学,2001:1-10.
[41]韩逢庆,李红梅,黄席樾.基于遗传算法的一种C-均值聚类算法研究[D].计算机工程与应用,2002,38(24):64-65.
[42]吴高洪,章毓晋,林行刚.分割双纹理图像的最佳滤波器设计方法[J].电子学报,2001,29(1):48-50.
[43]Stan,G.Palubinskas,M Datcu.Bayesian selection of the neighbourhood order for Gauss-Markov texture madels[J].Pattern Recognition Letters,2002,23(10):1229-1238.
[44]S Geman,D Geman.Stochastic Relaxation,Gibbs distributions,and the Bayesian restoration of images[J].IEEE Trans.On Patt.Anal.And Mach. Intell,1984,6(6):721-741.
[45]C T Li.Multi-resolution image segmentation integration Gibbs sampler and region merging algotithm[J].Signal Processing,2003,83(1):67-78.
[46]A Mausumi,K Malay,Kundu.An adaptive approach to unsupervised texture segmentation using M-Band wavelet transform[J].Signal Processing,2001,81:1337-1356.
[47]Chungming,Henry Hom-shing Lu,Ko-chung Han.A Textural approach based on gabor functions for texture edge detection in ultrasound images[J].Ultrasound in Med.& Biol,2001,27(4):515-534.
[48]郭立,朱俊株,陆大虎.基于Gabor小波变换的无监督纹理图像分割[J].微机发展,2000,5:51-54.
[49]吴高洪,章毓晋,林行刚.利用小波变换和特征加权进行纹理分割[J].中国图像图形学报,2001,6(4):333-337.
[50]胡召玲,郭达志,盛业华.基于小波分解的星载SAR图像纹理信息提取[J].遥感学报,2001,5(6):423-427.
[51]Wang Keqi,BAI Xuebing.Classification of Surface texture based on Gauss-MRF Model[J].Journal of Forestry Research,2006,17(1):57-61.
[52]杨浩明,裴继红,杨烜.基于小波框架和模糊软聚类的纹理图像分割方法[J].西安工业学院学报,1999,19(2):103-108.
[53]叶桦,章国宝,陈维楠.基于小波变换的纹理图像分割[J].东南大学学报,1999,29(10):44-48.
[54]刘昉,赵荣椿,程敬之.提高超声图像纹理分析空间分辨率的研究[J].中国生物医学工程学报,2001,20(6):566-570.
[55]郭英凯,杨杰,陆正刚.基于高斯-马尔可夫随机场和神经网络的无监督纹理分割[J].红外与激光工程,2000,29(2):5-8.
[56]G R Gross,J Jain.Markov random field texture models[J].IEEE APMI,1983,5(1):25-39.
[57]I M Elfadel,R W Picard.Gibbs randon fields,co-occurrences and texture modeling[J].IEEE PAMI,1994,16(1):24-37.
[58]靳中鑫.数字图像信息处理[M].北京:国防工业出版社.2003:620-621.
[59]D Chen,L Wang.Texture Features based on Texture Spectrum[J].Pattern Recognition,1991:391-399.
[60]D H Hubel,T N Wiesel.Receptive fields,binocular interaction and functional architecture in the cat's visual cortex[J].Journal of Physiology,2006,160:154.
[61]S G Mallat,S Zhong.Characterization of Signals from Multi-scale Edges[J].IEEE PAMI,1992,14(7):710-732.
[62]董长虹.Matlab神经网络与应用.北京:国防工业出版社,2007年9月第2版,246-248.
[63]W Selsnickl.The design of Hilbert transform pairs of wavelet bases via the flat delay[C].In Proc.IEEE Int.Conf.on Acoustic,Peech and Signal Processing,ICASSP'01,Slat Lake City,UT,May 2001:3673-3776.
[64]Stephane Mallat,Wen Liang Hwang.Singularity Detection and Processing with Wavelets.IEEE Trans.Actions on Information Theory,1992,38(2):617-643.
[65]A Laine,J Fan.Texture classfication by wavelet packet signature[J].IEEE Transaction on Pattern Anlysis and Machine Intelligence,1993,15:1186-1191.
[66]B Chaudhuri,N Sarkar.Texture Segmentation Using Fractal Dimension[J].IEEE Trans Pattern Analysis and Machine Intelligence,1995,17(1):72-77.
[67]李厚强,王超,叶中付,等.一种改进的基于Gabor滤波器的纹理分割方法[J].电路与系统学报,2003,8(6):82-86.
[68]S G Mallat,G Stephane.A Theory for Multi-resolution Signal Decomposition:the wavelet representation[J].IEEE Transactions PAMI,1989,11(7):674-693.
[69]Gabor.Theory of communication[J].Journal of the Institute of Electronical Engineers,1974,93:429-457.
[70]T Chang,C J Kuo.Texture Analysis and Classification with Tree-Structured wavelet Transformation.IEEE Transactions on Image Processing,1993,2(4):429-441.
[71]O Pithier,A Tenner,B J Horticka.A Comparision of Texture Feature Extraction Using Adaptive Gabor Filtering[J].Pyramidal and Tree Structured Wavelet Transation of Pattern Recgnition,2003,29(5):733-742.
[72]J LI,R M Naryanan.A shape-based approach to change detection of lakes using time series remote sensing images[J].IEEE Trasactions on Geo-science and Remote Sensing,2005,41(11):2466-2477.
[73]周伟,桂林MATLAB高级技术应用与分析[M].西安:西安电子科技大学出版社,2006:9-11.
[74]W W Hsieh.Nonlinear canonical correlation analysis of the tropical Pacific climate variability using Neural Network Approach[J].Journal of Climate,2001,14(12):2528-2539.
[75]胡江林,涂松柏,冯光柳.基于人工神经网络的暴雨预报方法探讨[J].热带气象学报,2003,19(4):422-428.
[76]张骥祥.小波变换和马尔科夫随机场在图像处理中的应用研究[D].天津大学博士论文,2007,12:19-28.
[77]I Zavor.Use of multiresolution wavelet feature pyramids for automatic registration of multisensor imagery[J].IEEE Transation on Image Processing,2005,14(6):770-782.
[78]汤顺青.色度学[M].北京:北京理工大学出版社,1990.
[79]Zeki S.A Vision of the Brain[J].London:Blaekwell Scientific Publications,1993:22-24.
[80]陶霖密,姚国正,汪云九.人类颜色视觉的计算理论[J].心理学报,1993,25(3):233-240.
[81]M A Webster,J D Mollon.Color constancy influenced by contrast adaptation[J].Nature,1995,373(23):694-698.
[82]H B Barlow.Vision:Coding and Efficiency[M].Cambridge University Press,1989:363-375.
[83]J Sun,P Perona.Early computation of shape and reflectance in the visual system[J]].Nature,1996,379(11):165-168.
[84]J V Pokorny,D Visual.The Perception of Colour[M].London:Maemillan,1991,6:43-61.
[85]M D Zmura,P Lennie.Mechanisms of color constancecy[J].J Opt Soe Am,1986,3:1662-1672.
[86]M Ebner.Evolving color constancy[J].Pattern Recognition Letters,2006,27(11):1220-1229.
[87]G D Finlayson,M S Drew.White-point preserving color correction[C].Proc.of the 5~(th) Color Imaging Conference:Color,Science,Systems and Apllications.1997:258-261.
[88]蒋小悦.光照变化条件下的人脸检测与识别算法研究[D].西北工业大学博士论文,2006,27-29.
[89]毕于慧.彩色航空图像森林纹理特征提取方法的研究[D].北京林业大学,博士论文,2007:15.
[90]H R Kang.Compare of three-dimensional interpolation techniques by simulation[C].Proc of International Society of Optical Engineer,1995:104-113.
[91]陈功.鲁棒的智能视频监控方法研究[D].中国科技大学博士论文,2008:18.
[92]徐光佑,贾相夷.光照光谱功率功率分布的估计和颜色分割[J].光学学报,1994,14(8):862-866.
[93]S Stilesw,G Wyszecki,N Ohta.Counting metameric object color stimuli using frequency-limited spectral reflectance functions[J].Journal of the Optical Society of America,1977,67(6):779-784.
[94]D B Judd,D L Macadam,Wyszeckig.Spectral Distribution of typical daylight as a function of correlated color temperature[J].Journal of the Optical Society of America,1964,54(8):1031-1040.
[95]J Cohen.Dependency of the spectral reflectance curves of the Mun-sell color chips[J].Psychonomic Science,1964,1:369-370.
[96]L T Maloney,B A Wandell.Color constancy:a method for re-covering surface spectral reflectance[J].Journal of the Optical Society of America,1986,3(1):29-33.
[97]刘立峰,徐光佑.彩色视觉中恢复饱和度信息的探讨[J].计算机工程与科学,1998,20(1):11-15.
[98]徐舒畅,张三元,张引,等.利用直线拟合估算光源强度[J],计算机辅助设计与图形学学报,2005,17(12):2654-2658.
[99]王运琼,游志胜.光滑物体表面颜色失真校正的新方法[J].计算机应用,2003,23(6):127-130.
[100]李峰红.基于图像分析的数字图像色偏检测方法[J].江苏大学学报, 2004,25(5):430-433.
[101]F Gasparingi,R Schettingi.Color correction for digital photo- graphs [C].Proc of the 12~(th) International Conference on Image Analysis and Processing,2003:646-651.
[102]E Lam.Image restoration in digital photography[J].IEEE Tran on Consumer Electronics,2003,49(2):269-274.
[103]N Nakno,R Nishimura,Saih,et al.Digital still camera system formega pixel CCD[J].IEEE Trans on Consumer Electronics,1998,44(3):581-586.
[104]R C Gonzalez,R E Woods.Digital Image Processing.Prentice Hall,Upper Saddle River,NJ,2002,34(2):321-331.
[105]S E Umbaugh.Computer Imaging:Digital Image Analysis and Processing.CRC Press,Florida,2005,2:216-221.
[106]Cohen.Dependency of the spectral reflectance curves of munsell color chips[J].Psychonomical Science,1964,1:169-170.
[107]L T Maloney.Evaluation of linear models of surface spectral reflectance with small number of parameters[J].Journal of Optical Society of America,1986,3(10):1673-1682.
[108]L T Klinker,S A Shafer,T Kanade.Using a color[C].Processing of IEEE Interntional Conference on Computer Vision.New York:Kluwer Academic Publishers,1987:145-150.
[109]C L Novak,S A Shafer.Supervised color constancy for machine vision[J].Proceedings SPIE Vol 1453,Human Vision,Visual Proceeding Processing,and Digital Display.1991:353-368.
[110]白雪生,刘利峰,徐光,等.基于颜色直方图的监督恒常性算法[J].清华大学学报,1997,37(3):1-6.
[111]刘关松,徐建国,吕嘉雯,等.基于有限维线性模型的监督颜色回归恒常性算法[J].华东理工大学学报,2002,28(4):423-425.
[112]蒙丰博,张新荣,李雪威.一种新的基于颜色恒常性的肤色分割算法[J].计算机工程与应用,2007,43(17):82-85.
[113]郑建铧,郝建阳,雷方元,等.利用色彩直方图特征进行偏色图像的自动检测和校正[J].中国图像图形学报,2003,8(9):1001-100.
[114]蔡珣,孟祥旭,向辉.光照色调颜色恒常性算法研究.中国图像图形学 报.2004,9(8):922-927.
[115]蔡利梅,钱建生,罗驱波,等.一种基于色彩保持的低照度图像增强算法[J].计算机工程与软件,2009,26(3):226-227.
[116]王志芳,刘玉红,王颖,等.基于数字图像处理的人类视觉对比度分辨率限制测定[J].生物医学工程学杂志,2008,25(5):998-1002.
[117]J Ross,H D Speed.Contrast adaptation and contrast masking in human vision[J].Proc R Soc B,1991,246:61-69.
[118]Z X Xie,Z F Wang,X L Xiong,et al.Gray color spectral theory and its application[J].IFMBE Proceedings of World Congress on Medical Physics and Biomedical Engineering.COEX Seoul,Korea,2006(4):2500-2503.
[119]Li Hong,Lin Jun,Feng Yanhui.Road Surface Condition Recognition Method Based on DBTA 2009,Wuhan,Hubei China.2009:61-64.
[120]李虹,冯彦辉,林君.基于改进BP神经网络的路面状态识别研究[J].微计算机信息,2010,2:45-47.
[121]李洪宇.机器视觉图像采集设计与研究[D].大庆石油学院硕士论文,2007:40-42.
[122]张杰.基于机器视觉的图像采集与处理系统研究.成都理工大学硕士论文,2006:6-7.
[123]黄志开.彩色图像特征提取与植物分类研究[D].中国科技大学,2006:19-34.
[124]张若宇,坎杂,杨秉义.基于RGB模型脱绒质量与颜色特征的相关性分析[C].中国农业工程学会学术会议论文集,2007:262-264.
[125]陈涛,徐小波,乐忠宇,等.棉花种子颜色分选自动化系统研究[C].中国农业机械学会学术会议论文集,2006:451-454.
[126]金飞剑.基于机器视觉的杂草图像特征提取及识别研究[D].江苏大学,2007,6:49-50.
[127]于海鹏.基于数字图像处理学的木材纹理定量化研究[D].东北林业大学博士论文,2005,6:34-47.
[128]张艳娥.基于计算机视觉技术温室作物长势诊断机理与方法研究[D].中国农业大学博士论文,2005,5:21-39.
[129]Yukihisa,et al.Development of the road surface condition sensing system[A].Proceedings of IEEE Conference on Intelligent Transportation Systems,1999:14-19.
[130]M H Bharati,J Liu,J F Gregor.Image Texture Analysis:Methods and Comparisons[J].Chemometrics & Intelligent Laboratory Systems,2004,72(1):57-71.
[131]R W Conners,C A A Harlow.Theoretical Comparison of Texture Algorithms[J].IEEE Transactions on PATTERN Analysis and Machine Intelligence,1980,2(3):204-222.
[132]焦李成,孙强.多尺度变换域图像的感知与识别:进展和展望[J].计算机学报,2006,29(2):177-193.
[133]谢锦辉.隐马尔可夫随机场及其在语言处理中的应用[J].中南大学学报,1991,19(4):129-133.
[134]李杰.隐马尔科夫模型的研究及其在图像识别中的应用[D],清华大学博士论文,2004:24-27.
[135]J K Romberg,H Choi,R G Baraniuk.Bayessian tree-structured image modeling using wavelet-domain hidden Markov models[J].IEEE Transactions on Signal Processing,2001,10(7):1056-1078.
[136]M S Crouse,R D Nowak,R G Baraniuk.Wavelet-based statistical signal processing using hidden Markov models[J].IEEE Transactions on Signal Processing,1998,46(4)886-902.
[137]C Griorgio,G Giogio.Coupling Fuzzy Modeling and Neural Networks for River Flood Prediction[J].IEEE Transactions on Systems and Cybernetic-Part C:Applications and Reviews,2005,25(3):382-388.
[138]吴建生,金龙,汪灵枝.遗传算法进化设计BP神经网络气象预报建模研究[J].热带气象学报,2006,22(4):411-416.
[139]G E Hinton,P Dayan,M Revow.Modelling the manifolds of images of handwritten digats[J].IEEE Trans Neural Networks,1997,8(1):65-74.
[140]M Fukumi,S Omatu,Y Nishikawa.Rotation-invariant neural pattern recognition system estimating a rotation angle[J],IEEE Trans Neural Networks,1997,8(3):568-586.
[141]许廷发.GABOR小波神经网络算法及其在灰度图像目标识别中的应用研究[D].中国科学院研究生院博士论文,2003:10.
[142]胡宝新,郑兴年.神经网络在遥感图像自动分类中的应用研究[M].遥感技术与应用专辑,1996.
[143]王伟.人工神经网络原理[M].北京:北京航空航天大学出版社,1995.
[144]过仲阳,陈中原,李绿苹,等.人工神经网络技术在水质动态预测中的应用[J].华东师范大学学报(自然科学版),2001,1:84-89.
[145]王文成.神经网络及其在汽车工程中的应用[M].北京:北京理工大学出版社,1998:9-14.
[146]吴川.基于神经网络的目标识别及定位方法的研究[D].中科院长春光学精密机械与物理研究所,2006,6:37-38.
[147]N R Helcht.Neuro-computer Applications[J].Neural Computer,1988:445-453.
[148]屈求真,刘延柱.人工神经网络及其在汽车工程领域中的应用[J].世界汽车,1999,7:22-24
[149]游先祥.遥感原理及在资源环境中的应用[M].北京:中国林业出版社,2003:24-26.
[150]杨嘉麟,郑文玲,马文丽.基于改进BP神经网络的白细胞图像分割[J].微计算机信,2008,11-3:294-295.
[151]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1996:3-20.
[2]Overview,U.S.Department of Transportation.Safety Facts 1997[R].NHSTA,1998.
[3]包左军,汤筠筠,李长城等.公路交通安全与气象影响[M].人民交通出版社,2008年11月第一版:1-12.
[4]曾胜.路面性能评价与分析方法研究[D].中南大学,2003,6:17-19.
[5]诸昌铃.智能交通系统[J].自动化信息,2003(4):13-17.
[6]Johnson.Christine M The Future of ITS[C].Keynote Presentation.ITS Ameria 11th Annual Meeting,2001,Miami,Florida(powerpoint file available at http://www.itsa.org / press.html on Aug 9,2001).
[7]王印海,魏恒等.智能交通系统的发展现状及标准化进程.ITS通讯.2001(3):8-16.
[8]Horsleg J.Overview of ISTEA and MIS[C].Conference on Majo Investment Studies in Transportation:Sep.1996.
[9]K Thirumalai.Rural ITS Applications for Snow Mainenance and Winter-Hazard Mitigation.Proceedings of ITSC,1999,1:465-468.
[10]Harold Brodsky,Hakkert Shalcm.Risk of a road accident in rainy weather[J].Accident Analysis and Prevention,1998,20:161-176.
[11]杨志清.服务于安全运营管理的高速公路网信息系统[D].同济大学,2008,6:3.
[12]王笑京.智能运输系统体系框架研究[J],交通与计算机,2001,19(4):4-7.
[13]冯民学.高速公路交通气象监测智能化预警系统研究[D].南京:南京信息工程大学博士论文,2005,6:11.
[14]章澄昌.产业工程气象学[M].北京:气象出版社,1997.
[15]Jonas Norrman.Slipperiness on road-an expert system classification.Meteorology[J].2000,7(8):27-46.
[16]周须文.气象条件对高速公路路面抗滑性能的影响与预报探讨[J].北 京:中国气象学会年会会议录,2007:189-194.
[17]Xianming Shi,Rodde.Larson.Vehicle-Based Sensor Technologies for Winter Maintenance[J].A Critical Review:2006,10:14-18.
[18]王柏林,胡玉峰,李佳.移动式自动气象站设计及其在应急气象环境监测服务中的应用.气象科技,2006,34(5):628-631.
[19]黎健,魏丽,傅敏宁,等译.美国交通气象信息国家需要评估报告[R].美国联邦气象协调办公室.北京:气象出版社,2008:155-168.
[20]Brinkman,Charles Philip.Highway Ice Detection[J].Transportation Engineering,1977,47(11):34-36.
[21]G Fudger.Sensor Applications in Road Tunnels[J].Proceedings of Sensors in Highway and Civil Engineering,1981:46-62.
[22]Sato Tsutomu,Amakasu Shuji,Honda Syozo,and et al.National Technical Report,1978,24(3):526-538.
[23]J Shao.Fuzzy Categorization of Weather Conditions for Thermal Mapping.Journal Applied Meteorology,1999,39:1784-1790.
[24]J Shao,C Swanson,R Petterson,and et al.Variation of winter road surface temperature due to topography and application of thermal mapping.Meterology Application,1997,131-137
[25]Panu Partanen,Ville Haavisto,Taisto Havvasoja.Laboratory and Field Test Reault from a Pavement Sensor DRS 511.(article file available at attp://www.vaisala.com)
[26]H Rudolf,G Wanielik,A J Sieber,et al.Road condition recognition using microwaves.Proceedings of Intelligent Transportation System,1997,4(5):996-999.
[27]Kamal Sarabandi,S Eric Li and Adib Nashashibi.Modeling and Measurement of Scattering from Road Surfaces at Millimeter-Wave Frequencies.IEEE Transactions on Antennas and Propagation,1997,45(1):1679- 1688.
[28]T Paulsen,P Schmokkel.Laser Road Surface Sensor-LASS.Proceedings of the 12~(th) SIRWEC Conference,Germany,2004:324-328.
[29]Y Chen.Image analysis applied to black ice detection[C].Proceedings of SPIE - The International Society for Optical Engineering,1991,
[30]K Ueda,I Horiba,K Iedaga,et al.A detecting method of wet condition on road using image processing[J].Tran.IPSJ,1994,35(6):1072-1078.
[31]S Yoda,H Okabe,J Takagi,et al.Road surface recognition sensor using an optical spatial filter[J].Proc.Intelligent vehicle'95 Symp,1995:253-257.
[32]M Kawana,Masuo Kawana,Isao Yamazaki.The Application of Visible Image Road Surface Sensors to Winter Road Management,Society of Automotive Engineers of Japan,2005,3888:1-11.
[33]B S Anis,K Majdi,B Jacques,et al.Characterization of road microtexture by means of image analysis[J].Laboratoire Signal,Image at Communications(SIC),2007:4129-4140.
[34]浦毅彬.水体反射光谱特性及其在黑河试验场的初步应用[M].遥感基础试验与应用.北京:能源出版社,1986:68-79.
[35]H S Philip,M D Shirly.Remote Sensing[M].The Quantitative Approach.New York:Mc Graw-Hill,Inc,1998,226-227.
[36]徐存禄.图像纹理分析的新方法及其应用[D].上海复旦学,2005,12:15-17.
[37]王辉.灰度共生纹理矩阵木材表面纹理模式识别方法的研究[D].东北林业大学,2007,6:91-99.
[38]章毓晋.图像分割[M].科学出版社,2001:43-66,122-135.
[39]Park,Jaehyun,Kurz,et al.Unsupervised segmentation of texture images[J].Information Sciences,1996,92(1-4):255-267.
[40]周峰.纹理分析中若干问题的研究[D].北京大学,2001:1-10.
[41]韩逢庆,李红梅,黄席樾.基于遗传算法的一种C-均值聚类算法研究[D].计算机工程与应用,2002,38(24):64-65.
[42]吴高洪,章毓晋,林行刚.分割双纹理图像的最佳滤波器设计方法[J].电子学报,2001,29(1):48-50.
[43]Stan,G.Palubinskas,M Datcu.Bayesian selection of the neighbourhood order for Gauss-Markov texture madels[J].Pattern Recognition Letters,2002,23(10):1229-1238.
[44]S Geman,D Geman.Stochastic Relaxation,Gibbs distributions,and the Bayesian restoration of images[J].IEEE Trans.On Patt.Anal.And Mach. Intell,1984,6(6):721-741.
[45]C T Li.Multi-resolution image segmentation integration Gibbs sampler and region merging algotithm[J].Signal Processing,2003,83(1):67-78.
[46]A Mausumi,K Malay,Kundu.An adaptive approach to unsupervised texture segmentation using M-Band wavelet transform[J].Signal Processing,2001,81:1337-1356.
[47]Chungming,Henry Hom-shing Lu,Ko-chung Han.A Textural approach based on gabor functions for texture edge detection in ultrasound images[J].Ultrasound in Med.& Biol,2001,27(4):515-534.
[48]郭立,朱俊株,陆大虎.基于Gabor小波变换的无监督纹理图像分割[J].微机发展,2000,5:51-54.
[49]吴高洪,章毓晋,林行刚.利用小波变换和特征加权进行纹理分割[J].中国图像图形学报,2001,6(4):333-337.
[50]胡召玲,郭达志,盛业华.基于小波分解的星载SAR图像纹理信息提取[J].遥感学报,2001,5(6):423-427.
[51]Wang Keqi,BAI Xuebing.Classification of Surface texture based on Gauss-MRF Model[J].Journal of Forestry Research,2006,17(1):57-61.
[52]杨浩明,裴继红,杨烜.基于小波框架和模糊软聚类的纹理图像分割方法[J].西安工业学院学报,1999,19(2):103-108.
[53]叶桦,章国宝,陈维楠.基于小波变换的纹理图像分割[J].东南大学学报,1999,29(10):44-48.
[54]刘昉,赵荣椿,程敬之.提高超声图像纹理分析空间分辨率的研究[J].中国生物医学工程学报,2001,20(6):566-570.
[55]郭英凯,杨杰,陆正刚.基于高斯-马尔可夫随机场和神经网络的无监督纹理分割[J].红外与激光工程,2000,29(2):5-8.
[56]G R Gross,J Jain.Markov random field texture models[J].IEEE APMI,1983,5(1):25-39.
[57]I M Elfadel,R W Picard.Gibbs randon fields,co-occurrences and texture modeling[J].IEEE PAMI,1994,16(1):24-37.
[58]靳中鑫.数字图像信息处理[M].北京:国防工业出版社.2003:620-621.
[59]D Chen,L Wang.Texture Features based on Texture Spectrum[J].Pattern Recognition,1991:391-399.
[60]D H Hubel,T N Wiesel.Receptive fields,binocular interaction and functional architecture in the cat's visual cortex[J].Journal of Physiology,2006,160:154.
[61]S G Mallat,S Zhong.Characterization of Signals from Multi-scale Edges[J].IEEE PAMI,1992,14(7):710-732.
[62]董长虹.Matlab神经网络与应用.北京:国防工业出版社,2007年9月第2版,246-248.
[63]W Selsnickl.The design of Hilbert transform pairs of wavelet bases via the flat delay[C].In Proc.IEEE Int.Conf.on Acoustic,Peech and Signal Processing,ICASSP'01,Slat Lake City,UT,May 2001:3673-3776.
[64]Stephane Mallat,Wen Liang Hwang.Singularity Detection and Processing with Wavelets.IEEE Trans.Actions on Information Theory,1992,38(2):617-643.
[65]A Laine,J Fan.Texture classfication by wavelet packet signature[J].IEEE Transaction on Pattern Anlysis and Machine Intelligence,1993,15:1186-1191.
[66]B Chaudhuri,N Sarkar.Texture Segmentation Using Fractal Dimension[J].IEEE Trans Pattern Analysis and Machine Intelligence,1995,17(1):72-77.
[67]李厚强,王超,叶中付,等.一种改进的基于Gabor滤波器的纹理分割方法[J].电路与系统学报,2003,8(6):82-86.
[68]S G Mallat,G Stephane.A Theory for Multi-resolution Signal Decomposition:the wavelet representation[J].IEEE Transactions PAMI,1989,11(7):674-693.
[69]Gabor.Theory of communication[J].Journal of the Institute of Electronical Engineers,1974,93:429-457.
[70]T Chang,C J Kuo.Texture Analysis and Classification with Tree-Structured wavelet Transformation.IEEE Transactions on Image Processing,1993,2(4):429-441.
[71]O Pithier,A Tenner,B J Horticka.A Comparision of Texture Feature Extraction Using Adaptive Gabor Filtering[J].Pyramidal and Tree Structured Wavelet Transation of Pattern Recgnition,2003,29(5):733-742.
[72]J LI,R M Naryanan.A shape-based approach to change detection of lakes using time series remote sensing images[J].IEEE Trasactions on Geo-science and Remote Sensing,2005,41(11):2466-2477.
[73]周伟,桂林MATLAB高级技术应用与分析[M].西安:西安电子科技大学出版社,2006:9-11.
[74]W W Hsieh.Nonlinear canonical correlation analysis of the tropical Pacific climate variability using Neural Network Approach[J].Journal of Climate,2001,14(12):2528-2539.
[75]胡江林,涂松柏,冯光柳.基于人工神经网络的暴雨预报方法探讨[J].热带气象学报,2003,19(4):422-428.
[76]张骥祥.小波变换和马尔科夫随机场在图像处理中的应用研究[D].天津大学博士论文,2007,12:19-28.
[77]I Zavor.Use of multiresolution wavelet feature pyramids for automatic registration of multisensor imagery[J].IEEE Transation on Image Processing,2005,14(6):770-782.
[78]汤顺青.色度学[M].北京:北京理工大学出版社,1990.
[79]Zeki S.A Vision of the Brain[J].London:Blaekwell Scientific Publications,1993:22-24.
[80]陶霖密,姚国正,汪云九.人类颜色视觉的计算理论[J].心理学报,1993,25(3):233-240.
[81]M A Webster,J D Mollon.Color constancy influenced by contrast adaptation[J].Nature,1995,373(23):694-698.
[82]H B Barlow.Vision:Coding and Efficiency[M].Cambridge University Press,1989:363-375.
[83]J Sun,P Perona.Early computation of shape and reflectance in the visual system[J]].Nature,1996,379(11):165-168.
[84]J V Pokorny,D Visual.The Perception of Colour[M].London:Maemillan,1991,6:43-61.
[85]M D Zmura,P Lennie.Mechanisms of color constancecy[J].J Opt Soe Am,1986,3:1662-1672.
[86]M Ebner.Evolving color constancy[J].Pattern Recognition Letters,2006,27(11):1220-1229.
[87]G D Finlayson,M S Drew.White-point preserving color correction[C].Proc.of the 5~(th) Color Imaging Conference:Color,Science,Systems and Apllications.1997:258-261.
[88]蒋小悦.光照变化条件下的人脸检测与识别算法研究[D].西北工业大学博士论文,2006,27-29.
[89]毕于慧.彩色航空图像森林纹理特征提取方法的研究[D].北京林业大学,博士论文,2007:15.
[90]H R Kang.Compare of three-dimensional interpolation techniques by simulation[C].Proc of International Society of Optical Engineer,1995:104-113.
[91]陈功.鲁棒的智能视频监控方法研究[D].中国科技大学博士论文,2008:18.
[92]徐光佑,贾相夷.光照光谱功率功率分布的估计和颜色分割[J].光学学报,1994,14(8):862-866.
[93]S Stilesw,G Wyszecki,N Ohta.Counting metameric object color stimuli using frequency-limited spectral reflectance functions[J].Journal of the Optical Society of America,1977,67(6):779-784.
[94]D B Judd,D L Macadam,Wyszeckig.Spectral Distribution of typical daylight as a function of correlated color temperature[J].Journal of the Optical Society of America,1964,54(8):1031-1040.
[95]J Cohen.Dependency of the spectral reflectance curves of the Mun-sell color chips[J].Psychonomic Science,1964,1:369-370.
[96]L T Maloney,B A Wandell.Color constancy:a method for re-covering surface spectral reflectance[J].Journal of the Optical Society of America,1986,3(1):29-33.
[97]刘立峰,徐光佑.彩色视觉中恢复饱和度信息的探讨[J].计算机工程与科学,1998,20(1):11-15.
[98]徐舒畅,张三元,张引,等.利用直线拟合估算光源强度[J],计算机辅助设计与图形学学报,2005,17(12):2654-2658.
[99]王运琼,游志胜.光滑物体表面颜色失真校正的新方法[J].计算机应用,2003,23(6):127-130.
[100]李峰红.基于图像分析的数字图像色偏检测方法[J].江苏大学学报, 2004,25(5):430-433.
[101]F Gasparingi,R Schettingi.Color correction for digital photo- graphs [C].Proc of the 12~(th) International Conference on Image Analysis and Processing,2003:646-651.
[102]E Lam.Image restoration in digital photography[J].IEEE Tran on Consumer Electronics,2003,49(2):269-274.
[103]N Nakno,R Nishimura,Saih,et al.Digital still camera system formega pixel CCD[J].IEEE Trans on Consumer Electronics,1998,44(3):581-586.
[104]R C Gonzalez,R E Woods.Digital Image Processing.Prentice Hall,Upper Saddle River,NJ,2002,34(2):321-331.
[105]S E Umbaugh.Computer Imaging:Digital Image Analysis and Processing.CRC Press,Florida,2005,2:216-221.
[106]Cohen.Dependency of the spectral reflectance curves of munsell color chips[J].Psychonomical Science,1964,1:169-170.
[107]L T Maloney.Evaluation of linear models of surface spectral reflectance with small number of parameters[J].Journal of Optical Society of America,1986,3(10):1673-1682.
[108]L T Klinker,S A Shafer,T Kanade.Using a color[C].Processing of IEEE Interntional Conference on Computer Vision.New York:Kluwer Academic Publishers,1987:145-150.
[109]C L Novak,S A Shafer.Supervised color constancy for machine vision[J].Proceedings SPIE Vol 1453,Human Vision,Visual Proceeding Processing,and Digital Display.1991:353-368.
[110]白雪生,刘利峰,徐光,等.基于颜色直方图的监督恒常性算法[J].清华大学学报,1997,37(3):1-6.
[111]刘关松,徐建国,吕嘉雯,等.基于有限维线性模型的监督颜色回归恒常性算法[J].华东理工大学学报,2002,28(4):423-425.
[112]蒙丰博,张新荣,李雪威.一种新的基于颜色恒常性的肤色分割算法[J].计算机工程与应用,2007,43(17):82-85.
[113]郑建铧,郝建阳,雷方元,等.利用色彩直方图特征进行偏色图像的自动检测和校正[J].中国图像图形学报,2003,8(9):1001-100.
[114]蔡珣,孟祥旭,向辉.光照色调颜色恒常性算法研究.中国图像图形学 报.2004,9(8):922-927.
[115]蔡利梅,钱建生,罗驱波,等.一种基于色彩保持的低照度图像增强算法[J].计算机工程与软件,2009,26(3):226-227.
[116]王志芳,刘玉红,王颖,等.基于数字图像处理的人类视觉对比度分辨率限制测定[J].生物医学工程学杂志,2008,25(5):998-1002.
[117]J Ross,H D Speed.Contrast adaptation and contrast masking in human vision[J].Proc R Soc B,1991,246:61-69.
[118]Z X Xie,Z F Wang,X L Xiong,et al.Gray color spectral theory and its application[J].IFMBE Proceedings of World Congress on Medical Physics and Biomedical Engineering.COEX Seoul,Korea,2006(4):2500-2503.
[119]Li Hong,Lin Jun,Feng Yanhui.Road Surface Condition Recognition Method Based on DBTA 2009,Wuhan,Hubei China.2009:61-64.
[120]李虹,冯彦辉,林君.基于改进BP神经网络的路面状态识别研究[J].微计算机信息,2010,2:45-47.
[121]李洪宇.机器视觉图像采集设计与研究[D].大庆石油学院硕士论文,2007:40-42.
[122]张杰.基于机器视觉的图像采集与处理系统研究.成都理工大学硕士论文,2006:6-7.
[123]黄志开.彩色图像特征提取与植物分类研究[D].中国科技大学,2006:19-34.
[124]张若宇,坎杂,杨秉义.基于RGB模型脱绒质量与颜色特征的相关性分析[C].中国农业工程学会学术会议论文集,2007:262-264.
[125]陈涛,徐小波,乐忠宇,等.棉花种子颜色分选自动化系统研究[C].中国农业机械学会学术会议论文集,2006:451-454.
[126]金飞剑.基于机器视觉的杂草图像特征提取及识别研究[D].江苏大学,2007,6:49-50.
[127]于海鹏.基于数字图像处理学的木材纹理定量化研究[D].东北林业大学博士论文,2005,6:34-47.
[128]张艳娥.基于计算机视觉技术温室作物长势诊断机理与方法研究[D].中国农业大学博士论文,2005,5:21-39.
[129]Yukihisa,et al.Development of the road surface condition sensing system[A].Proceedings of IEEE Conference on Intelligent Transportation Systems,1999:14-19.
[130]M H Bharati,J Liu,J F Gregor.Image Texture Analysis:Methods and Comparisons[J].Chemometrics & Intelligent Laboratory Systems,2004,72(1):57-71.
[131]R W Conners,C A A Harlow.Theoretical Comparison of Texture Algorithms[J].IEEE Transactions on PATTERN Analysis and Machine Intelligence,1980,2(3):204-222.
[132]焦李成,孙强.多尺度变换域图像的感知与识别:进展和展望[J].计算机学报,2006,29(2):177-193.
[133]谢锦辉.隐马尔可夫随机场及其在语言处理中的应用[J].中南大学学报,1991,19(4):129-133.
[134]李杰.隐马尔科夫模型的研究及其在图像识别中的应用[D],清华大学博士论文,2004:24-27.
[135]J K Romberg,H Choi,R G Baraniuk.Bayessian tree-structured image modeling using wavelet-domain hidden Markov models[J].IEEE Transactions on Signal Processing,2001,10(7):1056-1078.
[136]M S Crouse,R D Nowak,R G Baraniuk.Wavelet-based statistical signal processing using hidden Markov models[J].IEEE Transactions on Signal Processing,1998,46(4)886-902.
[137]C Griorgio,G Giogio.Coupling Fuzzy Modeling and Neural Networks for River Flood Prediction[J].IEEE Transactions on Systems and Cybernetic-Part C:Applications and Reviews,2005,25(3):382-388.
[138]吴建生,金龙,汪灵枝.遗传算法进化设计BP神经网络气象预报建模研究[J].热带气象学报,2006,22(4):411-416.
[139]G E Hinton,P Dayan,M Revow.Modelling the manifolds of images of handwritten digats[J].IEEE Trans Neural Networks,1997,8(1):65-74.
[140]M Fukumi,S Omatu,Y Nishikawa.Rotation-invariant neural pattern recognition system estimating a rotation angle[J],IEEE Trans Neural Networks,1997,8(3):568-586.
[141]许廷发.GABOR小波神经网络算法及其在灰度图像目标识别中的应用研究[D].中国科学院研究生院博士论文,2003:10.
[142]胡宝新,郑兴年.神经网络在遥感图像自动分类中的应用研究[M].遥感技术与应用专辑,1996.
[143]王伟.人工神经网络原理[M].北京:北京航空航天大学出版社,1995.
[144]过仲阳,陈中原,李绿苹,等.人工神经网络技术在水质动态预测中的应用[J].华东师范大学学报(自然科学版),2001,1:84-89.
[145]王文成.神经网络及其在汽车工程中的应用[M].北京:北京理工大学出版社,1998:9-14.
[146]吴川.基于神经网络的目标识别及定位方法的研究[D].中科院长春光学精密机械与物理研究所,2006,6:37-38.
[147]N R Helcht.Neuro-computer Applications[J].Neural Computer,1988:445-453.
[148]屈求真,刘延柱.人工神经网络及其在汽车工程领域中的应用[J].世界汽车,1999,7:22-24
[149]游先祥.遥感原理及在资源环境中的应用[M].北京:中国林业出版社,2003:24-26.
[150]杨嘉麟,郑文玲,马文丽.基于改进BP神经网络的白细胞图像分割[J].微计算机信,2008,11-3:294-295.
[151]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1996:3-20.