基于视觉导航的智能车辆目标检测关键技术研究
|
摘要
智能车辆是智能交通系统的重要组成部分，是智能交通系统的主体。智能车辆是一个可以自主感知环境信息并进行自主决策进而实现自动化操作控制的综合统一体，它的实现涉及模式识别、图形图像处理、自动控制、机器视觉等多个交叉学科的理论与技术，在智能车辆的各项关键技术中，导航是车辆感知外部环境进而做出下一步决策的前提。由于视觉信息尤其是彩色图像信息具有信息含量丰富、被动无污染和探测无损伤等优点而倍受关注，是智能车辆实现自主导航的主要技术。其中，对于场景环境中的目标的检测(包括道路检测、交通标志检测以及障碍物检测)又是不可缺少的功能，是预防危险、安全行驶的前提条件。但由于智能车辆所处的室外环境的复杂性和不可控性以及彩色场景图像数据量大、运算复杂度高等因素，导致视觉导航中目标检测的实时性、准确性和鲁棒性得不到满足。为了减小数据量、提高检测的实时性，提高视觉导航的效率，本文在分析现有目标检测技术特点与不足的基础上，对以下关键技术进行了深入而详实的研究。
1．为了降低彩色图像处理的复杂度、提高后续目标检测的速度，本文提出了一种智能车辆视觉导航彩色图像的预处理算法。算法针对饱和度过低时H分量不稳定的不足，在饱和度分量上选择阈值T，把S分量划分为高饱和度区域和低饱和度区域，在高饱和度区域中投影H分量,在低饱和度区域中投影V分量，并且对投影后的S分量进行拉伸。这样S分量即包含了必要的颜色信息又包含了灰度信息，而且图像由原来的高维降到二维。克服了传统预处理方法中颜色信息的丢失造成的分割不准确问题，大大降低了后续处理的数据量，提高了算法实时性，同时也对因光照和阴影等不确定因素造成的影响有较好的鲁棒性。
2．为了克服现有道路检测算法在道路分割时依赖于道路模型、道路区域不完整及自适应性差等缺点，本文提出了一种基于语义的多神经网络非结构化道路自适应检测算法。算法用直方图对道路图像进行多阈值粗分割，然后用多神经网络对分割区域进行高层语义映射，可有效解决当道路特征发生变化时的自适应性和道路检测过程中的实时性问题，实现非结构化道路的完整提取。
3．针对现有主动交通标志检测算法中存在运算量大、复杂背景排除困难等问题，本文提出了一种被动的交通标志快速检测方法。算法对彩色图像在HSV空间中预处理的基础上，构造待检测区域中交通标志中可能包含的颜色的粗糙度直方图，根据颜色匹配表、背景颜色的粗糙度和前景颜色的粗糙度判断图像中是否有交通标志出现，如果有可能出现交通标志则根据粗糙度统计提取标志区域，如果没有则不进行后续的分割，这样减少了检测中的盲目分割和重复判断，大大提高了检测算法的效率和实时性。
4．在障碍物检测方面，针对现有算法在颜色和边缘检测中障碍物提取不准确以及提取的信息不全面等问题，提出一种基于可疑区域二次匹配的立体视觉障碍检测算法。该算法首先分割出可疑障碍区域，然后对可疑区域进行初次匹配，对匹配成功的区域进行二次立体匹配。这样既减少了匹配的样本空间，提高了算法的效率，同时检测出的障碍物又能提供全面的导航信息。
Intelligent vehicle is an important component of Intelligent TransportationSystem (ITS); and also it is a key step in achieving intelligent transportation.Intelligent vehicle is a synthesis body which can percept environmental informationand make a decision automaticly. It involves many theories and techniques such aspattern recognition, image processing, automatic control theory and othertechnologies. It represents the latest achievements of information science andartificial intelligence.Among the many key technologies of intelligence vehicle,vision navigation is base of perception environmental information and making thenext step decision. Since visual information such as color image has advantages ofinformation-rich, passive non-polluting and non-invasive detection, so it has beenattentioned widely, and has become the commonly used technology for realization ofautonomous navigation of intelligent vehicles. Especially road detection and trafficsigns detection and obstacle detection are an essential function in vision basednavigation, and it is the important precondition to prevent dangerous condition and insave driving. But there are many factors such as the complexity and environmentuncontrollable of intelligent vehicle while working in the outdoor environment, thevolume of color images in scene and the computational complexity are very high,which result in poor performance of system’s real-time, accuracy and robustness invision navigation. To improve the performance, enhance the effectiveness of objectdetection system, based on the existing techniques and theories, the paper researchedfollowing key techniques in detail.
1. In order to overcome the computational complexity and enhance the speed ofwhole system, the paper proposed an effective color image preprocessing algorithm ofintelligent vehicle. As H component is instable when saturation is too low, so select athreshold T on the saturation component, and divided S component into the regions ofhigh saturation in low saturation, then project H component in the high saturation areaand V component in low saturation area, the projected components is stretched in S.while the S-component contains not only necessary color information but alsograyscale information, at the same time, the images reduced from the originalhigh-dimension to two-dimension. This algorithm not only overcomes thesegmentation inaccuracy caused by traditional method which lost color information,reduce the amount of data in follow-up treatment significantly, improve real-time, andalso improve the robustness against light and shadow effect significantly.
2. In order to resolving the shortcoming of region imperfection in segmentationand increasing the fault-tolerant, the paper proposed a novel road detection algorithmbased on semantic model and multi-neural network adaptive detection. The algorithmsegment road image using multi-threshold method on histogram firstly, then projectsegmented area by multi-neural network into the semantic model. The algorithm caneffective overcome the problem of self-adaptive during the road occurred change, andcan realize the full road region extraction in unstructured road.
3. Aimed at overcoming the deficiency of high computational complexity and difficulty of extracting complex background in active traffic sign detection, the paperproposed a rapid passive traffic signs detection algorithm. Firstly, the algorithmconstructs roughness histogram for olor which included in traffic signs. If there aretraffic signs in road can bedeterminated according to color matching table, theroughness and it’s background and foreground color. If there are no traffic signs in theroad image, the algorithm do not do following work, if there are traffic signs in theroad image, it extract the region according to roughness statistics in RSH, so thealgorithm avoid to blind detection and repeat judgment during the whole process, andcan dramatically enhance the effectiveness.
4. In the aspect of obstacle detection, in order to overcome the problem of bothlow accuracy in color and edge detection and low comprehensiveness in informationextraction, the paper proposed a spatial vision obstacle detection algorithm based onquestionable area match techniques. The algorithm segment questionable area firstly,then match it at the first time, during the results of it, if matched success, thealgorithm matched second time. Thus the algorithm not only decreased the specimenspatial, but also offered much useful information.
1．为了降低彩色图像处理的复杂度、提高后续目标检测的速度，本文提出了一种智能车辆视觉导航彩色图像的预处理算法。算法针对饱和度过低时H分量不稳定的不足，在饱和度分量上选择阈值T，把S分量划分为高饱和度区域和低饱和度区域，在高饱和度区域中投影H分量,在低饱和度区域中投影V分量，并且对投影后的S分量进行拉伸。这样S分量即包含了必要的颜色信息又包含了灰度信息，而且图像由原来的高维降到二维。克服了传统预处理方法中颜色信息的丢失造成的分割不准确问题，大大降低了后续处理的数据量，提高了算法实时性，同时也对因光照和阴影等不确定因素造成的影响有较好的鲁棒性。
2．为了克服现有道路检测算法在道路分割时依赖于道路模型、道路区域不完整及自适应性差等缺点，本文提出了一种基于语义的多神经网络非结构化道路自适应检测算法。算法用直方图对道路图像进行多阈值粗分割，然后用多神经网络对分割区域进行高层语义映射，可有效解决当道路特征发生变化时的自适应性和道路检测过程中的实时性问题，实现非结构化道路的完整提取。
3．针对现有主动交通标志检测算法中存在运算量大、复杂背景排除困难等问题，本文提出了一种被动的交通标志快速检测方法。算法对彩色图像在HSV空间中预处理的基础上，构造待检测区域中交通标志中可能包含的颜色的粗糙度直方图，根据颜色匹配表、背景颜色的粗糙度和前景颜色的粗糙度判断图像中是否有交通标志出现，如果有可能出现交通标志则根据粗糙度统计提取标志区域，如果没有则不进行后续的分割，这样减少了检测中的盲目分割和重复判断，大大提高了检测算法的效率和实时性。
4．在障碍物检测方面，针对现有算法在颜色和边缘检测中障碍物提取不准确以及提取的信息不全面等问题，提出一种基于可疑区域二次匹配的立体视觉障碍检测算法。该算法首先分割出可疑障碍区域，然后对可疑区域进行初次匹配，对匹配成功的区域进行二次立体匹配。这样既减少了匹配的样本空间，提高了算法的效率，同时检测出的障碍物又能提供全面的导航信息。
Intelligent vehicle is an important component of Intelligent TransportationSystem (ITS); and also it is a key step in achieving intelligent transportation.Intelligent vehicle is a synthesis body which can percept environmental informationand make a decision automaticly. It involves many theories and techniques such aspattern recognition, image processing, automatic control theory and othertechnologies. It represents the latest achievements of information science andartificial intelligence.Among the many key technologies of intelligence vehicle,vision navigation is base of perception environmental information and making thenext step decision. Since visual information such as color image has advantages ofinformation-rich, passive non-polluting and non-invasive detection, so it has beenattentioned widely, and has become the commonly used technology for realization ofautonomous navigation of intelligent vehicles. Especially road detection and trafficsigns detection and obstacle detection are an essential function in vision basednavigation, and it is the important precondition to prevent dangerous condition and insave driving. But there are many factors such as the complexity and environmentuncontrollable of intelligent vehicle while working in the outdoor environment, thevolume of color images in scene and the computational complexity are very high,which result in poor performance of system’s real-time, accuracy and robustness invision navigation. To improve the performance, enhance the effectiveness of objectdetection system, based on the existing techniques and theories, the paper researchedfollowing key techniques in detail.
1. In order to overcome the computational complexity and enhance the speed ofwhole system, the paper proposed an effective color image preprocessing algorithm ofintelligent vehicle. As H component is instable when saturation is too low, so select athreshold T on the saturation component, and divided S component into the regions ofhigh saturation in low saturation, then project H component in the high saturation areaand V component in low saturation area, the projected components is stretched in S.while the S-component contains not only necessary color information but alsograyscale information, at the same time, the images reduced from the originalhigh-dimension to two-dimension. This algorithm not only overcomes thesegmentation inaccuracy caused by traditional method which lost color information,reduce the amount of data in follow-up treatment significantly, improve real-time, andalso improve the robustness against light and shadow effect significantly.
2. In order to resolving the shortcoming of region imperfection in segmentationand increasing the fault-tolerant, the paper proposed a novel road detection algorithmbased on semantic model and multi-neural network adaptive detection. The algorithmsegment road image using multi-threshold method on histogram firstly, then projectsegmented area by multi-neural network into the semantic model. The algorithm caneffective overcome the problem of self-adaptive during the road occurred change, andcan realize the full road region extraction in unstructured road.
3. Aimed at overcoming the deficiency of high computational complexity and difficulty of extracting complex background in active traffic sign detection, the paperproposed a rapid passive traffic signs detection algorithm. Firstly, the algorithmconstructs roughness histogram for olor which included in traffic signs. If there aretraffic signs in road can bedeterminated according to color matching table, theroughness and it’s background and foreground color. If there are no traffic signs in theroad image, the algorithm do not do following work, if there are traffic signs in theroad image, it extract the region according to roughness statistics in RSH, so thealgorithm avoid to blind detection and repeat judgment during the whole process, andcan dramatically enhance the effectiveness.
4. In the aspect of obstacle detection, in order to overcome the problem of bothlow accuracy in color and edge detection and low comprehensiveness in informationextraction, the paper proposed a spatial vision obstacle detection algorithm based onquestionable area match techniques. The algorithm segment questionable area firstly,then match it at the first time, during the results of it, if matched success, thealgorithm matched second time. Thus the algorithm not only decreased the specimenspatial, but also offered much useful information.
引文
[1]徐友春,王荣本.世界智能车辆近况综述.汽车工程,2001,23(5):289-295.
[2] Matthies, L.Xiong, Y.Hogg, et al, A Portable, Autonomous, UrbanReconnaissance Robot.Robotics and Autonomous Systems,2002,40(2-3):163-172.
[3] Dirk J.Verburg, Albert C.M.Vander Knap, Jeroen Ploeg.Developing andTesting Intelligent Vehicles.IEEE Intelligent Vehicle, June2002,(2):537-544.
[4]林鹰.ITS系统及其实现的关键技术.计算机控制与管理,2004,24(4):54-59.
[5]孙涵,任明武,唐振民等.基于机器视觉的智能车辆导航综述.公路交通科技,2005,22(5):132-135.
[6]苏开娜,刘忠云,耿超等.公路智能车辆视觉辅助导航系统的研究.计算机工程,2002,28(9):67-69.
[7] Kiyosumi.Kidono, Jun.Miura, Yoshiaki.Shirai, Autonomous VisualNavigation of a Mobile Robot Using a Human-Guided Experience.Roboticsand Autonomous Systems,2002,40(2-3):124-132.
[8] Shishir.Shah.Mobile robot navigation and scenemodeling using stereofish-eye lens system.machine vision and applications,1997,10(5):159-173.
[9] Bouguet.J.Y, Perona.P. Visual navigation using a single camera. InternationalConference on Computer Vision,2005,645-652.
[10]韩俊淑,韩佳文,高翔等.智能车辆的研究及发展.世界汽车.2003，10(9):79-80
[11]孙海涛.基于视觉导航的智能车辆自主行驶研究:[合肥工业大学硕士论文].2005,1-6.
[12] J.Gowdy, A.Stents, et al.Hierarchical Terrain Representation for Off-roadNavigation.Proc of SPIE Mobile Robots,1991,131-140.
[13] S.Sanjiv,et al,Obstacle Detection for High Speed Autonomous Navigation.Proc.of IEEE Int.Conf.on Robotics and Automation,1991:2798-2805.
[14] R.Wallance, K.Matsuzaki, et al.Progress in robot road following.In1986IEEEInternation Conference on Robotics and Automation,1986,1615-1621.
[15] A.Kelly,Z.Stentz,M.Hebert,Terrain Map Building for Fast Navigation onRugged outdoor Terrain.SPIE,Vol.1831,Mobile RobotsⅦ,1992,576-589.
[16] T.R.Dunlay, Obstacle Avoidance Perception Processing for the AutonomousLand Vehicle. Conf.On Robotics and Automation,1988,912-917.
[17] Jan C Becker, Andreas Simon.Sensor and Navigation Data Fusion for anAutonomousVehicle [J].Proceedings of the IEEE Intelligent VehiclesSymposium,2000,10(2):156-161.
[18] A.Asada.Building a3-D World Model for a Mobile Robot from SensoryData.Proc.IEEE Conf.On Robotics and Automation,1988,918-923.
[19] K.Kluge,T.Weymouth,R.Smith.Information Assimilation Research at theUniversity of Michigan for the ARPA Unmaned Ground Vehicle Project.SPIEVol.2355,Sensor Fusion VII,1994:2-13.
[20] Volpe.R. Navigation Results from Desert Field Tests of the Rocky Mars RoverPrototype.International Journal of Robotics Research,1999,18(7):100-105
[21] J.Kurtz. DEMO III Experimental Unmanned Vehicle Autonomous MobilitySystem Overview.Proceedings of the1998IEEE ISIC/CERA/ISAS JointConference Gaithersburg,1998,14-17.
[22]谢飞.未来智能汽车及智能汽车交通系统.汽车技术,2002.5(1):87~91
[23] P.Bellutta, R.Manduchi, L.Matthies, K.Owens, A.Rankin.Terrain Perceptionfor DEMO III.Proceedings of the IEEE Intelligent Vehicles SysmposiumDearborn (MI),2000,326-331.
[24] Hubert.Weisser,Peter,J.Schulenberg,et al.Autonomous Driving on Vehicle TestTracks: Overview,Motivation,and Concept,Proc.IEEE Conference IntelligentVehicles,1998,445-450.
[25] Xie Xiuqing,Liu Jinlin,Gu Weikang.An Integrated Vision System for ALVNavigation[J].International Journal of Pattern Recognition and ArtificialIntelligence,2000,14(7):929~940.
[26] M.Bertozzi, A.Broggi, A.Fascioli.Vision-based Intelligent Vehicles: State ofthe Art and Perspectives, Robotics and Autonomous System,2000,32:1-16.
[27] M.Maurer,R.Behringer,et.al.A Compact Vision System for Road VehicleGuidance.Proceedings of the13th International Conference on PatternRecognition,Vienna,Austria,1996,512-518.
[28]黄开胜,金华民,蒋狄南.韩国智能车技术方案分析.电子测量技术,2007,30(2):150-154.
[29]卓晴,邵贝贝,黄开胜.学做智能车.北京:北京航空航天大学出版社,2007:1-18.
[30]周凌翔,叶秀清,顾伟康.国内外自主车研究的最新进展.浙江大学信息与电子工程学ALV实验室技术报告.2005.
[31]朱志刚.视觉导航中环境建模的研究.清华大学,1997,5.
[32] M.Bertozzi, A.Broggi, A.Fascioli.Vision-based Intelligent Vehicles: State ofthe Art and Perspectives [J].Robotics and Autonomous Systems,2000,32(1):1-16.
[33]孙振平,安向京,贺汉根.CITAVT-IV视觉导航的自主车.机器人,2002,24(2):115-121.
[34] D.Marr[著],姚国正,刘磊,汪云九[译].视觉计算理论.北京:科学出版社,1988.
[35]陈熙霖.视觉计算-人类感知能力的延伸.测控技术,2000,29(5):7-14.
[36] Milan Sonka,Vaclav Hlavac,Roger Boyle.Image Processing, Analysis, andMachine Vision.Thomson Asia Pte Led,2002.
[37]王天珍.计算机视觉研究进展.武汉汽车工业大学学报,1998,20(1):23-27.
[38] M.Bart, T.H.Romeny. Computer Vision and Mathematica.Computing andVisualization in Science,2002:53-65.
[39]席学强,王润生.计算机视觉模型中的知识及其表示.计算机工程与应用,2000,11(4):45-48.
[40]章毓晋.中国图像工程:2008.中国图形图像学报,2009,14(5):809-838.
[41] Xu Youchun, Wang Rongben,Li Bing,Summarize of Intelligent Vehicle Studyin the World.Automobile Engine,2001,23(5):234-239.
[42] Wang Rongben,Li Bin,Chu Jiangwei,Ji Suowen,A New Optimal Controller forIntelligent Vehicle Headway Distance,IEEE Intelligent Vehicle Symposium ofIV’2002,FRANCE,2002.
[43] J.R.Spofford, R.D.Rimey, S.H.Munkeby.Overview of the UGV/DemoII Prograin Reconnaissance, Surveillance, and Target Acquisition for the UnmannedGround Vehicle: Providing Surveillance “Eyes” for an Autonomous Vehicle,Editors O.Firschein and T.M.Strat, Morgan Kaufmann,1997:21-40.
[44] J.S.Albus.Outline for a Theory of Intelligence.IEEE Trans on Systems, Manand Cybernetics,1991,21(3):473-509.
[45] J.R.Beveridge, B.Draper, M.R.Stevens, K.Siejko, A.Hanson.A Coregis-trationApproach to Multisensor Target Recognition with Extensions to ExploitDigital Elevation Map Data. In Oscar Firschein,anc Target Acquisition for theUnmanned Ground Vehicle,Morgan Kaufmann,1997:231-265.
[46] M.Maurer, R.Behringer, et al.VaMoRs-P, An Advanced Platform for VisualAutonomous Road Vehicle Guidance, SPIE,2352:239-248.
[47] M.Rosenblum,B.Gothard, B.Klarquist, J. Kurtz, Autonomous Mobility forDemo III, SPIE Intermational Symposium on Intelligent Systems andAdvanced Manufacturing:Mobile Robots VIII,1998:3525A-2.
[48]徐利民.智能交通系统发展及其战略思考.技术经济,2003,(4):15-16.
[49] A.Broggi, M.Bertozzi, A.Fascioli. The2000km Test of theARGOVision-based Autonomous Vehicle, IEEE Intelligent Systems14,1999:1-2.
[50]彭玉华.小波变换与工程应用.北京:科学出版社,1999.
[51]杨龙平,丁宣浩,孙建明.一种新的基于小波变换的图像去噪方法.云南民族大学学报.2005,14(1):136-139.
[52]李淑彼,王茹霖,李春梅.基于噪声方差估计的小波阈值去噪新方法.计算机应用研究,2007,8(3):221-225.
[53]叶于雷,戴文战.一种基于新阈值函数的小波信号去噪方法.计算机应用.2006,26(7):1617-1619.
[54] RAY S,MALLICK BK.A.bayesian transformation model for wavelets.IEEETrans Image Processing,2003,11(9):1512-1526.
[55]刘浩,尹忠科,王建英.Daubechies提升小波在图像去噪中的仿真研究.计算机仿真,2008,11(1):53-57.
[56] Wei Pan, Jinhui Yi, Ye San.Rough Set theory and its application in theintelligent systems. In: proceedings of the7th world congress on intelligentcontrol and automation. chongqing, china,2008,25-27.
[57] Pawlak Z. Rough Sets. International Journal of Computer Information Science,1982,11(5):341-356.
[58] PAWLAK Z.Rough sets: theoretical aspects of reasoning about date.Dordrecht: Kluwer Publishers,1991.
[59] SLOW INSKI R. Intelligent decision support handbook of applications andadvances of the rough sets theory. Dordrecht: Kluwer Academic Publishers,1992.
[60]张立明.人工神经网络的模型及应用.复旦大学出版社.1992.
[61]房振勇,游文虎,冯汝鹏.改进BP算法在模糊神经网络中的应用.北京航空航天大学学报,2007,33(11):1321-1324.
[62]王文成．神经网络及其在汽车工程中的应用．北京理工大学出版社．1998.
[63] DUBO IS D, PRADE H. Rough fuzzy sets and fuzzy rough sets. Int. GeneralSystems,1990,17(1):191-208.
[64] NAKAMURA A. Fuzzy rough sets. Note on Multiplevalued Logic in Japan,1998,9(8):122-128.
[65] BISWASR.On rough sets and fuzzy rough sets. Bull. Pol.Axad.Sci. Math,1994,42:345-349.
[66]杨治明,王晓蓉,彭军,陈应祖.BP人工神经网络在图像分割中的应用.计算机科学,2007,34(4):234-236.
[67] Robert J, Schilling. James J.carroll, Ahmad F.Approxim-ation of nonlinearsystems with radial basis function neural networks.IEEE Transactions onNeural Networks,2001,12(1):1-15.
[68] Zhang Guo-quan, Li zhan-ming, Research on multi-threshold color imagesegmentation based on rough set.2011International Conference on AdvancedMaterials and Computer Science, Key Engineering Materials.2011,771-776.
[69] Zhang Guo-quan, Li zhan-ming.Research on Preprocessing of Color Imagefor Vision based Mobile Robot Navigation. Information Technologyjournal.201110(3):597-601.
[70] Wei Wei-yi, Li zhan-ming, Zhang Guo-quan. novel fuzzy clustering-basedimage segmentation with simultaneous uneven illumination estimation.Information Technology journal,2011,10(3):607-610.
[71] Otsu N. A threshold selection method from gray-level histogram.IEEE TransonSystem, Man and Cybemetics,1979,9(1):62-66.
[72] Pun T. A new method for gray-level picture thresholding using the entropy ofthe histogram.Signal Process,1980,2(3):223-237.
[73]刘岩,岳应娟,李言俊,等.基于粗糙集的图像聚类分割方法研究.红外与激光工程,2004,33(3):300-302.
[74]岳峰,左旺孟,王宽全.基于灰度分解的图像二维阈值选取算法.自动化学报,2009,35(7):1022-1027.
[75]李弼程,柳葆芳.基于二维直方图的模糊门限分割方法.数据采集与处理,2000,15(3):324-329.
[76]范九伦,赵凤.灰度图像的二维曲线阈值分割法.电子学报,2007,5(4):751-755.
[77]赵凤,范九伦.一种结合二维法和模糊熵的图像分割方法.计算机应用研究,2007,24(6):189-191.
[78]吴一全,张金矿.基于改进的二维最大熵及微粒群递推的图像分割.计算机辅助设计与图形学学报,2008,20(10):1338-1344.
[79]唐英干,邸秋艳,赵立兴.基于二维最小Tsallis交叉熵的图像阈值分割方法.物理学报,2008,58(1):9-14.
[80]徐立中,李士进,石爱业.数字图像的智能信息处理.国防工业出版社,2007,137-140.
[81]谢晓峰,张文俊,杨之廉.微粒群算法概述.控制与决策,2003,18(2):129-134.
[82]张国权.基于遗传算法的彩色图像多阈值分割方法研究.电子设计工程,2011,19(2):82-84.
[83]章毓晋.图像分割评价技术分类和比较.中国图像图形学报,1996,1(2):151-158.
[84]张国权,李战明.HSV空间中的彩色图像分割.计算机工程与应用.2010,9(1):86-89.
[85] D.Kuan, Gray Phipps, A.C.Hsuen, Autonomous Robotic Vehicle RoadFollowing, IEEE Trans, PAMI,1988,10(5):648-658.
[86] D.kuan, U.K.Sharma.Model Based Geometric Reasoning For AutonomousRoad Following, IEEE Trans, on Robotics and Automation,1987:416-423.
[87] J.D.Crisman, C.E.Thorpe. A Color Vision System that Tracks Roads andIntersections, IEEE Trams.On Robotics and Automation,1993:49-58.
[88]刘化胜.智能车辆视觉导航中道路检测算法的研究.[南京航空航天大学硕士论文],2004:3-7.
[89]郑伟.基于机器视觉的汽车前方路况识别系统的研究.[广东工业大学硕士论文],2005:1-3
[90]王强.智能车辆视觉辅助导航中的道路检测技术研究.[南京航空航天大学硕士论文],2005:1-2.
[91]邢延,超谈正.基于计算机视觉的车道标线与障碍物自动检测.计算机工程与应用.2003,6:223-225.
[92]杨明,陆建业,王宏,张钹.基于视觉的道路跟踪.模式识别与人工智能,2001，14(2):186-193.
[93] Piccioli G, de Micheli E, Parodi P, et al.Robust method for road sign detectionand recognition.Image and Vision Computing,1996,14(3):209-223.
[94] Hsu S H, Huang C L.Road sign detection and recognition using matchingpursuit method.Image and Vision Computing,2001,19:119-129.
[95] Liou Yi Sheng, Jyh Der, Chen Shu Yuan, et al.A fast method to detect andrecognize scaled and skewed road signs. Berlin: Springer-Verlag,2005.
[96]王驰.基于单目视觉的道路检测算法的研究.[长春理工大学硕士论文].2008.4.
[97] SANTOSH K S A,DEEPTI D R,PRABHAKAR B.Face recognition usingpseudo-2D ergodic HMM.IEEE International Conference onAcoustics,Speech,and Signal Processing. France: IEEE Press.2007:369-372.
[98]金一,阮秋琦.基于核的正交局部保持投影的人脸识别.电子与信息学报,2009,31(2):283－287.
[99]龙飞,董槐林,王备战等.一种基于Gabor描述的概率子空间人脸识别方法.电子与信息学报,2007,29(3):626-630.
[100] LIU C.Capitalize on dimensionality increasing techniques for improving facerecognition grand challenge performance.IEEE Trans.Pattern Analysis andMachine Intelligence,2006,28(5):725-737.
[101] ZHAO H T, SUN S Y, JING Z L, et al.Local structure based supervisedfeaturee extraction.Pattern Recognition,2006,39(88):1546-1550.
[102]叶伟龙,刘华平,孙富春等.非结构化道路区域检测的协同学习方法.中国图象图形学报,2011,16(5):792-799.
[103]张建华,祁力钧,冀荣华等.基于Gabor小波和颜色矩的棉花盲椿象分类方法.农业工程学报,2012,28(1):133-137.
[104] Mike Foedisch, Aya Takeuchi. Adaptive Road Detection through ContinuousEnvironment Learning. Computer society, Proceedings of the33rd AppliedImagery Pattern Recognition Workshop,2005.
[105] Kehtarnavaz N,Griswold N C,Kang D S.Stop-sign recognition based oncolor/shape processing.Machine Vision and Applications,1993,6(4):206-208.
[106] De la Escalera A, Armingol J M, Mata M.Traffic sign recognition and analysisfor intelligent vehicles.Image and Vision Computing,2003,21:247-258.
[107]运士伟,张永胜.转换矩阵算法在粗糙集属性约简中的应用.计算机工程与应用,2009,45(13):45-48.
[108]交通部公路交通安全研究中心.道路交通标志.北京:化学工业出版社,2005.
[109] Barnes NZ, elinsky A, Fletcher L S.Real-time speed sign detection using theradial symmetry detector.IEEE Transaction on Intelligent TransportationSystems,2008,9(2):322-331.
[110]许少秋.户外交通标志检测和形状识别.中国图象图形学报,2009,14(4)：707-711.
[111] Pal S K, King R A.On edge detection of X-ray image using fuzzy sets.IEEETransactions on Pattern Analysis and Machine intelligence,1983,5(1):69-72.
[112] Zhang Guo-quan, Li zhan-ming.Research on color image segmentation basedon RS for intelligent vehicle navigation. Information Technology journal.201110(7),1432-1436.
[113]胡华梅.未知环境中基于视觉的移动智能车辆障碍物检测研究.中南大学,2007.
[114]皮燕妮.智能车中基于单目视觉的前车检测和跟踪.计算机应用研究,2005,1(1):220-223.
[115]王荣本,李琳辉,郭烈,等.基于立体视觉的越野环境感知技术.吉林大学学报,2008,38(3):520-524.
[116] Fattal R, Lischinski D, Werman M. Gradient domain high dynamic rangecompression. In: proceedings of the Proc of the29th Annual conference oncomputer graphics and interactive techniques. New York: ACM Press,2002,249-256.
[117] W.Vander, F.Groen.Stereo based Navigation in Unstructed Environments.Hungary, IEEE Instrumentation and Measurement Technology conferenee,IMTC,2001:2038-2042.
[118]司秉玉,吕宗涛,宿国军等.基于视觉非完整自主车的道路避障.东北大学学报,2003,24(2):107-110.
[119]欧宗瑛,袁野,张艳珍.基于颜色信息足球智能车辆视觉跟踪算法.大连理工大学学报,2000,40(6):729-732.
[120]屈有山,田维坚,李英才.基于并行隔帧差分光流场与灰度分析综合算法的运动目标检测.光子学报,2003,32(2):182-286.
[121] Steven B.Goldberg, Mark W.Maimone, Larry Matthies. Stereo vision androver navigation software for planetary exploration.IEEE AerospaceConference Proceedings, Montana.2002:324-335.
[122]何俊学.基于图像的工件曲面重建关键技术研究.[兰州理工大学博士论文].2011.
[123]于今,饶冀,闫军涛.基于双目立体视觉的壁面清洗机器人障碍物检测研究.传感器与微系统,2007,26(7):67-72.
[124]李庆忠,陈显华,顾伟康.基于彩色立体视觉的障碍物快速检测方法.计算机科学.2003,30(9):72~75.
[125] M.Gong,Y.H.Yang,Multi-baseline stereo matching using genetic algotithm,IEEE Workshop on Stereo and Multi-Baseline Vision, IJCV,2001.
[126] V.Kolmogorov,R.Zabih. Multi-camera scene reconstruction via graph cuts.InEuropean Conference on Computer Vision,2002:82-96.
[2] Matthies, L.Xiong, Y.Hogg, et al, A Portable, Autonomous, UrbanReconnaissance Robot.Robotics and Autonomous Systems,2002,40(2-3):163-172.
[3] Dirk J.Verburg, Albert C.M.Vander Knap, Jeroen Ploeg.Developing andTesting Intelligent Vehicles.IEEE Intelligent Vehicle, June2002,(2):537-544.
[4]林鹰.ITS系统及其实现的关键技术.计算机控制与管理,2004,24(4):54-59.
[5]孙涵,任明武,唐振民等.基于机器视觉的智能车辆导航综述.公路交通科技,2005,22(5):132-135.
[6]苏开娜,刘忠云,耿超等.公路智能车辆视觉辅助导航系统的研究.计算机工程,2002,28(9):67-69.
[7] Kiyosumi.Kidono, Jun.Miura, Yoshiaki.Shirai, Autonomous VisualNavigation of a Mobile Robot Using a Human-Guided Experience.Roboticsand Autonomous Systems,2002,40(2-3):124-132.
[8] Shishir.Shah.Mobile robot navigation and scenemodeling using stereofish-eye lens system.machine vision and applications,1997,10(5):159-173.
[9] Bouguet.J.Y, Perona.P. Visual navigation using a single camera. InternationalConference on Computer Vision,2005,645-652.
[10]韩俊淑,韩佳文,高翔等.智能车辆的研究及发展.世界汽车.2003，10(9):79-80
[11]孙海涛.基于视觉导航的智能车辆自主行驶研究:[合肥工业大学硕士论文].2005,1-6.
[12] J.Gowdy, A.Stents, et al.Hierarchical Terrain Representation for Off-roadNavigation.Proc of SPIE Mobile Robots,1991,131-140.
[13] S.Sanjiv,et al,Obstacle Detection for High Speed Autonomous Navigation.Proc.of IEEE Int.Conf.on Robotics and Automation,1991:2798-2805.
[14] R.Wallance, K.Matsuzaki, et al.Progress in robot road following.In1986IEEEInternation Conference on Robotics and Automation,1986,1615-1621.
[15] A.Kelly,Z.Stentz,M.Hebert,Terrain Map Building for Fast Navigation onRugged outdoor Terrain.SPIE,Vol.1831,Mobile RobotsⅦ,1992,576-589.
[16] T.R.Dunlay, Obstacle Avoidance Perception Processing for the AutonomousLand Vehicle. Conf.On Robotics and Automation,1988,912-917.
[17] Jan C Becker, Andreas Simon.Sensor and Navigation Data Fusion for anAutonomousVehicle [J].Proceedings of the IEEE Intelligent VehiclesSymposium,2000,10(2):156-161.
[18] A.Asada.Building a3-D World Model for a Mobile Robot from SensoryData.Proc.IEEE Conf.On Robotics and Automation,1988,918-923.
[19] K.Kluge,T.Weymouth,R.Smith.Information Assimilation Research at theUniversity of Michigan for the ARPA Unmaned Ground Vehicle Project.SPIEVol.2355,Sensor Fusion VII,1994:2-13.
[20] Volpe.R. Navigation Results from Desert Field Tests of the Rocky Mars RoverPrototype.International Journal of Robotics Research,1999,18(7):100-105
[21] J.Kurtz. DEMO III Experimental Unmanned Vehicle Autonomous MobilitySystem Overview.Proceedings of the1998IEEE ISIC/CERA/ISAS JointConference Gaithersburg,1998,14-17.
[22]谢飞.未来智能汽车及智能汽车交通系统.汽车技术,2002.5(1):87~91
[23] P.Bellutta, R.Manduchi, L.Matthies, K.Owens, A.Rankin.Terrain Perceptionfor DEMO III.Proceedings of the IEEE Intelligent Vehicles SysmposiumDearborn (MI),2000,326-331.
[24] Hubert.Weisser,Peter,J.Schulenberg,et al.Autonomous Driving on Vehicle TestTracks: Overview,Motivation,and Concept,Proc.IEEE Conference IntelligentVehicles,1998,445-450.
[25] Xie Xiuqing,Liu Jinlin,Gu Weikang.An Integrated Vision System for ALVNavigation[J].International Journal of Pattern Recognition and ArtificialIntelligence,2000,14(7):929~940.
[26] M.Bertozzi, A.Broggi, A.Fascioli.Vision-based Intelligent Vehicles: State ofthe Art and Perspectives, Robotics and Autonomous System,2000,32:1-16.
[27] M.Maurer,R.Behringer,et.al.A Compact Vision System for Road VehicleGuidance.Proceedings of the13th International Conference on PatternRecognition,Vienna,Austria,1996,512-518.
[28]黄开胜,金华民,蒋狄南.韩国智能车技术方案分析.电子测量技术,2007,30(2):150-154.
[29]卓晴,邵贝贝,黄开胜.学做智能车.北京:北京航空航天大学出版社,2007:1-18.
[30]周凌翔,叶秀清,顾伟康.国内外自主车研究的最新进展.浙江大学信息与电子工程学ALV实验室技术报告.2005.
[31]朱志刚.视觉导航中环境建模的研究.清华大学,1997,5.
[32] M.Bertozzi, A.Broggi, A.Fascioli.Vision-based Intelligent Vehicles: State ofthe Art and Perspectives [J].Robotics and Autonomous Systems,2000,32(1):1-16.
[33]孙振平,安向京,贺汉根.CITAVT-IV视觉导航的自主车.机器人,2002,24(2):115-121.
[34] D.Marr[著],姚国正,刘磊,汪云九[译].视觉计算理论.北京:科学出版社,1988.
[35]陈熙霖.视觉计算-人类感知能力的延伸.测控技术,2000,29(5):7-14.
[36] Milan Sonka,Vaclav Hlavac,Roger Boyle.Image Processing, Analysis, andMachine Vision.Thomson Asia Pte Led,2002.
[37]王天珍.计算机视觉研究进展.武汉汽车工业大学学报,1998,20(1):23-27.
[38] M.Bart, T.H.Romeny. Computer Vision and Mathematica.Computing andVisualization in Science,2002:53-65.
[39]席学强,王润生.计算机视觉模型中的知识及其表示.计算机工程与应用,2000,11(4):45-48.
[40]章毓晋.中国图像工程:2008.中国图形图像学报,2009,14(5):809-838.
[41] Xu Youchun, Wang Rongben,Li Bing,Summarize of Intelligent Vehicle Studyin the World.Automobile Engine,2001,23(5):234-239.
[42] Wang Rongben,Li Bin,Chu Jiangwei,Ji Suowen,A New Optimal Controller forIntelligent Vehicle Headway Distance,IEEE Intelligent Vehicle Symposium ofIV’2002,FRANCE,2002.
[43] J.R.Spofford, R.D.Rimey, S.H.Munkeby.Overview of the UGV/DemoII Prograin Reconnaissance, Surveillance, and Target Acquisition for the UnmannedGround Vehicle: Providing Surveillance “Eyes” for an Autonomous Vehicle,Editors O.Firschein and T.M.Strat, Morgan Kaufmann,1997:21-40.
[44] J.S.Albus.Outline for a Theory of Intelligence.IEEE Trans on Systems, Manand Cybernetics,1991,21(3):473-509.
[45] J.R.Beveridge, B.Draper, M.R.Stevens, K.Siejko, A.Hanson.A Coregis-trationApproach to Multisensor Target Recognition with Extensions to ExploitDigital Elevation Map Data. In Oscar Firschein,anc Target Acquisition for theUnmanned Ground Vehicle,Morgan Kaufmann,1997:231-265.
[46] M.Maurer, R.Behringer, et al.VaMoRs-P, An Advanced Platform for VisualAutonomous Road Vehicle Guidance, SPIE,2352:239-248.
[47] M.Rosenblum,B.Gothard, B.Klarquist, J. Kurtz, Autonomous Mobility forDemo III, SPIE Intermational Symposium on Intelligent Systems andAdvanced Manufacturing:Mobile Robots VIII,1998:3525A-2.
[48]徐利民.智能交通系统发展及其战略思考.技术经济,2003,(4):15-16.
[49] A.Broggi, M.Bertozzi, A.Fascioli. The2000km Test of theARGOVision-based Autonomous Vehicle, IEEE Intelligent Systems14,1999:1-2.
[50]彭玉华.小波变换与工程应用.北京:科学出版社,1999.
[51]杨龙平,丁宣浩,孙建明.一种新的基于小波变换的图像去噪方法.云南民族大学学报.2005,14(1):136-139.
[52]李淑彼,王茹霖,李春梅.基于噪声方差估计的小波阈值去噪新方法.计算机应用研究,2007,8(3):221-225.
[53]叶于雷,戴文战.一种基于新阈值函数的小波信号去噪方法.计算机应用.2006,26(7):1617-1619.
[54] RAY S,MALLICK BK.A.bayesian transformation model for wavelets.IEEETrans Image Processing,2003,11(9):1512-1526.
[55]刘浩,尹忠科,王建英.Daubechies提升小波在图像去噪中的仿真研究.计算机仿真,2008,11(1):53-57.
[56] Wei Pan, Jinhui Yi, Ye San.Rough Set theory and its application in theintelligent systems. In: proceedings of the7th world congress on intelligentcontrol and automation. chongqing, china,2008,25-27.
[57] Pawlak Z. Rough Sets. International Journal of Computer Information Science,1982,11(5):341-356.
[58] PAWLAK Z.Rough sets: theoretical aspects of reasoning about date.Dordrecht: Kluwer Publishers,1991.
[59] SLOW INSKI R. Intelligent decision support handbook of applications andadvances of the rough sets theory. Dordrecht: Kluwer Academic Publishers,1992.
[60]张立明.人工神经网络的模型及应用.复旦大学出版社.1992.
[61]房振勇,游文虎,冯汝鹏.改进BP算法在模糊神经网络中的应用.北京航空航天大学学报,2007,33(11):1321-1324.
[62]王文成．神经网络及其在汽车工程中的应用．北京理工大学出版社．1998.
[63] DUBO IS D, PRADE H. Rough fuzzy sets and fuzzy rough sets. Int. GeneralSystems,1990,17(1):191-208.
[64] NAKAMURA A. Fuzzy rough sets. Note on Multiplevalued Logic in Japan,1998,9(8):122-128.
[65] BISWASR.On rough sets and fuzzy rough sets. Bull. Pol.Axad.Sci. Math,1994,42:345-349.
[66]杨治明,王晓蓉,彭军,陈应祖.BP人工神经网络在图像分割中的应用.计算机科学,2007,34(4):234-236.
[67] Robert J, Schilling. James J.carroll, Ahmad F.Approxim-ation of nonlinearsystems with radial basis function neural networks.IEEE Transactions onNeural Networks,2001,12(1):1-15.
[68] Zhang Guo-quan, Li zhan-ming, Research on multi-threshold color imagesegmentation based on rough set.2011International Conference on AdvancedMaterials and Computer Science, Key Engineering Materials.2011,771-776.
[69] Zhang Guo-quan, Li zhan-ming.Research on Preprocessing of Color Imagefor Vision based Mobile Robot Navigation. Information Technologyjournal.201110(3):597-601.
[70] Wei Wei-yi, Li zhan-ming, Zhang Guo-quan. novel fuzzy clustering-basedimage segmentation with simultaneous uneven illumination estimation.Information Technology journal,2011,10(3):607-610.
[71] Otsu N. A threshold selection method from gray-level histogram.IEEE TransonSystem, Man and Cybemetics,1979,9(1):62-66.
[72] Pun T. A new method for gray-level picture thresholding using the entropy ofthe histogram.Signal Process,1980,2(3):223-237.
[73]刘岩,岳应娟,李言俊,等.基于粗糙集的图像聚类分割方法研究.红外与激光工程,2004,33(3):300-302.
[74]岳峰,左旺孟,王宽全.基于灰度分解的图像二维阈值选取算法.自动化学报,2009,35(7):1022-1027.
[75]李弼程,柳葆芳.基于二维直方图的模糊门限分割方法.数据采集与处理,2000,15(3):324-329.
[76]范九伦,赵凤.灰度图像的二维曲线阈值分割法.电子学报,2007,5(4):751-755.
[77]赵凤,范九伦.一种结合二维法和模糊熵的图像分割方法.计算机应用研究,2007,24(6):189-191.
[78]吴一全,张金矿.基于改进的二维最大熵及微粒群递推的图像分割.计算机辅助设计与图形学学报,2008,20(10):1338-1344.
[79]唐英干,邸秋艳,赵立兴.基于二维最小Tsallis交叉熵的图像阈值分割方法.物理学报,2008,58(1):9-14.
[80]徐立中,李士进,石爱业.数字图像的智能信息处理.国防工业出版社,2007,137-140.
[81]谢晓峰,张文俊,杨之廉.微粒群算法概述.控制与决策,2003,18(2):129-134.
[82]张国权.基于遗传算法的彩色图像多阈值分割方法研究.电子设计工程,2011,19(2):82-84.
[83]章毓晋.图像分割评价技术分类和比较.中国图像图形学报,1996,1(2):151-158.
[84]张国权,李战明.HSV空间中的彩色图像分割.计算机工程与应用.2010,9(1):86-89.
[85] D.Kuan, Gray Phipps, A.C.Hsuen, Autonomous Robotic Vehicle RoadFollowing, IEEE Trans, PAMI,1988,10(5):648-658.
[86] D.kuan, U.K.Sharma.Model Based Geometric Reasoning For AutonomousRoad Following, IEEE Trans, on Robotics and Automation,1987:416-423.
[87] J.D.Crisman, C.E.Thorpe. A Color Vision System that Tracks Roads andIntersections, IEEE Trams.On Robotics and Automation,1993:49-58.
[88]刘化胜.智能车辆视觉导航中道路检测算法的研究.[南京航空航天大学硕士论文],2004:3-7.
[89]郑伟.基于机器视觉的汽车前方路况识别系统的研究.[广东工业大学硕士论文],2005:1-3
[90]王强.智能车辆视觉辅助导航中的道路检测技术研究.[南京航空航天大学硕士论文],2005:1-2.
[91]邢延,超谈正.基于计算机视觉的车道标线与障碍物自动检测.计算机工程与应用.2003,6:223-225.
[92]杨明,陆建业,王宏,张钹.基于视觉的道路跟踪.模式识别与人工智能,2001，14(2):186-193.
[93] Piccioli G, de Micheli E, Parodi P, et al.Robust method for road sign detectionand recognition.Image and Vision Computing,1996,14(3):209-223.
[94] Hsu S H, Huang C L.Road sign detection and recognition using matchingpursuit method.Image and Vision Computing,2001,19:119-129.
[95] Liou Yi Sheng, Jyh Der, Chen Shu Yuan, et al.A fast method to detect andrecognize scaled and skewed road signs. Berlin: Springer-Verlag,2005.
[96]王驰.基于单目视觉的道路检测算法的研究.[长春理工大学硕士论文].2008.4.
[97] SANTOSH K S A,DEEPTI D R,PRABHAKAR B.Face recognition usingpseudo-2D ergodic HMM.IEEE International Conference onAcoustics,Speech,and Signal Processing. France: IEEE Press.2007:369-372.
[98]金一,阮秋琦.基于核的正交局部保持投影的人脸识别.电子与信息学报,2009,31(2):283－287.
[99]龙飞,董槐林,王备战等.一种基于Gabor描述的概率子空间人脸识别方法.电子与信息学报,2007,29(3):626-630.
[100] LIU C.Capitalize on dimensionality increasing techniques for improving facerecognition grand challenge performance.IEEE Trans.Pattern Analysis andMachine Intelligence,2006,28(5):725-737.
[101] ZHAO H T, SUN S Y, JING Z L, et al.Local structure based supervisedfeaturee extraction.Pattern Recognition,2006,39(88):1546-1550.
[102]叶伟龙,刘华平,孙富春等.非结构化道路区域检测的协同学习方法.中国图象图形学报,2011,16(5):792-799.
[103]张建华,祁力钧,冀荣华等.基于Gabor小波和颜色矩的棉花盲椿象分类方法.农业工程学报,2012,28(1):133-137.
[104] Mike Foedisch, Aya Takeuchi. Adaptive Road Detection through ContinuousEnvironment Learning. Computer society, Proceedings of the33rd AppliedImagery Pattern Recognition Workshop,2005.
[105] Kehtarnavaz N,Griswold N C,Kang D S.Stop-sign recognition based oncolor/shape processing.Machine Vision and Applications,1993,6(4):206-208.
[106] De la Escalera A, Armingol J M, Mata M.Traffic sign recognition and analysisfor intelligent vehicles.Image and Vision Computing,2003,21:247-258.
[107]运士伟,张永胜.转换矩阵算法在粗糙集属性约简中的应用.计算机工程与应用,2009,45(13):45-48.
[108]交通部公路交通安全研究中心.道路交通标志.北京:化学工业出版社,2005.
[109] Barnes NZ, elinsky A, Fletcher L S.Real-time speed sign detection using theradial symmetry detector.IEEE Transaction on Intelligent TransportationSystems,2008,9(2):322-331.
[110]许少秋.户外交通标志检测和形状识别.中国图象图形学报,2009,14(4)：707-711.
[111] Pal S K, King R A.On edge detection of X-ray image using fuzzy sets.IEEETransactions on Pattern Analysis and Machine intelligence,1983,5(1):69-72.
[112] Zhang Guo-quan, Li zhan-ming.Research on color image segmentation basedon RS for intelligent vehicle navigation. Information Technology journal.201110(7),1432-1436.
[113]胡华梅.未知环境中基于视觉的移动智能车辆障碍物检测研究.中南大学,2007.
[114]皮燕妮.智能车中基于单目视觉的前车检测和跟踪.计算机应用研究,2005,1(1):220-223.
[115]王荣本,李琳辉,郭烈,等.基于立体视觉的越野环境感知技术.吉林大学学报,2008,38(3):520-524.
[116] Fattal R, Lischinski D, Werman M. Gradient domain high dynamic rangecompression. In: proceedings of the Proc of the29th Annual conference oncomputer graphics and interactive techniques. New York: ACM Press,2002,249-256.
[117] W.Vander, F.Groen.Stereo based Navigation in Unstructed Environments.Hungary, IEEE Instrumentation and Measurement Technology conferenee,IMTC,2001:2038-2042.
[118]司秉玉,吕宗涛,宿国军等.基于视觉非完整自主车的道路避障.东北大学学报,2003,24(2):107-110.
[119]欧宗瑛,袁野,张艳珍.基于颜色信息足球智能车辆视觉跟踪算法.大连理工大学学报,2000,40(6):729-732.
[120]屈有山,田维坚,李英才.基于并行隔帧差分光流场与灰度分析综合算法的运动目标检测.光子学报,2003,32(2):182-286.
[121] Steven B.Goldberg, Mark W.Maimone, Larry Matthies. Stereo vision androver navigation software for planetary exploration.IEEE AerospaceConference Proceedings, Montana.2002:324-335.
[122]何俊学.基于图像的工件曲面重建关键技术研究.[兰州理工大学博士论文].2011.
[123]于今,饶冀,闫军涛.基于双目立体视觉的壁面清洗机器人障碍物检测研究.传感器与微系统,2007,26(7):67-72.
[124]李庆忠,陈显华,顾伟康.基于彩色立体视觉的障碍物快速检测方法.计算机科学.2003,30(9):72~75.
[125] M.Gong,Y.H.Yang,Multi-baseline stereo matching using genetic algotithm,IEEE Workshop on Stereo and Multi-Baseline Vision, IJCV,2001.
[126] V.Kolmogorov,R.Zabih. Multi-camera scene reconstruction via graph cuts.InEuropean Conference on Computer Vision,2002:82-96.