装甲战车图像跟踪系统的关键技术研究
|
摘要
在未来高技术条件下的局部战争中,装甲战车乘员要在对目标作战的瞬间处理大量的信息,这就需要一个将传感器、处理机和显示器等装置结合在一起的目标自动跟踪系统。这种系统应能从复杂的和混乱的散射干扰背景中迅速、可靠地提取目标,从而使乘员能尽快地对敌目标作出反应。但由于装甲战车的工作环境恶劣、作战环境多样化、目标种类繁多,而且跟踪系统对其所处平台的振动干扰较为敏感,这些都导致了研制装甲战车图像跟踪系统存在着较大的难度。
本文探讨了图像跟踪系统用于装甲战车所存在的技术难点,研究了车载环境下目标的检测识别与跟踪技术,并进一步研究了装甲战车图像跟踪系统的实现技术,完成了相应工程项目的研制任务。
本文的研究工作包括以下几个部分:
①建立了装甲战车图像跟踪系统的跟踪理论。首先,根据对系统任务及战术技术指标的分析,建立了系统的数学模型并给出了系统的跟踪方程;然后,通过探讨如何求解该跟踪方程,将系统进行状态划分,并根据各个工作状态的描述,建立了系统的基本功能结构。论文通过分析系统的基本理论,指出系统的难点和本课题研究的重点。
②针对车体振动对图像序列带来的干扰问题,提出了一种基于特征匹配的实时电子稳像算法。首先,对电子稳像中关键环节——图像配准技术进行了深入研究,给出一种由粗到精、由局部到全局的高效配准算法;接着,采用了递归Kalman滤波技术对配准参数进行运动滤波并对实际图像进行运动补偿;最后,利用了图像拼接技术进行“无定义区”重建,避免了普遍存在的信息丢失和图像降质问题。该算法在保证实时性的同时,具有很高的稳像精度。
③为了使系统在简单场景下能够通过自动选取分割算法来提取目标,提出了一种基于粗糙集理论的图像分割智能决策方法。首先选取若干具代表性的分割算法构成算法库,并用它们对各种样本图像进行分割;然后利用从样本图像中提取出来的各种数值特征,并根据图像分割质量评价标准评判出各样本图像的最优分割算法,用其构成决策信息表;最后应用粗糙集理论来对决策信息表进行离散化处理和属性约简,以生成图像分割算法选取的决策规则。该决策方法能比较有效地根据系统所处理图像特征选取出算法库中最优的分割算法,并可满足系统的实时性要求。
④提出了一种综合运用分形和特征匹配等技术,将复杂场景中目标提取出来的方法。首先,对传统的Snake模型进行改进,并将其应用到初始模板的建立中;然后,引入分形布朗随机场模型,利用分形维数和分形拟合误差确定可能的目标区域;最后,定义了一种新的最小失配距离(MMD)相似性度量,并基于目标的特征区域进行快速相关匹配,从可能区域中提取出目标。该算法通过精确建立初始模板和由粗到精的目标搜索策略,既保证了目标提取的精度、速度,又能对各种噪声干扰有较强的抑制。
⑤对跟踪系统软、硬件平台的实现技术进行了研究。设计了以DSP为核心,结合PC104嵌入式计算机的双处理器并行处理硬件平台;并给出了嵌入式计算机和图像采集处理板的
In the future local war of high technology, people on the armored vehicle must processabundant information in the moment of battling against the enemy target, so an automatic targettracking system is needed which hangs sensors, processor and display and so on together. Such asystem should extract the target from complicated and chaotic background of scatteringdisturbance quickly and reliably, thereby people on vehicle can react to the enemy target asquickly as possible. However, the working condition of armored vehicle is abominable andmultiplicate, the targets are diversified, and the tracking system is sensitive to the platform’s vibration. All these things have caused great difficulty in developing image tracking system onarmored vehicle.
This paper probes into the technical difficulties in the application of image tracking systemon armored vehicle, and studies on the target detection, recognition and tracking techniques onvehicle. It also investigates the realizing technology of image tracking system on vehicle, andaccomplishes the development task of corresponding project.
The primaryresearch of this paper includes:
①Setting up the tracking theory of image tracking system on armored vehicle. First, thepaper constructs the system’s mathematical model and brings out the tracking equation according to the analysis of system task and tactics-technology index. Second, it divides the state of systemin order to solve the tracking equation, and constructs the basic function structure of systembased on the description of each working state. By analyzing the system’s basic theory, this paperpoints out the system difficultyand our study emphasis.
②Putting forward a real-time electronic image stabilizing algorithm (EIS) in allusion to thedisturbance to image sequence by vehicle vibration. First, it delves into the key technique of EIS—image registration, and presents an effective registration algorithm which is from coarse toprecise and form local to global. Second, it applies recursive Kalman filtering technique inmotion filtering of registration parameters and makes motion compensation for practical image.Finally, it takes advantage of mosaicking to reconstruct undefined regions to avoid theubiquitous information missing and image degradation. This algorithm has high precision as wellas high speed.
③Bringing forward an intelligent decision method of image segmentation based on roughset theory to make the system automatically select segmentation algorithm in simple scenes.Firstly, it selects some representative segmentation algorithms to make up of an algorithm library,which is used to process kinds of sample images; secondly, it makes the decision informationtable utilizing diversified numerical features extracted from the sample images and the optimalsegmentation algorithm of each sample image according to segmentation quality evaluationcriterion; finally, it applies rough set theory on discretization and attribution reduction of
本文探讨了图像跟踪系统用于装甲战车所存在的技术难点,研究了车载环境下目标的检测识别与跟踪技术,并进一步研究了装甲战车图像跟踪系统的实现技术,完成了相应工程项目的研制任务。
本文的研究工作包括以下几个部分:
①建立了装甲战车图像跟踪系统的跟踪理论。首先,根据对系统任务及战术技术指标的分析,建立了系统的数学模型并给出了系统的跟踪方程;然后,通过探讨如何求解该跟踪方程,将系统进行状态划分,并根据各个工作状态的描述,建立了系统的基本功能结构。论文通过分析系统的基本理论,指出系统的难点和本课题研究的重点。
②针对车体振动对图像序列带来的干扰问题,提出了一种基于特征匹配的实时电子稳像算法。首先,对电子稳像中关键环节——图像配准技术进行了深入研究,给出一种由粗到精、由局部到全局的高效配准算法;接着,采用了递归Kalman滤波技术对配准参数进行运动滤波并对实际图像进行运动补偿;最后,利用了图像拼接技术进行“无定义区”重建,避免了普遍存在的信息丢失和图像降质问题。该算法在保证实时性的同时,具有很高的稳像精度。
③为了使系统在简单场景下能够通过自动选取分割算法来提取目标,提出了一种基于粗糙集理论的图像分割智能决策方法。首先选取若干具代表性的分割算法构成算法库,并用它们对各种样本图像进行分割;然后利用从样本图像中提取出来的各种数值特征,并根据图像分割质量评价标准评判出各样本图像的最优分割算法,用其构成决策信息表;最后应用粗糙集理论来对决策信息表进行离散化处理和属性约简,以生成图像分割算法选取的决策规则。该决策方法能比较有效地根据系统所处理图像特征选取出算法库中最优的分割算法,并可满足系统的实时性要求。
④提出了一种综合运用分形和特征匹配等技术,将复杂场景中目标提取出来的方法。首先,对传统的Snake模型进行改进,并将其应用到初始模板的建立中;然后,引入分形布朗随机场模型,利用分形维数和分形拟合误差确定可能的目标区域;最后,定义了一种新的最小失配距离(MMD)相似性度量,并基于目标的特征区域进行快速相关匹配,从可能区域中提取出目标。该算法通过精确建立初始模板和由粗到精的目标搜索策略,既保证了目标提取的精度、速度,又能对各种噪声干扰有较强的抑制。
⑤对跟踪系统软、硬件平台的实现技术进行了研究。设计了以DSP为核心,结合PC104嵌入式计算机的双处理器并行处理硬件平台;并给出了嵌入式计算机和图像采集处理板的
In the future local war of high technology, people on the armored vehicle must processabundant information in the moment of battling against the enemy target, so an automatic targettracking system is needed which hangs sensors, processor and display and so on together. Such asystem should extract the target from complicated and chaotic background of scatteringdisturbance quickly and reliably, thereby people on vehicle can react to the enemy target asquickly as possible. However, the working condition of armored vehicle is abominable andmultiplicate, the targets are diversified, and the tracking system is sensitive to the platform’s vibration. All these things have caused great difficulty in developing image tracking system onarmored vehicle.
This paper probes into the technical difficulties in the application of image tracking systemon armored vehicle, and studies on the target detection, recognition and tracking techniques onvehicle. It also investigates the realizing technology of image tracking system on vehicle, andaccomplishes the development task of corresponding project.
The primaryresearch of this paper includes:
①Setting up the tracking theory of image tracking system on armored vehicle. First, thepaper constructs the system’s mathematical model and brings out the tracking equation according to the analysis of system task and tactics-technology index. Second, it divides the state of systemin order to solve the tracking equation, and constructs the basic function structure of systembased on the description of each working state. By analyzing the system’s basic theory, this paperpoints out the system difficultyand our study emphasis.
②Putting forward a real-time electronic image stabilizing algorithm (EIS) in allusion to thedisturbance to image sequence by vehicle vibration. First, it delves into the key technique of EIS—image registration, and presents an effective registration algorithm which is from coarse toprecise and form local to global. Second, it applies recursive Kalman filtering technique inmotion filtering of registration parameters and makes motion compensation for practical image.Finally, it takes advantage of mosaicking to reconstruct undefined regions to avoid theubiquitous information missing and image degradation. This algorithm has high precision as wellas high speed.
③Bringing forward an intelligent decision method of image segmentation based on roughset theory to make the system automatically select segmentation algorithm in simple scenes.Firstly, it selects some representative segmentation algorithms to make up of an algorithm library,which is used to process kinds of sample images; secondly, it makes the decision informationtable utilizing diversified numerical features extracted from the sample images and the optimalsegmentation algorithm of each sample image according to segmentation quality evaluationcriterion; finally, it applies rough set theory on discretization and attribution reduction of
引文
[1] 董志荣. 现代舰载作战系统(上册) . 北京: 兵器工业出版社, 1989.
[2] 蒋谱成. 电视跟踪在火控雷达中的地位和作用. 雷达, 1987, 3:44-49.
[3] 郭治. 现代火控理论. 北京: 国防工业出版社, 1996.
[4] 舰载机起飞与着舰技术. 中国航空工业总公司, 1994.
[5] 三光合一的光电跟踪仪. 现代军事, 1992, 2:78-80.
[6] Maheu XJ. Video-rate Stabilization System. SPIE, 1998, 3414:232-238.
[7] Censi A. Image Stabilization by Feature Tracking. 10th International Conference on Image Analysis andProcessing, 1999, 665-667.
[8] 沈宏海, 刘晶红, 贾平, 等. 摄像稳定技术. 光学 精密工程, 2001, 9(2):115-119.
[9] Gilbert AL, Giles MK, and Flachs GM, et al. A Real-Time Video Tracking System. IEEE Trans. PatternAnalysis and Machine Intelligence, 1980, 2(1):47-56.
[10] Schaming WB. Adaptive Gate Multifeature Bayesian Statistical Tracker. Proceedings of SPIE, 1982,359:68-76.
[11] Ghosh A, Pal NR, and Pal SK. Self-Organization for Object Extraction Using Multilayer Neural Networksand Fuzziness Measure. IEEE Trans. Fuzzy System, 1993, 1(1):54-68.
[12] Henk J, Heijmans AM. Connected Morphological Operator for Binary Images. Computer Vision and ImageUnderstanding, 1999, 73(1):99-120.
[13] Montera DA, Rogers SK, and Runck DW, et al. Object Tracking Through Adaptive Correlation. OpticalEngineering, 1994, 33(1):294-302.
[14] Parry HS, Marshall AD, and Markham K. Tracking Targets in FLIR Images by Region Template Correlation.Proceedings of SPIE, 3086:221-232.
[15] 潘仲明, 王跃科, 杨俊. 现代测控理论基础. 长沙: 国防科技大学出版社, 2003.
[16] 王启才. 机动目标估值与跟踪. 华东工学院电子工程系资料. 1980.
[17] Clark BL. The Development of an Adaptive kalman Target Tracking Filter. AIAA Guidance and ControlConference, 1976, 8:365–382.
[18] 郭旭平. 任意指定图像目标实时高速识别跟踪系统技术研究与实现. 电子科技大学博士论文, 1998, 6.
[19] 魏波. 点时空约束图像目标跟踪理论与实时实现技术研究. 电子科技大学博士论文, 2000, 12
[20] 郑江滨. 视频监视方法研究. 西北工业大学博士学位论文, 2002.
[21] Brown LG. A Survey of Image Registration Technique. ACM Computing Survays, 1992, 24(4):325-376.
[22] Herbin M, Venot A, and Devaux JY, et al. Automated Registration of Dissimilar Images: Application toMedical Imagery. Computer Vision, Graphics, and Image Processing, 1989, 47:77-88.
[23] Merickel M. 3D Reconstruction: The Registration Problem. Computer Vision, Graphics, and ImageProcessing, 1988, 42:206-219.
[24] Chen SW, Jain AK. Strategies of Multi-view and Multi-matching for 3D Object Recognition. ComputerVision, Graphics, and Image Processing, 1993, 57(1):121-130.
[25] Bergevin R, SoucyM, and Gagnon H, et al. Towards a General Multi-view Registration Technique. IEEETransaction on Pattern Analysis and Machine Intelligence, 1996, 18(5):540-547.
[26] Weng J, Ahuja N, and Huang TS. Matching Two Perspective Views. IEEE Transaction on Pattern Analysisand Machine Intelligence, 1992, 8(8):806-825.
[27] 罗诗途, 张玘, 罗飞路. 车载图像跟踪系统中电子稳像算法的研究. 光学 精密工程, 2005,13(1):95-103.
[28] Carlo Tomasi, Takeo Kanade. Detection and Tracking of Point Features. Carnegic Mellon UniversityTechnical Report CMU-CS-91-132, 1991.
[29] Shi Jianbo, Carlo Tomasi. Good Features to Track. IEEE Conference on Computer Vision and PatternRecognition, 1994, 593-600.
[30] 刘哲星, 李树祥. 基于联合直方图区域记数的时间序列图象自动配准方法. 中国图象图形学报, 2002,7(A)(5):450-456.
[31] 罗诗途, 张玘, 罗飞路. 车载图像稳定算法中关键技术的实现. 光电工程, 2005, 32(5):16-20.
[32] Mark Mc Donnell. B.A. (Mod.) Computer Science. Final Year Project, 2004.
[33] Frederik Maes, Andre Collignon. Multimodality Image Registration by Maximization of Mutual Information.IEEE Transaction on Medical Imaging, 2000, 16(2):187-198.
[34] PluimJPW, Maintz JBA,Viergever MA. Interpolation Artifacts in Mutual Information-Based ImageRegistration. Computer Vision and Image Understanding, 2000, 77:211-232.
[35] Press WH, Teukolsky SA, and Vetterling WT. C 语言数值算法程序大全(第二版). 傅祖芸, 丁岩等译. 北京: 电子工业出版社, 1995, 350-356.
[36] 罗诗途, 张玘, 罗飞路. 一种基于特征匹配的实时电子稳像算法. 国防科技大学学报, 2005,27(3):45-48.
[37] Andrew Litvin, Janusz Konrad, and WilliamCK. Probabilistic Video Stabilization Using Kalman Filteringand Mosaicking. IS&T/SPIE Symposium on Electronic Imaging, Image and Video Communications andProc., 2003, Jan. 20-24.
[38] Kwong Kin Wah, Eric. Video Stabilization Algorithms. ELEC 533 Project Report, Spring 2003.
[39] 钟平, 于前洋, 金光. 基于特征点匹配技术的运动估计及补偿方法. 光电子 激光, 2004, 15(1):73-77.
[40] 宋永江, 夏良正, 杨世周. 多直线全局运动估计及其在图像稳定中的应用. 东南大学学报, 2002,32(2):211-217.
[41] 杨海波, 姚庆栋, 荆仁杰. 一种自然场景中的目标分割方法. 中国图象图形学报, 1998, 3(8):646-650.
[42] 章毓晋, 罗惠韬. 基于评价知识的图像分割算法优选系统[J]. 高技术通讯, 1998, 8(4):21~24.
[43] Marie Pierre Dubuisson Jolly, Sridhar Lakshmanan, and Anil K. Jain. Vehicle Segmentation andClassification Using Deformable Templates. IEEE Trans. Pattern Analysis and Machine Intelligence, 1996,18(3):293-3086.
[44] 薛景浩, 章毓晋, 林行刚. SAR 图像基于 Rayleigh 分布假设的最小误差阈值化分割. 电子科学学刊,1999, 21(2):219-225.
[45] Tian B, Shaikh MA, and Azimi Sadjadi MR, et al. A Study of Cloud Classification with Neural NetworksUsing Spectral and Textural Features. IEEE Trans. Neural Networks, 1999, 10(1):138-151.
[46] 陈哲, 冯天谨. 基于小波分形特征提取的图像分割方法. 中国图象图形学报, 1999, 4(A)(12):1072-1077.
[47] Zhang Y, Smith SM, and Brady JM. Segmentation of Brain MR Images Using Markov RandomField.Proceedings of Medical Image Understanding and Analysis’99.
[48] Swanson MD, Tewfik AH. Fast Progressively Refined Image Retrieval. Journal of Electronic Imaging, 1998,7(3):443-452.
[49] 蔡忠闽, 管晓宏, 邵萍 等. 基于粗糙集理论的入侵检测新方法. 计算机学报, 2003, 26(3):361-366.
[50] 张文修, 吴伟志, 梁吉业 等. 粗糙集理论与方法[M]. 北京: 科学出版社, 2001
[51] Tsai W. Moment-preserving Thresholding: A New Approach, CVGIP. 1985, 29:377-393.
[52] Wu AY, Rosenfeld A. Threshold Selection Using Quad Tree. IEEE Trans. on Pattern Anal. Mach. Intel.1982, 4:90-94.
[53] Ostu NA. Threshold Selection Method fromGray-level Histograms. IEEE Trans. on System, Man, andCybernetics, 1979, 9(1):62-66.
[54] Kapur J, Sahop P, and Wong A. A New Method for Grey-level Picture Thresholding Using the Entropy ofthe Histogram. Computer Vision Graphics, and Image Processing, 1985, 29:210-239.
[55] Kittler J, Illingworth J. MinimumError Thresholding. Pattern Recognition, 1986, 19:41-47.
[56] Shitu Luo, Qi Zhang, Feilu Luo. An improved moment-preserving auto threshold image segmentationalgorithm. Proceedings of 2004 International Conference on Information Acquisition, 2004, 316-318.
[57] 孙即祥. 数字图像处理[M]. 石家庄: 河北教育出版社, 1993.
[58] 徐立中. 数字图像的智能信息处理. 北京: 国防工业出版社, 2001.
[59] 罗惠韬, 章毓晋. 基于算法评价的分割算法优化思想及其系统实现. 电子科学学刊, 1998,20(5):577-583.
[60] Shareef N, Wang DL, and Yagel R. Segmentation of Medical Images Using Legion. IEEE Trans. MedicalImaging, 1999, 18(1):74-91.
[61] 尹屏, 王润生. 基于边缘信息的分开合并图象分割方法. 中国图象图形学报, 1998, 3(6):450-454.
[62] Felzenszwalb PF, Huttenlocher DP. Efficiently Computing a Good Segmentation. Available onhttp://www.cs.cornell.edu/vision/segmentation.
[63] Sahoo PK, Soltani S, and Wong AKC, et al. A Survey of Thresholding Techniques. CVGIP, 1988,41:233-260.
[64] 侯格贤, 毕笃彦, 吴成柯. 图象分割质量评价方法研究. 中国图象图形学报, 2000, 5(A)(1):40-43.
[65] 王润生. 图像理解, 2th. 国防科技大学出版社. 1998.
[66] 章毓晋. 图象分割评价技术分类和比较. 中国图象图形学报, 1996, 1(2):151-158.
[67] Dougherty J, Kohavi R, and Sahami M. Supervised and Unsupervised Discretization of Continuous Features.Preiditis A, Russel S. Proceedings Twelfth International Conference on Machine Learning. San Francisco,California: Morgan Kaufmann Publishers, 1995, 194-202.
[68] Holte R C. Very Simple Classification Rules PerformWell on Most Commonly Used Datasets. MachineLearning, 1993, 11:63-90.
[69] Richeldi M, Rossotto M. Class-Driven Statistical Discretization of Continuous Attributes (Extended Abstract)In: N Lavrac &.S. Wrobel, eds, Machine Learning: ECML-95, Lecture Notes in Artificial Intelligence 914,Spinger Verlag. Berlin, Heidelberg ,NewYork, 1995, 335-338.
[70] Chmielewski M R, Grzymala-Busse J W. Global Discretization of Attributes as Per-Processing for MachineLearning. Proc of the III International Workshop on RSSC94. 1994, 294-301.
[71] Dougherty J, Kohavi R, and Sahami M. Supervised and Unsupervised Discretization of Continuous Features.Proceedings of the Twelfth International Conference on Machine Learning .Morgan Kaufmann, Publishers,San Francisco, CA, 1995, 194-202.
[72] 张文宇, 贾嵘 等. 知识发现过程中连续属性离散化方法研究. 西安理工大学学报, 2002,18(3):249-253.
[73] Vinterbo S, ?hrn A. Minimal Approximate Hitting Sets and Rule Templates. International Journal ofApproximate Reasoning, 2000, 25(2):123-143.
[74] Ohrn A, Komorowski J. ROSETTA: A Rough Set Toolkit for Analysis of Data. Third International JointConference on Information Sciences, Fifth International Workshop on Rough Sets and Soft Computing(RSSC’97), Durham, NC, USA, 1997, 3:403-407.
[75] 刘永, 戴礼荣, 宋彦. 一种静态背景下的运动目标提取算法. 中国图象图形学报, 2003, 8(A)(7):759-763.
[76] 朱仲杰, 蒋刚毅, 郁梅, 等. 一种基于时空信息的运动目标提取新算法. 中国图象图形学报, 2003,8(A)(4): 422-426.
[77] Huang J, Liu S, and Hayes M. A Multi-frame Pel-recursive Algorithm for Varying Frame-to-frameDisplacement Estimation. IEEE ICA SSP, 1992, 3:242-244.
[78] Montera DA, Rogers SK, and Runck DW, et al. Object Tracking through Adaptive Correlation. OpticalEngineering, 1994, 33(1):294-302.
[79] Parry HS, Marshall AD, and Markham KC. Tracking Targets in FLIR Images by Region TemplateCorrelation. SPIE Vol.3066.
[80] 任仙怡, 廖云涛. 一种新的相关跟踪方法的研究. 中国图象图形学报, 2002, 7(5): 553~557.
[81] Cohen F S, Fan Z. Maximum Likelihood Unsupervised Textured Image Segmentation. CVGIP, 1992,54(3):239-247.
[82] Mallat S. Wavelets for a Vision. Proc. Of the IEEE, April, 1996, 84:604-615.
[83] Reed Todd. A Review of Recent Texture Segmentation and Feature Extraction Techniques. CVGIP ImageUnderstanding, 1993, 57(3):359-367.
[84] Stein M C. Fractal Image Models and Object Detection. Visual Communication and Image Processing II.SPIE, 1987, 845:293-300.
[85] Peli T. Multiscale Fractal Theory and Object Characterization. Opt. Soc. of Amer, 1990, 7(6):1101-1112.
[86] 杨波, 徐光, 朱志刚. 基于分形特征的自然景物图象分割方法. 中国图象图形学报, 1999, 4(A)(1):7-12.
[87] Luo Shitu, Zhang Qi, Luo Feilu. Image Tracking Method Based on Fractal-geometry Edge Extraction.ISIST’2004. 2004, 9.
[88] Pentland AP. Fractal Based Description of Natural Scenes. IEEE Trans. On Pattern Analysis and MachineIntelligence, 1984, 6(6):661-674.
[89] Michael Kass, Andrew Witkin, and Demetri Terzopoulos. Snakes: Active Contour Models. InternationalJournal of Computer Vision, 1987, 1:321-331
[90] Cohen LD. On active contour models and balloons. CVGIP: Image Understanding, 1991, 53(2):211-218.
[91] Cohen LD, Cohen I. Finite-element Methods for Active Contour Models and Balloons for 2-D and 3-DImages. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11):1131-1147.
[92] Xu Chen-Yang, Prince Jerry L. Snakes, Shapes, and Gradient Vector Flow. IEEE Transactions on ImageProcessing, 1998, 7(3):359-369.
[93] 侯志强, 韩崇昭. 基于力场分析的主动轮廓模型. 计算机学报, 2004, 27(6):743-749.
[94] Smith S, Brady M. A New Approach to Low Level Image Processing. IJCV, 1997, 23(1):45-78.
[95] 马波, 裘正定. 小波变换的分形特性. 铁道学报, 1997, 16(3):74-80.
[96] 王思贤, 江筱炳, 廖孟扬. 基于小波变换及布朗分形模型的纹理分割. 武汉大学学报, 1998,44(1):118-120.
[97] 杨斌利, 向健勇, 韩建栋. 一种新的基于分形特征的人造目标快速检测算法. 激光与红外, 2003,33(5):374-376.
[98] Barnea DI, Silverman HF. A Class of Algorithms for Fast Digital Image Registration. IEEE Trans.Computers, 1972, 21:179-186.
[99] 罗诗途, 张玘, 罗飞路. 基于自适应模板修正的相关跟踪方法, 仪器仪表学报. 2004, 25(4):633-635.
[100] Ashraf Elnagar, Kamal Gupta. Motion Prediction of Moving Objects Based on Autoregressive Model.SMC-A, 1998, 28(6): 803-810.
[101] 罗诗途, 张玘, 罗飞路. 基于 TMS320C6202 的装甲战车智能图像跟踪系统硬件平台设计. 电子技术应用, 2005, 31(3):29-32.
[2] 蒋谱成. 电视跟踪在火控雷达中的地位和作用. 雷达, 1987, 3:44-49.
[3] 郭治. 现代火控理论. 北京: 国防工业出版社, 1996.
[4] 舰载机起飞与着舰技术. 中国航空工业总公司, 1994.
[5] 三光合一的光电跟踪仪. 现代军事, 1992, 2:78-80.
[6] Maheu XJ. Video-rate Stabilization System. SPIE, 1998, 3414:232-238.
[7] Censi A. Image Stabilization by Feature Tracking. 10th International Conference on Image Analysis andProcessing, 1999, 665-667.
[8] 沈宏海, 刘晶红, 贾平, 等. 摄像稳定技术. 光学 精密工程, 2001, 9(2):115-119.
[9] Gilbert AL, Giles MK, and Flachs GM, et al. A Real-Time Video Tracking System. IEEE Trans. PatternAnalysis and Machine Intelligence, 1980, 2(1):47-56.
[10] Schaming WB. Adaptive Gate Multifeature Bayesian Statistical Tracker. Proceedings of SPIE, 1982,359:68-76.
[11] Ghosh A, Pal NR, and Pal SK. Self-Organization for Object Extraction Using Multilayer Neural Networksand Fuzziness Measure. IEEE Trans. Fuzzy System, 1993, 1(1):54-68.
[12] Henk J, Heijmans AM. Connected Morphological Operator for Binary Images. Computer Vision and ImageUnderstanding, 1999, 73(1):99-120.
[13] Montera DA, Rogers SK, and Runck DW, et al. Object Tracking Through Adaptive Correlation. OpticalEngineering, 1994, 33(1):294-302.
[14] Parry HS, Marshall AD, and Markham K. Tracking Targets in FLIR Images by Region Template Correlation.Proceedings of SPIE, 3086:221-232.
[15] 潘仲明, 王跃科, 杨俊. 现代测控理论基础. 长沙: 国防科技大学出版社, 2003.
[16] 王启才. 机动目标估值与跟踪. 华东工学院电子工程系资料. 1980.
[17] Clark BL. The Development of an Adaptive kalman Target Tracking Filter. AIAA Guidance and ControlConference, 1976, 8:365–382.
[18] 郭旭平. 任意指定图像目标实时高速识别跟踪系统技术研究与实现. 电子科技大学博士论文, 1998, 6.
[19] 魏波. 点时空约束图像目标跟踪理论与实时实现技术研究. 电子科技大学博士论文, 2000, 12
[20] 郑江滨. 视频监视方法研究. 西北工业大学博士学位论文, 2002.
[21] Brown LG. A Survey of Image Registration Technique. ACM Computing Survays, 1992, 24(4):325-376.
[22] Herbin M, Venot A, and Devaux JY, et al. Automated Registration of Dissimilar Images: Application toMedical Imagery. Computer Vision, Graphics, and Image Processing, 1989, 47:77-88.
[23] Merickel M. 3D Reconstruction: The Registration Problem. Computer Vision, Graphics, and ImageProcessing, 1988, 42:206-219.
[24] Chen SW, Jain AK. Strategies of Multi-view and Multi-matching for 3D Object Recognition. ComputerVision, Graphics, and Image Processing, 1993, 57(1):121-130.
[25] Bergevin R, SoucyM, and Gagnon H, et al. Towards a General Multi-view Registration Technique. IEEETransaction on Pattern Analysis and Machine Intelligence, 1996, 18(5):540-547.
[26] Weng J, Ahuja N, and Huang TS. Matching Two Perspective Views. IEEE Transaction on Pattern Analysisand Machine Intelligence, 1992, 8(8):806-825.
[27] 罗诗途, 张玘, 罗飞路. 车载图像跟踪系统中电子稳像算法的研究. 光学 精密工程, 2005,13(1):95-103.
[28] Carlo Tomasi, Takeo Kanade. Detection and Tracking of Point Features. Carnegic Mellon UniversityTechnical Report CMU-CS-91-132, 1991.
[29] Shi Jianbo, Carlo Tomasi. Good Features to Track. IEEE Conference on Computer Vision and PatternRecognition, 1994, 593-600.
[30] 刘哲星, 李树祥. 基于联合直方图区域记数的时间序列图象自动配准方法. 中国图象图形学报, 2002,7(A)(5):450-456.
[31] 罗诗途, 张玘, 罗飞路. 车载图像稳定算法中关键技术的实现. 光电工程, 2005, 32(5):16-20.
[32] Mark Mc Donnell. B.A. (Mod.) Computer Science. Final Year Project, 2004.
[33] Frederik Maes, Andre Collignon. Multimodality Image Registration by Maximization of Mutual Information.IEEE Transaction on Medical Imaging, 2000, 16(2):187-198.
[34] PluimJPW, Maintz JBA,Viergever MA. Interpolation Artifacts in Mutual Information-Based ImageRegistration. Computer Vision and Image Understanding, 2000, 77:211-232.
[35] Press WH, Teukolsky SA, and Vetterling WT. C 语言数值算法程序大全(第二版). 傅祖芸, 丁岩等译. 北京: 电子工业出版社, 1995, 350-356.
[36] 罗诗途, 张玘, 罗飞路. 一种基于特征匹配的实时电子稳像算法. 国防科技大学学报, 2005,27(3):45-48.
[37] Andrew Litvin, Janusz Konrad, and WilliamCK. Probabilistic Video Stabilization Using Kalman Filteringand Mosaicking. IS&T/SPIE Symposium on Electronic Imaging, Image and Video Communications andProc., 2003, Jan. 20-24.
[38] Kwong Kin Wah, Eric. Video Stabilization Algorithms. ELEC 533 Project Report, Spring 2003.
[39] 钟平, 于前洋, 金光. 基于特征点匹配技术的运动估计及补偿方法. 光电子 激光, 2004, 15(1):73-77.
[40] 宋永江, 夏良正, 杨世周. 多直线全局运动估计及其在图像稳定中的应用. 东南大学学报, 2002,32(2):211-217.
[41] 杨海波, 姚庆栋, 荆仁杰. 一种自然场景中的目标分割方法. 中国图象图形学报, 1998, 3(8):646-650.
[42] 章毓晋, 罗惠韬. 基于评价知识的图像分割算法优选系统[J]. 高技术通讯, 1998, 8(4):21~24.
[43] Marie Pierre Dubuisson Jolly, Sridhar Lakshmanan, and Anil K. Jain. Vehicle Segmentation andClassification Using Deformable Templates. IEEE Trans. Pattern Analysis and Machine Intelligence, 1996,18(3):293-3086.
[44] 薛景浩, 章毓晋, 林行刚. SAR 图像基于 Rayleigh 分布假设的最小误差阈值化分割. 电子科学学刊,1999, 21(2):219-225.
[45] Tian B, Shaikh MA, and Azimi Sadjadi MR, et al. A Study of Cloud Classification with Neural NetworksUsing Spectral and Textural Features. IEEE Trans. Neural Networks, 1999, 10(1):138-151.
[46] 陈哲, 冯天谨. 基于小波分形特征提取的图像分割方法. 中国图象图形学报, 1999, 4(A)(12):1072-1077.
[47] Zhang Y, Smith SM, and Brady JM. Segmentation of Brain MR Images Using Markov RandomField.Proceedings of Medical Image Understanding and Analysis’99.
[48] Swanson MD, Tewfik AH. Fast Progressively Refined Image Retrieval. Journal of Electronic Imaging, 1998,7(3):443-452.
[49] 蔡忠闽, 管晓宏, 邵萍 等. 基于粗糙集理论的入侵检测新方法. 计算机学报, 2003, 26(3):361-366.
[50] 张文修, 吴伟志, 梁吉业 等. 粗糙集理论与方法[M]. 北京: 科学出版社, 2001
[51] Tsai W. Moment-preserving Thresholding: A New Approach, CVGIP. 1985, 29:377-393.
[52] Wu AY, Rosenfeld A. Threshold Selection Using Quad Tree. IEEE Trans. on Pattern Anal. Mach. Intel.1982, 4:90-94.
[53] Ostu NA. Threshold Selection Method fromGray-level Histograms. IEEE Trans. on System, Man, andCybernetics, 1979, 9(1):62-66.
[54] Kapur J, Sahop P, and Wong A. A New Method for Grey-level Picture Thresholding Using the Entropy ofthe Histogram. Computer Vision Graphics, and Image Processing, 1985, 29:210-239.
[55] Kittler J, Illingworth J. MinimumError Thresholding. Pattern Recognition, 1986, 19:41-47.
[56] Shitu Luo, Qi Zhang, Feilu Luo. An improved moment-preserving auto threshold image segmentationalgorithm. Proceedings of 2004 International Conference on Information Acquisition, 2004, 316-318.
[57] 孙即祥. 数字图像处理[M]. 石家庄: 河北教育出版社, 1993.
[58] 徐立中. 数字图像的智能信息处理. 北京: 国防工业出版社, 2001.
[59] 罗惠韬, 章毓晋. 基于算法评价的分割算法优化思想及其系统实现. 电子科学学刊, 1998,20(5):577-583.
[60] Shareef N, Wang DL, and Yagel R. Segmentation of Medical Images Using Legion. IEEE Trans. MedicalImaging, 1999, 18(1):74-91.
[61] 尹屏, 王润生. 基于边缘信息的分开合并图象分割方法. 中国图象图形学报, 1998, 3(6):450-454.
[62] Felzenszwalb PF, Huttenlocher DP. Efficiently Computing a Good Segmentation. Available onhttp://www.cs.cornell.edu/vision/segmentation.
[63] Sahoo PK, Soltani S, and Wong AKC, et al. A Survey of Thresholding Techniques. CVGIP, 1988,41:233-260.
[64] 侯格贤, 毕笃彦, 吴成柯. 图象分割质量评价方法研究. 中国图象图形学报, 2000, 5(A)(1):40-43.
[65] 王润生. 图像理解, 2th. 国防科技大学出版社. 1998.
[66] 章毓晋. 图象分割评价技术分类和比较. 中国图象图形学报, 1996, 1(2):151-158.
[67] Dougherty J, Kohavi R, and Sahami M. Supervised and Unsupervised Discretization of Continuous Features.Preiditis A, Russel S. Proceedings Twelfth International Conference on Machine Learning. San Francisco,California: Morgan Kaufmann Publishers, 1995, 194-202.
[68] Holte R C. Very Simple Classification Rules PerformWell on Most Commonly Used Datasets. MachineLearning, 1993, 11:63-90.
[69] Richeldi M, Rossotto M. Class-Driven Statistical Discretization of Continuous Attributes (Extended Abstract)In: N Lavrac &.S. Wrobel, eds, Machine Learning: ECML-95, Lecture Notes in Artificial Intelligence 914,Spinger Verlag. Berlin, Heidelberg ,NewYork, 1995, 335-338.
[70] Chmielewski M R, Grzymala-Busse J W. Global Discretization of Attributes as Per-Processing for MachineLearning. Proc of the III International Workshop on RSSC94. 1994, 294-301.
[71] Dougherty J, Kohavi R, and Sahami M. Supervised and Unsupervised Discretization of Continuous Features.Proceedings of the Twelfth International Conference on Machine Learning .Morgan Kaufmann, Publishers,San Francisco, CA, 1995, 194-202.
[72] 张文宇, 贾嵘 等. 知识发现过程中连续属性离散化方法研究. 西安理工大学学报, 2002,18(3):249-253.
[73] Vinterbo S, ?hrn A. Minimal Approximate Hitting Sets and Rule Templates. International Journal ofApproximate Reasoning, 2000, 25(2):123-143.
[74] Ohrn A, Komorowski J. ROSETTA: A Rough Set Toolkit for Analysis of Data. Third International JointConference on Information Sciences, Fifth International Workshop on Rough Sets and Soft Computing(RSSC’97), Durham, NC, USA, 1997, 3:403-407.
[75] 刘永, 戴礼荣, 宋彦. 一种静态背景下的运动目标提取算法. 中国图象图形学报, 2003, 8(A)(7):759-763.
[76] 朱仲杰, 蒋刚毅, 郁梅, 等. 一种基于时空信息的运动目标提取新算法. 中国图象图形学报, 2003,8(A)(4): 422-426.
[77] Huang J, Liu S, and Hayes M. A Multi-frame Pel-recursive Algorithm for Varying Frame-to-frameDisplacement Estimation. IEEE ICA SSP, 1992, 3:242-244.
[78] Montera DA, Rogers SK, and Runck DW, et al. Object Tracking through Adaptive Correlation. OpticalEngineering, 1994, 33(1):294-302.
[79] Parry HS, Marshall AD, and Markham KC. Tracking Targets in FLIR Images by Region TemplateCorrelation. SPIE Vol.3066.
[80] 任仙怡, 廖云涛. 一种新的相关跟踪方法的研究. 中国图象图形学报, 2002, 7(5): 553~557.
[81] Cohen F S, Fan Z. Maximum Likelihood Unsupervised Textured Image Segmentation. CVGIP, 1992,54(3):239-247.
[82] Mallat S. Wavelets for a Vision. Proc. Of the IEEE, April, 1996, 84:604-615.
[83] Reed Todd. A Review of Recent Texture Segmentation and Feature Extraction Techniques. CVGIP ImageUnderstanding, 1993, 57(3):359-367.
[84] Stein M C. Fractal Image Models and Object Detection. Visual Communication and Image Processing II.SPIE, 1987, 845:293-300.
[85] Peli T. Multiscale Fractal Theory and Object Characterization. Opt. Soc. of Amer, 1990, 7(6):1101-1112.
[86] 杨波, 徐光, 朱志刚. 基于分形特征的自然景物图象分割方法. 中国图象图形学报, 1999, 4(A)(1):7-12.
[87] Luo Shitu, Zhang Qi, Luo Feilu. Image Tracking Method Based on Fractal-geometry Edge Extraction.ISIST’2004. 2004, 9.
[88] Pentland AP. Fractal Based Description of Natural Scenes. IEEE Trans. On Pattern Analysis and MachineIntelligence, 1984, 6(6):661-674.
[89] Michael Kass, Andrew Witkin, and Demetri Terzopoulos. Snakes: Active Contour Models. InternationalJournal of Computer Vision, 1987, 1:321-331
[90] Cohen LD. On active contour models and balloons. CVGIP: Image Understanding, 1991, 53(2):211-218.
[91] Cohen LD, Cohen I. Finite-element Methods for Active Contour Models and Balloons for 2-D and 3-DImages. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11):1131-1147.
[92] Xu Chen-Yang, Prince Jerry L. Snakes, Shapes, and Gradient Vector Flow. IEEE Transactions on ImageProcessing, 1998, 7(3):359-369.
[93] 侯志强, 韩崇昭. 基于力场分析的主动轮廓模型. 计算机学报, 2004, 27(6):743-749.
[94] Smith S, Brady M. A New Approach to Low Level Image Processing. IJCV, 1997, 23(1):45-78.
[95] 马波, 裘正定. 小波变换的分形特性. 铁道学报, 1997, 16(3):74-80.
[96] 王思贤, 江筱炳, 廖孟扬. 基于小波变换及布朗分形模型的纹理分割. 武汉大学学报, 1998,44(1):118-120.
[97] 杨斌利, 向健勇, 韩建栋. 一种新的基于分形特征的人造目标快速检测算法. 激光与红外, 2003,33(5):374-376.
[98] Barnea DI, Silverman HF. A Class of Algorithms for Fast Digital Image Registration. IEEE Trans.Computers, 1972, 21:179-186.
[99] 罗诗途, 张玘, 罗飞路. 基于自适应模板修正的相关跟踪方法, 仪器仪表学报. 2004, 25(4):633-635.
[100] Ashraf Elnagar, Kamal Gupta. Motion Prediction of Moving Objects Based on Autoregressive Model.SMC-A, 1998, 28(6): 803-810.
[101] 罗诗途, 张玘, 罗飞路. 基于 TMS320C6202 的装甲战车智能图像跟踪系统硬件平台设计. 电子技术应用, 2005, 31(3):29-32.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |