内河在航船舶动态跟踪和航迹融合方法研究
|
摘要
随着我国内河航运的蓬勃发展,水上运输任务日益繁重。内河各港口的吞吐量急剧增加,船舶流量和船舶密度也不断加大,导致航运事故发生的风险加剧,对内河在航船舶的动态跟踪和实时监控显得尤为重要。近年来,船舶交通管理系统(VTS)中雷达、船舶自动识别系统(AIS)、电子海图信息显示系统(ECDIS)等智能化的监控设备在内河海事监管中得到积极应用。雷达是跟踪船舶的最佳选择,但是在盲区会失去跟踪能力且不能识别船舶类型；AIS可以提供船舶的动态、静态信息,可以较好地识别船舶类型,但是由于其安装成本较高,在内河总吨位300以下的中小船舶没有配备；安装价格便宜,技术成熟的视频监控技术可为监控内河船舶提供另一种手段,但是其只能在航道的有限范围内获得信息。因此,在探讨基于视频的内河在航船舶目标识别和跟踪方法的基础上,应用视频、AIS、雷达等三种方法对船舶轨迹进行融合,提高内河在航船舶跟踪的可靠性和准确性,这对内河在航船舶的实时监控具有重要的学术和应用价值。本文的主要工作和创新如下：
(1)基于视频的内河在航船舶目标识别方法研究：针对视频监控中运动目标的提取问题,提出一种基于改进相邻帧差法和Hu不变矩特征的运动目标识别方法。利用二维小波变换方法对采集到的视频图像进行去噪得到平滑的目标图像,采用连续帧间差分法处理图像得到运动区域,对当前帧目标进行Canny边缘检测得到边缘信息,两者检测结果相与得到运动目标边缘；提出一种改进的Hu不变矩目标图像特征提取方法提取目标图像的不变矩特征；设计一种基于优化权值附加动量因子的BP神经网络作为模式识别器,实现运动目标的自动识别。
(2)基于视频的内河在航船舶跟踪方法研究：针对目标的实时跟踪问题,结合内河船舶运动特性提出一种自适应带宽的Mean-shift目标跟踪算法,通过尺度检测的方法选择窗宽更新算法,解决了传统的基于Mean-shift目标跟踪算法中的固定核窗宽问题,可以随着运动目标尺寸的变化而变化,实现运动目标的实时跟踪,提高了目标跟踪的准确性和可靠性。
(3)视频、AIS、雷达轨迹融合方法研究：通过分析AIS、雷达两种系统采集的船舶信息特性,考虑AIS和雷达融合过程中所有可能出现的结果,建立船舶位置判定的识别框架。利用卡尔曼滤波算法对不同证据依据其重要性设置可信度,给出可信度公式,确定AIS和雷达的动态可信度,再用组合规则进行融合。然后应用获得的视频船舶运动轨迹对AIS、雷达融合结果进行修正,消除异常数据,得到更为准确的船舶运动轨迹,提高运动目标的识别率。
With the vigorous development in our country inland river shipping, water transport is becoming more and more arduous. As inland river ports throughput increased dramatically, ship traffic and shipping density also will continue to increase, which lead to a shipping accident risk is also increasing, it seems particularly important to dynamic tracking and real-time monitoring of inland river ships sailing. In recent years, vessel traffic management system (VTS) radar, automatic identification system (AIS), electronic chart display information system (ECDIS) and other intelligent monitoring equipment have been used in inland river is maritime supervision. The radar is the best choice in tracking the ship, but it will lose their tracking ability and can't identify the ship type in the blind zone; AIS can provide the ship dynamic and static information, but also can identify properly type of ship, because of its high cost of installation, in Inland River300tons of the following small ships not equipped it; with the mature technology of video monitoring technology, and install them cheap, makes up for the blank in the inland river ship real-time monitoring, which provides the possibility of a comprehensive monitoring of inland river ship, but it can only obtain the information in the limited channel.Therefore, this thesis fusion the navigation ship trajectory of the above three methods to improve the ship tracking precision, which based on the ship target recognition and tracking method, it has important acacemic and application value. The main work and innovation of this thesis is as follows:
1) The recognition method of inland waterway ships based on video
The thesis proposed a kind of moving target recognition method based on improvement of the adjacent frame and Hu moment invariants.At first; the2D wavelet transform was performed for filtering the noise. Then the moving targets are extracted by the Canny operator and the adjacent frame difference. An improved method of invariant moment's extraction is proposed to extract seven invariants characteristic value, and a BP neural network recognition algorithm based on optimizing the weights of additional momentum factor is designed. The sample of the torque characteristic value as input vector of neural network, and get accurate classification results, it is benefit the next target dynamic tracking.
2) The tracking method of inland waterway ships based on video
The thesis proposed an adaptive bandwidth mean-shift tracking algorithm and an update method of window width using scale detection. The window width can change follow the size of movement target, it solves the problem of fixed window width of the traditional mean-shift tracking algorithm, to achieve the goal of real-time tracking.
3) The Multi sensor information fusion of video, AIS and radar
After analyzing the ship information characteristics collected by AIS and radar, considering all possible result in the process of fusion two kinds of information, the thesis established a recognition framework of the ship location decision. It sets evidence credibility according to their importance using Kalman filter algorithm, gives a right credibility formula, determines the dynamic reliability of AIS and radar, and fuses all information by combination rules. Then revising the AIS and radar fusion results apply get the video of ship motion trajectory, to eliminate the abnormal data and get a more accurate ship motion trajectory and improve the moving target tracking accuracy.
(1)基于视频的内河在航船舶目标识别方法研究：针对视频监控中运动目标的提取问题,提出一种基于改进相邻帧差法和Hu不变矩特征的运动目标识别方法。利用二维小波变换方法对采集到的视频图像进行去噪得到平滑的目标图像,采用连续帧间差分法处理图像得到运动区域,对当前帧目标进行Canny边缘检测得到边缘信息,两者检测结果相与得到运动目标边缘；提出一种改进的Hu不变矩目标图像特征提取方法提取目标图像的不变矩特征；设计一种基于优化权值附加动量因子的BP神经网络作为模式识别器,实现运动目标的自动识别。
(2)基于视频的内河在航船舶跟踪方法研究：针对目标的实时跟踪问题,结合内河船舶运动特性提出一种自适应带宽的Mean-shift目标跟踪算法,通过尺度检测的方法选择窗宽更新算法,解决了传统的基于Mean-shift目标跟踪算法中的固定核窗宽问题,可以随着运动目标尺寸的变化而变化,实现运动目标的实时跟踪,提高了目标跟踪的准确性和可靠性。
(3)视频、AIS、雷达轨迹融合方法研究：通过分析AIS、雷达两种系统采集的船舶信息特性,考虑AIS和雷达融合过程中所有可能出现的结果,建立船舶位置判定的识别框架。利用卡尔曼滤波算法对不同证据依据其重要性设置可信度,给出可信度公式,确定AIS和雷达的动态可信度,再用组合规则进行融合。然后应用获得的视频船舶运动轨迹对AIS、雷达融合结果进行修正,消除异常数据,得到更为准确的船舶运动轨迹,提高运动目标的识别率。
With the vigorous development in our country inland river shipping, water transport is becoming more and more arduous. As inland river ports throughput increased dramatically, ship traffic and shipping density also will continue to increase, which lead to a shipping accident risk is also increasing, it seems particularly important to dynamic tracking and real-time monitoring of inland river ships sailing. In recent years, vessel traffic management system (VTS) radar, automatic identification system (AIS), electronic chart display information system (ECDIS) and other intelligent monitoring equipment have been used in inland river is maritime supervision. The radar is the best choice in tracking the ship, but it will lose their tracking ability and can't identify the ship type in the blind zone; AIS can provide the ship dynamic and static information, but also can identify properly type of ship, because of its high cost of installation, in Inland River300tons of the following small ships not equipped it; with the mature technology of video monitoring technology, and install them cheap, makes up for the blank in the inland river ship real-time monitoring, which provides the possibility of a comprehensive monitoring of inland river ship, but it can only obtain the information in the limited channel.Therefore, this thesis fusion the navigation ship trajectory of the above three methods to improve the ship tracking precision, which based on the ship target recognition and tracking method, it has important acacemic and application value. The main work and innovation of this thesis is as follows:
1) The recognition method of inland waterway ships based on video
The thesis proposed a kind of moving target recognition method based on improvement of the adjacent frame and Hu moment invariants.At first; the2D wavelet transform was performed for filtering the noise. Then the moving targets are extracted by the Canny operator and the adjacent frame difference. An improved method of invariant moment's extraction is proposed to extract seven invariants characteristic value, and a BP neural network recognition algorithm based on optimizing the weights of additional momentum factor is designed. The sample of the torque characteristic value as input vector of neural network, and get accurate classification results, it is benefit the next target dynamic tracking.
2) The tracking method of inland waterway ships based on video
The thesis proposed an adaptive bandwidth mean-shift tracking algorithm and an update method of window width using scale detection. The window width can change follow the size of movement target, it solves the problem of fixed window width of the traditional mean-shift tracking algorithm, to achieve the goal of real-time tracking.
3) The Multi sensor information fusion of video, AIS and radar
After analyzing the ship information characteristics collected by AIS and radar, considering all possible result in the process of fusion two kinds of information, the thesis established a recognition framework of the ship location decision. It sets evidence credibility according to their importance using Kalman filter algorithm, gives a right credibility formula, determines the dynamic reliability of AIS and radar, and fuses all information by combination rules. Then revising the AIS and radar fusion results apply get the video of ship motion trajectory, to eliminate the abnormal data and get a more accurate ship motion trajectory and improve the moving target tracking accuracy.
引文
[1]严忠贞,严新平,马枫,初秀民.绿色长江航运智能化信息服务系统及其关键技术研究[J].交通信息与安全,2010,(06)：76-81.
[2]孙文力,孙文强.船载自动识别系统[M].大连：大连海事大学出版社,2004.
[3]王世远,许开宇.AIS现状、前景及对策[J].航海技术,2001,,(05).
[4]长江海事局.长江海事局发展规划[Z],武汉：长江海事局,2005.
[5]朱雯瑾,廉清云RFID技术在内河船舶管理中的应用[J].中国水运(下半月刊),2010,(09).
[6]严新平,马枫,初秀民,陈晨.长江船舶交通流实时采集关键技术研究[J].中国航海,2010,33(02)：40-45.
[7]岳晋,贾小平,任光,曹辉.基于视频通信技术的船舶监管网络[J].大连海事大学学报,2006,32(2)：35-39.
[8]柳圣军.基于计算机视觉的内河航道智能监控系统的研究[D].杭州：浙江工业大学,2009.
[9]曹辉,张均东,宋威.视频技术在船舶领域中的研究与应用[J].船海工程,2007,21(3)：122-125.
[10]何乃甩,黄席樾,刘俊,权循宝.基于形态学重构的内河红外船舶目标检测[J].红外技术,2007,24(7)：419-424.
[11]李勇,周品,谭建军.基于AIS与GIS的船舶监控管理系统研究[J].微计算机信息,2007,23(6)：250-254.
[12]Torkild Eriksen, Gudrun HZye, BjZrn Narheim, Bente JenslZkken Meland. Maritime traffic monitoring using a space-basedAIS receiver [J]. Acta Astronautica 58 (2006):537-549.
[13]王晨熙,王晓博,朱靖,王国宏.雷达与AIS信息融合综述[J].指挥控制与仿真.2009,31(2)：14.
[14]郑芳,李赣华,蔡宣平.基于激光传感器的统计特征提取和误差分析[J].红外与激光工程,2006,35(6)：705-758.
[15]高岚,潘峰,张卉,廖云良.合成孔径雷达图像船舶自动检测新方法[J].船海工程,2006,18(4)：102-104.
[16]黄洪琼,汤天浩,金永兴,王天真.基于智能融合的船舶交通流预测系统[J].中国航海,2008,31(4)：364-367.
[17]John A. Crofts. Radio Frequency Identification's Potential to Monitor Small Vessels [D]. Naval Postgraduate School,2007,5-7.
[18]Vesecky, J.F, Laws, K.E, Paduan, J.D.Using HF surface wave radar and the ship Automatic Identification System (AIS) to monitor coastal vessels [C]//Proceedings of Geoscience and Remote Sensing Symposium,2009 IEEE International, IGARSS,2009,3:Ⅲ-761-Ⅲ-764.
[19]吴剑敏,滕少华,张巍.基于RFID技术的应用数据模型研究[J].微计算机信息,2007(23)：234-237.
[20]Steve Lewis. A Basic Introduction to RFID Technology and Its Use in the Supply Chain. White Paper RFID Supply Chain.2005.4.
[21]陈卓.基于主动式RFID的内河船舶监控系统的开发研究[D].大连：大连海事大学,2007,7-12.
[22]Chen Z K; Molloi S. Fast vessel identification using polyphase decomposition and inter-component processing [J]. Medical Imaging 2002,1-3:1653-1661.
[23]Lin C C, Dong F, Ou YP, et al; Study on the Differences of the Dynamic Target Information of the Marine radar and AIS[C].2009 5th International Conference on Wireless Communications, Networking and Mobile Computing, VOLS 1-85285-5288, Sep 24,2009-Sep 26,2009.
[24]Lin, CC; Lina, L; Fang, D. Fuzzy Fusion Processing Modeling and Simulation of Target's Information of AIS and Radar[C].2nd International Symposium on Test Automation and Instrumentation, VOLS 1-21091-1097, NOV 17,2008-NOV 21,2008.
[25]Li, Heng; Wang, Xinyu. Automatic recognition of ship types from infrared images Using superstructure moment invariants[C]. Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE):PTS 1 AND 2,6786:C7863-C7863 Part 1-2 2007.
[26]Chang, S.J.2. Development and analysis of AIS applications as an efficient tool for vessel traffic service[C]. Ocean '04-MTS/IEEE Techno-Ocean'04:Bridges across the Oceans-Conference Proceedings, November 9,2004-November 12,2004:2249-2253
[27]Lessing, P.A.1, Bernard, L.J.2, Tetreault, B.J.3, Chaffin, J.N. Use of the Automatic Identification System (AIS) on autonomous weather buoys for maritime domain awareness applications[C]. OCEANS 2006,18-21 Sept.2006 Page(s):1-6.
[28]Yue Jin, Jia Xiaoping, Ren Guang, Cao Hui. Video and communications technology based ships supervision and management network system [J]. Journal Of Dalian Maritime University.2006,32(2):35-39.
[29]吴兆麟.水上交通安全形势分析与评估：既要看事故还要看险情[J].世界海运,2010,(05).
[30]2001年公路水路交通行业发展统计公报[Z].北京：北京交通部综合规划司,2002,4.
[31]2002年公路水路交通行业发展统计公报[Z].北京：交通部综合规划司,2003,4.
[32]2003年公路水路交通行业发展统计公报[Z].北京：交通部综合规划司,2004，4.
[33]2004年公路水路交通行业发展统计公报[Z].北京：交通部综合规划司,2005,5.
[34]刘秀进,黄晋英.基于图像融合的运动目标检测与跟踪方法研究[J].机械工程与自动化,2009(4)：25-27.
[35]金雪丹,施朝健.图像处理与神经网络识别技术在船舶分类中的应用(英文)[J].上海海事大学学报,2007(1)：11-16.
[36]刘俊.基于红外图像的内河运动船舶目标检测和跟踪技术研究[D].重庆：重庆大学,2008.
[37]刘同明.目标类型识别方法研究[J].计算机应用研究,1999,(7)：49-51.
[38]綦辉,金鸿章,谭琳.基于神经网络的声纳特征级信息融合中目标分类研究[J].中国航海,2005,(2)：36-41.
[39]Han Y L, Guo X J. Target identification based on fuzzy-filter NN[C]. Proceedings of the Third International Symposium on Instrumentation Science and Technology,2004, 2121-125.
[40]刘艳丽,陈昊,余炎峰.基于帧间差分法和不变矩特征的运动目标检测与识别[J].工业控制计算机,2008,21(7)：34-36.
[41]王书玲.基于卡尔曼滤波的视频跟踪技术的研究及应用[D].天津：河北工业大学,2010.
[42]刘静,刘以安,杨新刚.基于Kalman滤波的船舶跟踪技术[J].仿真技术,2007,23(1)：187-189.
[43]云霄,肖刚.基于Camshift的多特征自适应融合船舶跟踪算法[J].光电工程,2011,38(5)：52-58.
[44]李斌,孙华锋.内河运动船舶的准确检测跟踪技术研究[J].微电子学与计算机,2012,29(11)：180-184.
[45]田雪怡.多传感器数据关联与航迹融合技术研究[D].哈尔滨：哈尔滨工程大学,2012.
[46]刘家忠.基于多雷达传感器的航迹融合方法研究[D].西安：西安电子科技大学,2012.
[47]刘进忙.空中目标分坐标滤波与参数航迹融合技术研究[D].西安：西安电子科技大学,2012.
[48]陈金广.运动目标状态估计及融合方法研究[D].西安：西安电子科技大学,2011.
[49]欧阳萍.AIS与雷达目标信息模糊融合方法研究[D].福建：集美大学,2010.
[50]姜明.VTS数据交换与数据融合的研究[D].哈尔滨：哈尔滨工程大学,2010.
[51]李维运.VTS中雷达和AIS信息融合算法研究[D].大连：大连海事大学,2007.
[52]于海霞.AIS与雷达数据融合方法的研究[D].大连：大连海事大学,2006.
[53]甘星.AIS与雷达信息融合在VTS中应用的研究[D].大连：大连海事大学,2003.
[54]葛红,田联房.信息融合技术在模式识别中的应用[J].计算机应用研究,2009,26(1)：19-24.
[55]Brownrigg D R K.The weighted median filter[J].ACM Communications,1984,27:807-818.
[56]Loupas T, W. N. McDicken, and P. L. Allan. An adaptive weighted median filter speckle suppression in medical ultrasonic images [J]. IEEE Transactions on Circuits and Systems, 1989,36(1):129-135.
[57]Poulos D, Waters K. Analysis and synthesis of facial image sequences using Physieal and anatomical models. IEEE Trans.PAMI,1993,15(6):569-579.
[58]曹雪.小波理论在人脸识别中的应用研究田].南京：南京理工大学,2011.
[59]袁国武.智能视频监控中的运动目标检测和跟踪算法研究[D].昆明：云南大学,2012.
[60]汪岳.基于边缘检测经典算法的改进研究与实现[D].合肥：安徽大学,2012.
[61]崔雨勇.智能交通监控中运动目标检测与跟踪算法研究[D].武汉：华中科技大学,2012.
[62]陈涛.图像仿射不变特征提取方法研究[D].长沙：国防科学技术大学,2006.
[63]Hu Ming-Kuei.Vidual pattern recognition by moment invariants [J]. IRE Trans.IT.1962,8: 179-187.
[64]姚军,蒋晓瑜,黄应清.目标识别中Hu矩>Zernike矩和小波矩的比较[J].装甲兵工程学院学报,2006,20(3)：35-36.
[65]李国祥,张显全,秦芳远.基于不变矩和BP神经网络的剪纸纹样识别[J].计算机工程与应用,2010,46(29)：158-169.
[66]Teague M R. Image analysis via the general theory of moments [J] Journal of the Optical Society of America,1980,70(08):920-930.
[67]Belkasim S, Shridhar M, Ahmadi M.Pattern recognition with moment invariants:a comparative study and new results [J].Pattern Recognition,1991,24(12):1117-1138.
[68]Shen D, Ip H H S. Discriminative Wavelet Shape Descriptors for Recognition of 2-D Patterns [J].Pattern Recognition,1999,32(2):151-165.
[69]2006年公路水路交通行业发展统计公报[Z].交通部综合规划司,2007,4.
[70]2007年公路水路交通行业发展统计公报[z].交通部综合规划司,2008，4.
[71]田秋红,孙政荣.基于Hu不变矩和BP网络的条形码图像识别方法[J].计算机工程与设计,2012,33(4)：1563-1568.
[72]杨福平,白振兴.BP神经网络和D-S证据理论的目标识别[J].火力与指挥控制,2006,31(10)：88-91.
[73]郑增国.基于均值漂移的目标跟踪算法研究[D].南宁：广西民族大学,2012.
[74]韩华.基于改进粒子滤波算法的多目标智能视频跟踪研究[D].上海：东华大学,2012.
[75]薛陈.复杂环境下视频目标跟踪技术的算法和应用研究[D].长春：中国科学院研究生院(长春光学精密机械与物理研究所),2010.
[76]袁克非.组合导航系统多源信息融合关键技术研究[D].哈尔滨：哈尔滨工程大学,2012.
[77]杨峻巍.水下航行器导航及数据融合技术研究[D].哈尔滨：哈尔滨工程大学,2012.
[78]王晓帆.信息融合中的态势评估技术研究[D].西安：西安电子科技大学,2012.
[79]冯涛.多源模糊信息系统的信息融合与知识获取方法研究[D].石家庄：河北师范大学,2012.
[80]朱允刚.贝叶斯网学习中若干问题研究及其在信息融合中的应用[D].长春：吉林大学,2012.
[81]王禾军.基于支持向量机与模糊推理的智能信息融合方法研究[D].广东：华南理工大学,2012.
[82]杨金龙.被动多传感器目标跟踪及航迹维持算法研究[D].西安：西安电子科技大学,2012.
[83]Slob W. Determination of risks on inland waterways [J].Journal of Hazardous Materials, 1998,61(1-3):363-370.
[84]戴彤宇,聂武,刘伟力.长江干线船撞桥事故分析[J].中国航海,2002,53(4)：44-47.
[85]吴羲晖.内河船舶避碰决策系统研究[D].武汉：武汉理工大学,2003.
[86]李志玉玉.AIS对船舶安全的影响[J].中国水运(下半月),2009,(04).
[87]何敏毅,曹国柠.小型船舶监管中常见问题与对策[J].中国水运(下半月),2009,(03).
[88]朱雯瑾,廉清云.RFID技术在内河船舶管理中的应用[J].中国水运(下半月刊),2010,(09).
[89]姜凤娇,赵晓凤,赵树平.VTS系统在航道交通管理中的应用研究[J].交通科技,2010(2)：106-108.
[90]赵文奇.交通流信息采集单元的研发[D].长春：吉林大学,2010.
[91]郑丹.视频监控场景中的运动物体检测和跟踪[D].合肥：中国科学技术大学,2009.
[92]Donoho D L, JOHNSTONE I M. Ideal spatial adaptation via wavelet shrinkage [J]. Biometrika,1994,81(12):425-455.
[93]Bruce A G, Gao Hong ye. Waveshrink with firm shrinkage [J].Statistica Sinica,1997,7(4): 855-874.
[94]Donoho D L.De-noising by soft threshold [J].IEEE Trans. On IT,1995.41(3):613-627.
[95]于瑞厚,李志明.基于差值图像分块均方差帕图像质量评价方法[J].科技信息,2008,12：34-35.
[96]白婷婷,邓彩霞,耿英.基于小波变换与Canny算子融合的图像边缘检测方法[J].哈尔滨理工大学学报,2010,15(1)：44-51.
[97]张琳.基于加权Hu不变矩的监控视频人体行为识别方法的研究与实现[D].西安：西北大学,2011.
[98]曲衍鹏.模糊分类新方法及应用[D].大连：大连理工大学,2012.
[99]李宁.异构网络胡总的网络选择研究[D].北京：北京邮电大学,2012.
[100]徐鹏.基于模糊聚类与RBF神经网络的负荷预测方法研究[D].南宁：广西大学,2012.
[101]许新征.基于粗糙集的粒度神经网络研究[D].徐州：中国矿业大学,2012.
[102]李新欣.船舶及鲸类声信号特征提取和分类识别研究[D].哈尔滨：哈尔滨工程大学,2012.
[103]余琨.基于视觉与接近视觉的水下多目标定位技术研究[D].武汉：华中科技大学,2012.
[104]杜艳辉.基于粗糙集理论属性约简的分类算法研究[D].大连：大连理工大学,2012.
[105]叶莲.基于免疫遗传算法的分类方法及其应用研究[D].重庆：重庆大学,2012.
[106]李友坤.BP神经网络的研究分析及改进应用[D].合肥：安徽理工大学,2012.
[107]Li Z, Yan X, Yuan C, et al:Gear multi-faults diagnosis of a rotating machinery based on independent component analysis and fuzzy k-nearest neighbor, Advanced Materials Research, Vol.108-111(2010), p.1033-38.
[108]X Zou, L Kang:Fast annealing genetic algorithm for multi-objective optimization problems [J], International Journal of Computer Mathematics,2005,82:931-940.
[109]朱武亭,刘以建.BP神经网络中的应用问题及其解决[J].上海海事大学学报,2005,26(2)：64-66.
[110]史忠植.神经网络[M].北京：高等教育出版社,2009.
[111]龚小兵.基于BP神经网络的车辆牌照自动识别系统的研究[D].武汉：武汉理工大学,2006.
[112]Fashing M, Tomasi C. Mean shift is a bound optimization [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence (S0162-8828),2005,27(3):471-474.
[113]Collins R T., Liu Y X, Lleordeanu M. Online selection of discriminative tracking features [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27:1631-1643.
[114]Hager G D, Charles V S.Multiple kernel tracking with SSD[C]. CVPR,2004.
[115]Fan Z., Yang M., Wu Y G, et al. Efficient optimal kernel placement for reliable visual tracking [C].CVPR,2006.
[116]Yang M, Yu T, Wu Y G.Game-theoretic multiple target tracking[C], ICCV,2007.
[117]杨杰,张翔.视频目标检测和跟踪及其应用[M].上海：上海交通大学出版社,2012.
[118]朱必浩,冯新喜,鹿传国,王帛.多传感器多目标航迹关联算法综述[J].中国雷达,2010(3)：13-15.
[119]蒋雯,张安,邓勇.基于区间信息的基本概率赋值转换概率方法及应用[J].西北工业大学学报,2011,29(1)：4448.
[120]兰旭辉,熊家军.一种基于可信度矩阵的多传感器目标识别方法[J].计算机应用与软件,2011,28(3)：234-236.
[121]邓海卫.摄像机标定的六点法研究[D].青岛：青岛大学,2009.
[122]谭晓波.摄像机标定及相关技术研究[D].长沙：国防科技大学,2004.
[123]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报,2000,26(1)：43-55.
[124]Meyer C D, Matrix analysis and applied linear algebra [M].New York:Cambridge University Press,2001.
[2]孙文力,孙文强.船载自动识别系统[M].大连：大连海事大学出版社,2004.
[3]王世远,许开宇.AIS现状、前景及对策[J].航海技术,2001,,(05).
[4]长江海事局.长江海事局发展规划[Z],武汉：长江海事局,2005.
[5]朱雯瑾,廉清云RFID技术在内河船舶管理中的应用[J].中国水运(下半月刊),2010,(09).
[6]严新平,马枫,初秀民,陈晨.长江船舶交通流实时采集关键技术研究[J].中国航海,2010,33(02)：40-45.
[7]岳晋,贾小平,任光,曹辉.基于视频通信技术的船舶监管网络[J].大连海事大学学报,2006,32(2)：35-39.
[8]柳圣军.基于计算机视觉的内河航道智能监控系统的研究[D].杭州：浙江工业大学,2009.
[9]曹辉,张均东,宋威.视频技术在船舶领域中的研究与应用[J].船海工程,2007,21(3)：122-125.
[10]何乃甩,黄席樾,刘俊,权循宝.基于形态学重构的内河红外船舶目标检测[J].红外技术,2007,24(7)：419-424.
[11]李勇,周品,谭建军.基于AIS与GIS的船舶监控管理系统研究[J].微计算机信息,2007,23(6)：250-254.
[12]Torkild Eriksen, Gudrun HZye, BjZrn Narheim, Bente JenslZkken Meland. Maritime traffic monitoring using a space-basedAIS receiver [J]. Acta Astronautica 58 (2006):537-549.
[13]王晨熙,王晓博,朱靖,王国宏.雷达与AIS信息融合综述[J].指挥控制与仿真.2009,31(2)：14.
[14]郑芳,李赣华,蔡宣平.基于激光传感器的统计特征提取和误差分析[J].红外与激光工程,2006,35(6)：705-758.
[15]高岚,潘峰,张卉,廖云良.合成孔径雷达图像船舶自动检测新方法[J].船海工程,2006,18(4)：102-104.
[16]黄洪琼,汤天浩,金永兴,王天真.基于智能融合的船舶交通流预测系统[J].中国航海,2008,31(4)：364-367.
[17]John A. Crofts. Radio Frequency Identification's Potential to Monitor Small Vessels [D]. Naval Postgraduate School,2007,5-7.
[18]Vesecky, J.F, Laws, K.E, Paduan, J.D.Using HF surface wave radar and the ship Automatic Identification System (AIS) to monitor coastal vessels [C]//Proceedings of Geoscience and Remote Sensing Symposium,2009 IEEE International, IGARSS,2009,3:Ⅲ-761-Ⅲ-764.
[19]吴剑敏,滕少华,张巍.基于RFID技术的应用数据模型研究[J].微计算机信息,2007(23)：234-237.
[20]Steve Lewis. A Basic Introduction to RFID Technology and Its Use in the Supply Chain. White Paper RFID Supply Chain.2005.4.
[21]陈卓.基于主动式RFID的内河船舶监控系统的开发研究[D].大连：大连海事大学,2007,7-12.
[22]Chen Z K; Molloi S. Fast vessel identification using polyphase decomposition and inter-component processing [J]. Medical Imaging 2002,1-3:1653-1661.
[23]Lin C C, Dong F, Ou YP, et al; Study on the Differences of the Dynamic Target Information of the Marine radar and AIS[C].2009 5th International Conference on Wireless Communications, Networking and Mobile Computing, VOLS 1-85285-5288, Sep 24,2009-Sep 26,2009.
[24]Lin, CC; Lina, L; Fang, D. Fuzzy Fusion Processing Modeling and Simulation of Target's Information of AIS and Radar[C].2nd International Symposium on Test Automation and Instrumentation, VOLS 1-21091-1097, NOV 17,2008-NOV 21,2008.
[25]Li, Heng; Wang, Xinyu. Automatic recognition of ship types from infrared images Using superstructure moment invariants[C]. Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE):PTS 1 AND 2,6786:C7863-C7863 Part 1-2 2007.
[26]Chang, S.J.2. Development and analysis of AIS applications as an efficient tool for vessel traffic service[C]. Ocean '04-MTS/IEEE Techno-Ocean'04:Bridges across the Oceans-Conference Proceedings, November 9,2004-November 12,2004:2249-2253
[27]Lessing, P.A.1, Bernard, L.J.2, Tetreault, B.J.3, Chaffin, J.N. Use of the Automatic Identification System (AIS) on autonomous weather buoys for maritime domain awareness applications[C]. OCEANS 2006,18-21 Sept.2006 Page(s):1-6.
[28]Yue Jin, Jia Xiaoping, Ren Guang, Cao Hui. Video and communications technology based ships supervision and management network system [J]. Journal Of Dalian Maritime University.2006,32(2):35-39.
[29]吴兆麟.水上交通安全形势分析与评估：既要看事故还要看险情[J].世界海运,2010,(05).
[30]2001年公路水路交通行业发展统计公报[Z].北京：北京交通部综合规划司,2002,4.
[31]2002年公路水路交通行业发展统计公报[Z].北京：交通部综合规划司,2003,4.
[32]2003年公路水路交通行业发展统计公报[Z].北京：交通部综合规划司,2004，4.
[33]2004年公路水路交通行业发展统计公报[Z].北京：交通部综合规划司,2005,5.
[34]刘秀进,黄晋英.基于图像融合的运动目标检测与跟踪方法研究[J].机械工程与自动化,2009(4)：25-27.
[35]金雪丹,施朝健.图像处理与神经网络识别技术在船舶分类中的应用(英文)[J].上海海事大学学报,2007(1)：11-16.
[36]刘俊.基于红外图像的内河运动船舶目标检测和跟踪技术研究[D].重庆：重庆大学,2008.
[37]刘同明.目标类型识别方法研究[J].计算机应用研究,1999,(7)：49-51.
[38]綦辉,金鸿章,谭琳.基于神经网络的声纳特征级信息融合中目标分类研究[J].中国航海,2005,(2)：36-41.
[39]Han Y L, Guo X J. Target identification based on fuzzy-filter NN[C]. Proceedings of the Third International Symposium on Instrumentation Science and Technology,2004, 2121-125.
[40]刘艳丽,陈昊,余炎峰.基于帧间差分法和不变矩特征的运动目标检测与识别[J].工业控制计算机,2008,21(7)：34-36.
[41]王书玲.基于卡尔曼滤波的视频跟踪技术的研究及应用[D].天津：河北工业大学,2010.
[42]刘静,刘以安,杨新刚.基于Kalman滤波的船舶跟踪技术[J].仿真技术,2007,23(1)：187-189.
[43]云霄,肖刚.基于Camshift的多特征自适应融合船舶跟踪算法[J].光电工程,2011,38(5)：52-58.
[44]李斌,孙华锋.内河运动船舶的准确检测跟踪技术研究[J].微电子学与计算机,2012,29(11)：180-184.
[45]田雪怡.多传感器数据关联与航迹融合技术研究[D].哈尔滨：哈尔滨工程大学,2012.
[46]刘家忠.基于多雷达传感器的航迹融合方法研究[D].西安：西安电子科技大学,2012.
[47]刘进忙.空中目标分坐标滤波与参数航迹融合技术研究[D].西安：西安电子科技大学,2012.
[48]陈金广.运动目标状态估计及融合方法研究[D].西安：西安电子科技大学,2011.
[49]欧阳萍.AIS与雷达目标信息模糊融合方法研究[D].福建：集美大学,2010.
[50]姜明.VTS数据交换与数据融合的研究[D].哈尔滨：哈尔滨工程大学,2010.
[51]李维运.VTS中雷达和AIS信息融合算法研究[D].大连：大连海事大学,2007.
[52]于海霞.AIS与雷达数据融合方法的研究[D].大连：大连海事大学,2006.
[53]甘星.AIS与雷达信息融合在VTS中应用的研究[D].大连：大连海事大学,2003.
[54]葛红,田联房.信息融合技术在模式识别中的应用[J].计算机应用研究,2009,26(1)：19-24.
[55]Brownrigg D R K.The weighted median filter[J].ACM Communications,1984,27:807-818.
[56]Loupas T, W. N. McDicken, and P. L. Allan. An adaptive weighted median filter speckle suppression in medical ultrasonic images [J]. IEEE Transactions on Circuits and Systems, 1989,36(1):129-135.
[57]Poulos D, Waters K. Analysis and synthesis of facial image sequences using Physieal and anatomical models. IEEE Trans.PAMI,1993,15(6):569-579.
[58]曹雪.小波理论在人脸识别中的应用研究田].南京：南京理工大学,2011.
[59]袁国武.智能视频监控中的运动目标检测和跟踪算法研究[D].昆明：云南大学,2012.
[60]汪岳.基于边缘检测经典算法的改进研究与实现[D].合肥：安徽大学,2012.
[61]崔雨勇.智能交通监控中运动目标检测与跟踪算法研究[D].武汉：华中科技大学,2012.
[62]陈涛.图像仿射不变特征提取方法研究[D].长沙：国防科学技术大学,2006.
[63]Hu Ming-Kuei.Vidual pattern recognition by moment invariants [J]. IRE Trans.IT.1962,8: 179-187.
[64]姚军,蒋晓瑜,黄应清.目标识别中Hu矩>Zernike矩和小波矩的比较[J].装甲兵工程学院学报,2006,20(3)：35-36.
[65]李国祥,张显全,秦芳远.基于不变矩和BP神经网络的剪纸纹样识别[J].计算机工程与应用,2010,46(29)：158-169.
[66]Teague M R. Image analysis via the general theory of moments [J] Journal of the Optical Society of America,1980,70(08):920-930.
[67]Belkasim S, Shridhar M, Ahmadi M.Pattern recognition with moment invariants:a comparative study and new results [J].Pattern Recognition,1991,24(12):1117-1138.
[68]Shen D, Ip H H S. Discriminative Wavelet Shape Descriptors for Recognition of 2-D Patterns [J].Pattern Recognition,1999,32(2):151-165.
[69]2006年公路水路交通行业发展统计公报[Z].交通部综合规划司,2007,4.
[70]2007年公路水路交通行业发展统计公报[z].交通部综合规划司,2008，4.
[71]田秋红,孙政荣.基于Hu不变矩和BP网络的条形码图像识别方法[J].计算机工程与设计,2012,33(4)：1563-1568.
[72]杨福平,白振兴.BP神经网络和D-S证据理论的目标识别[J].火力与指挥控制,2006,31(10)：88-91.
[73]郑增国.基于均值漂移的目标跟踪算法研究[D].南宁：广西民族大学,2012.
[74]韩华.基于改进粒子滤波算法的多目标智能视频跟踪研究[D].上海：东华大学,2012.
[75]薛陈.复杂环境下视频目标跟踪技术的算法和应用研究[D].长春：中国科学院研究生院(长春光学精密机械与物理研究所),2010.
[76]袁克非.组合导航系统多源信息融合关键技术研究[D].哈尔滨：哈尔滨工程大学,2012.
[77]杨峻巍.水下航行器导航及数据融合技术研究[D].哈尔滨：哈尔滨工程大学,2012.
[78]王晓帆.信息融合中的态势评估技术研究[D].西安：西安电子科技大学,2012.
[79]冯涛.多源模糊信息系统的信息融合与知识获取方法研究[D].石家庄：河北师范大学,2012.
[80]朱允刚.贝叶斯网学习中若干问题研究及其在信息融合中的应用[D].长春：吉林大学,2012.
[81]王禾军.基于支持向量机与模糊推理的智能信息融合方法研究[D].广东：华南理工大学,2012.
[82]杨金龙.被动多传感器目标跟踪及航迹维持算法研究[D].西安：西安电子科技大学,2012.
[83]Slob W. Determination of risks on inland waterways [J].Journal of Hazardous Materials, 1998,61(1-3):363-370.
[84]戴彤宇,聂武,刘伟力.长江干线船撞桥事故分析[J].中国航海,2002,53(4)：44-47.
[85]吴羲晖.内河船舶避碰决策系统研究[D].武汉：武汉理工大学,2003.
[86]李志玉玉.AIS对船舶安全的影响[J].中国水运(下半月),2009,(04).
[87]何敏毅,曹国柠.小型船舶监管中常见问题与对策[J].中国水运(下半月),2009,(03).
[88]朱雯瑾,廉清云.RFID技术在内河船舶管理中的应用[J].中国水运(下半月刊),2010,(09).
[89]姜凤娇,赵晓凤,赵树平.VTS系统在航道交通管理中的应用研究[J].交通科技,2010(2)：106-108.
[90]赵文奇.交通流信息采集单元的研发[D].长春：吉林大学,2010.
[91]郑丹.视频监控场景中的运动物体检测和跟踪[D].合肥：中国科学技术大学,2009.
[92]Donoho D L, JOHNSTONE I M. Ideal spatial adaptation via wavelet shrinkage [J]. Biometrika,1994,81(12):425-455.
[93]Bruce A G, Gao Hong ye. Waveshrink with firm shrinkage [J].Statistica Sinica,1997,7(4): 855-874.
[94]Donoho D L.De-noising by soft threshold [J].IEEE Trans. On IT,1995.41(3):613-627.
[95]于瑞厚,李志明.基于差值图像分块均方差帕图像质量评价方法[J].科技信息,2008,12：34-35.
[96]白婷婷,邓彩霞,耿英.基于小波变换与Canny算子融合的图像边缘检测方法[J].哈尔滨理工大学学报,2010,15(1)：44-51.
[97]张琳.基于加权Hu不变矩的监控视频人体行为识别方法的研究与实现[D].西安：西北大学,2011.
[98]曲衍鹏.模糊分类新方法及应用[D].大连：大连理工大学,2012.
[99]李宁.异构网络胡总的网络选择研究[D].北京：北京邮电大学,2012.
[100]徐鹏.基于模糊聚类与RBF神经网络的负荷预测方法研究[D].南宁：广西大学,2012.
[101]许新征.基于粗糙集的粒度神经网络研究[D].徐州：中国矿业大学,2012.
[102]李新欣.船舶及鲸类声信号特征提取和分类识别研究[D].哈尔滨：哈尔滨工程大学,2012.
[103]余琨.基于视觉与接近视觉的水下多目标定位技术研究[D].武汉：华中科技大学,2012.
[104]杜艳辉.基于粗糙集理论属性约简的分类算法研究[D].大连：大连理工大学,2012.
[105]叶莲.基于免疫遗传算法的分类方法及其应用研究[D].重庆：重庆大学,2012.
[106]李友坤.BP神经网络的研究分析及改进应用[D].合肥：安徽理工大学,2012.
[107]Li Z, Yan X, Yuan C, et al:Gear multi-faults diagnosis of a rotating machinery based on independent component analysis and fuzzy k-nearest neighbor, Advanced Materials Research, Vol.108-111(2010), p.1033-38.
[108]X Zou, L Kang:Fast annealing genetic algorithm for multi-objective optimization problems [J], International Journal of Computer Mathematics,2005,82:931-940.
[109]朱武亭,刘以建.BP神经网络中的应用问题及其解决[J].上海海事大学学报,2005,26(2)：64-66.
[110]史忠植.神经网络[M].北京：高等教育出版社,2009.
[111]龚小兵.基于BP神经网络的车辆牌照自动识别系统的研究[D].武汉：武汉理工大学,2006.
[112]Fashing M, Tomasi C. Mean shift is a bound optimization [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence (S0162-8828),2005,27(3):471-474.
[113]Collins R T., Liu Y X, Lleordeanu M. Online selection of discriminative tracking features [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27:1631-1643.
[114]Hager G D, Charles V S.Multiple kernel tracking with SSD[C]. CVPR,2004.
[115]Fan Z., Yang M., Wu Y G, et al. Efficient optimal kernel placement for reliable visual tracking [C].CVPR,2006.
[116]Yang M, Yu T, Wu Y G.Game-theoretic multiple target tracking[C], ICCV,2007.
[117]杨杰,张翔.视频目标检测和跟踪及其应用[M].上海：上海交通大学出版社,2012.
[118]朱必浩,冯新喜,鹿传国,王帛.多传感器多目标航迹关联算法综述[J].中国雷达,2010(3)：13-15.
[119]蒋雯,张安,邓勇.基于区间信息的基本概率赋值转换概率方法及应用[J].西北工业大学学报,2011,29(1)：4448.
[120]兰旭辉,熊家军.一种基于可信度矩阵的多传感器目标识别方法[J].计算机应用与软件,2011,28(3)：234-236.
[121]邓海卫.摄像机标定的六点法研究[D].青岛：青岛大学,2009.
[122]谭晓波.摄像机标定及相关技术研究[D].长沙：国防科技大学,2004.
[123]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述[J].自动化学报,2000,26(1)：43-55.
[124]Meyer C D, Matrix analysis and applied linear algebra [M].New York:Cambridge University Press,2001.
© 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 |