摘要
弱小目标的检测与识别,是近年来图像处理与目标检测识别领域的一个研究热点,也是一项难度大且有着重要战略应用价值的课题。本文主要研究图像中的弱小目标检测识别技术。通过图像处理,检测出弱小目标;通过信息融合,最终识别出弱小目标。
首先,研究了含弱小目标的图像的基本特性,包括图像噪声模型、背景空间分布模型和弱小目标模型。同时研究了目标检测前的图像预处理方法。
其次,研究了弱小目标检测的“先检测后跟踪”算法,主要用于复杂背景弱噪声图像中的弱小目标检测。针对背景复杂时,弱小目标检测不能通过单一的图像处理方法实现的特点,提出基于小波分析和信息融合的弱小目标检测算法和基于小波形态学的弱小目标检测算法。仿真结果表明这两种算法都能取得较好的检测效果。
随后,研究了弱小目标检测的“先跟踪后检测”算法,主要用于背景简单强噪声图像中的弱小目标检测识别。针对使用常规的动态规划算法累积能量时效果较差的缺点,提出一种新的基于状态稳定性的动态规划能量累积算法。仿真结果结果表明,新算法较好的解决了目标能量累积时的能量扩散问题。
接着,研究了弱小目标识别算法。针对有效信息较少,弱小目标识别困难且致信度低的特点,提出一种新的基于弱小目标速度、灰度、轨迹信息的识别方法。仿真结果表明,新方法明显提高识别置信度。
最后,基于VC++和OpenCV语言开发了弱小目标检测识别软件,实现几种基本的目标检测识别算法和新设计的算法,同时也验证了新算法的正确性。
The detection and recognition of dim and small target is a hot research subject in the field of image process and target detection and recognition. This research also has an important strategic application value. In this dissertation, detection and recognition of dim and small target in images are studied. Dim and small targets are detected by processing images and be recognized with information technique.
Fist of all, the basic characteristics of the images with small targets are studied. These characteristics include the models of image noise, space background and small targets. The image pre-processing before targets detection is studied too.
Then,“Detect-Before-Track”algorithm is studied. It is used for detecting dim and small targets in complex background images with week noise. As the dim and small targets can not be detected with a single image processing technique, two new methods of dim and small targets detection are proposed. One is base on the wavelet transform algorithm and information fusion technology. The other is base on the wavelet transform algorithm and mathematical morphology. Simulation results show that the two new algorithms can obtain the good detection results.
Following,“Track-Before-Detect”algorithm is studied. It is used for detecting dim and small targets in simple background images with strong noise. In allusion to the flaws of general dynamic programming algorithm with maximizing energy, a new improved method is proposed, which is based on the most steady states. Simulation results show that the proposed algorithm can well solve the energy scattering problem.
And then, recognition algorithm of dim and small targets is studied. Because of the lack of the small targets’information, it is difficult to recognize small targets and the recognition reliabilities always are low. A new improved method of small targets recognition is proposed,which is base on the the information of targets’velocity , gray and tracks. Simulation results show that recognition reliabilities are raised obviously.
Finally, a kind of software of detection and recognition of dim and small target is developed with VC++ and OpenCV. Several basic dim and small targets detection and recognition algorithms and new methods are implemented by it. The effect of these new methods in this dissertation is validated by using the software.
引文
[1]梁发麦,复杂背景下运动弱小目标检测算法研究,[硕士学位论文],吉林,吉林大学,2005
[2]许春晓,一种红外序列图像弱小目标检测新方法研究,[硕士学位论文],长沙,华中科技大学研究生院,2005
[3] Chapple P B, Bertilone D C, Caprari R S, etal, Stochastic model-based processing for detection of small targets in non-Gaussian natural imagery, Image Processing, 2001, 10(4): 554~564
[4] Zhang J, Schroeder J, Redding N J, Small target detection using enhanced SAR images, Systems, Man and Cybernetics, 2003, 10(1): 1001~1006
[5]张弘,赵保军,朱梦宇等,复杂背景下的红外运动弱小目标的实时检测,系统工程与电子技术,2001,23(8):40~41
[6] Yang L, Yang J, Yang K, Adaptive detection for infrared small target under sea-sky complex background, Electronics Letters, 2004, 40(17): 1083~1085
[7]俞建成,孙胜利,陈桂林,红外图像中弱小目标检测研究,红外,2006,27 (4):15~19
[8] Chartene E Caefer, Jerry Sillivennan, Optimization of Point target tilting filters, IEEE Transaction on aerospace and electronic systems, 2000, 36(1): 15~25
[9] Wang G D, Chen C Y, Shen X B, Facet-based infrared small target detection method, Electronics Letters, 2005, 41(22): 1244~1246
[10]朱海峰,陈曾平,低空复杂背景红外弱小目标检测,电子工程师,2004,30(9):40~42
[11]郑文龙,张涌,汤心溢等,复杂背景下红外弱小目标实时识别方法研究,红外与毫米波学报,2001,20(6):433~436
[12]张兵,卢焕章,云杂波背景图像序列中弱小目标检测算法研究,红外技术,2004,26(6):66~71
[13]张江辉,陶声祥,陈翠华,空中红外弱小目标并行分割算法,光电工程,2005,32(11): 12~15
[14] Wang Yang, Zhen Qinbo, Zhang Junping, Real-time detection of smalltarget in IR grey image based on mathematical morphology, Infraredand Laser Engineering, 2003, 32(1): 28~31
[15] Chiang S S, Chang C I, Ginsberg I W, Unsupervised target detection in hyperspectralimages using projection pursuit, IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(7): 1380~1391
[16] Hanbury A G, Serra J, Morphological operators on the unit circle, Image Processing, 2001, 10(12): 1842~1850
[17]叶斌,彭嘉雄,基于形态学Top-Hat算子的弱小目标检测方法,中国图像图形学报,2002,9(7):638~ 642
[18] Ye Bin, Peng Jiaxiong, Small target detection method based on mor-phology top-hat operator, Journal of Image and Graphics, 2002, 7 (7): 638~642
[19] Leung H, Young, A Small target detection in clutter using recursive nonlinear prediction, Aerospace and Electronic Systems, 2000, 36(2): 713~718
[20]张焱,沈振康,王平,基于RBF神经网络的背景估计及红外弱小目标检测,国防科技大学学报,2004,26(5):39~45
[21] Henry Leung, Neville Dubash, Nan Xie, Detection of Small Objects in Clutter Using a GA-RBF Neural Network, IEEE Transactions on Aerospace and Electronic Systems, 2002, 38(1): 98～117
[22]张焱,沈振康,王平,基于BP神经网络的背景估计及红外弱小目标检测,系统工程与电子技术,2004,26(12):1901~1904
[23]王超,谭礼平,刘景雷等,Elman神经网络在红外小目标检测中的应用,红外,2007,28(1):18~22
[24] Li Hong, Zheng Cheng yong, Gao Jingli, Detecting small moving objectbased on wavelet multi-scale image registration, Infrared and Laser Engineering, 2003, 32(3): 268~270
[25]顾静良,万敏,张卫等,基于小波变换和数据融合技术的弱小目标检测,强激光与粒子束,2005,17(7):25~28
[26] S Arivazhagan, L Ganesan, Automatic target detection using wavelet transform, EURASIP Journal on Applied Processing, 2004, 14(17): 2663~2674
[27]李大鹏,陶观群,基于子波相关算法的红外图像点目标检测,红外,2002,14(1):1~4
[28]王俊林,张剑云,红外弱小目标识别的新方法,红外技术,2005,27(5):408~411
[29]马治国,王江安,改善海空背景下红外弱点目标识别性能的理论方法探讨,海军工程大学学报,2003,15(3):5~8
[30] Gan Wang, R M Inigo, E S MeVey, A single pixel target detection and tracking syste, IEEE, Proceedings of the IEEE International Conference on Pattern Recognition, USA, FL, 1990: 99~l03
[31] Reed I S, Ga ardi R M, Stotts L B, Optical moving target detection with 3-D matehed filtering, IEEE Trans on AES, 1988, 24(4): 327~336
[32] Bleekman S S, Mdfiple hypothesis tracking for mdfipletarget tracking, Aeropace and Eleenie systems Magazine, 2004, 19(1): 5~ l8
[33] Johnston L A, Krishnamurthy V, Performance analysis of a dynamic programming track before detect algprithm, Aeropaee and Electronic Systems, 2002, 38(1): 228~241
[34] Zhang Fei, LI Cheng-fang, SHI Li-na, Algorithm based on mathematical morphology for dim moving point target detection, Optical Technique, 2004, 30(5): 600~602
[35] Tzannes A P, Brooks D H, Detection small moving objects using temporal hypothesis testing, IEEE Trans on AES, 2002, 38(2): 570~585
[36]李秋华,李吉成,沈振康等,一种基于D-S证据理论的红外弱小目标融合识别方法,系统工程与电子技术,2002,24(6):25~27
[37]肖利平,杨嘉伟,一种基于模糊理论与D-S证据理论的红外弱小目标与诱饵识别算法,红外技术,2005,27(3):240~244
[38]侯志强,李鸿艳,韩崇昭等,基于雷达与图像信息融合的目标跟踪仿真研究,系统仿真学报,2004,16(8):1831~1834
[39]杜峰,施文康,红外弱小目标的证据理论识别方法,光电工程,2005,32(8):6~8
[40]李庆华,复杂背景条件下的红外图像中弱小目标的检测,[硕士学位论文],哈尔滨,哈尔滨工程大学研究生院,2006.
[41] Milan Sonka, Vackav Hlavac, Roger Boyle, Image Processing Analysis and Machine Vision,北京,人民邮电出版社,2003: 385~386
[42]李卓,郭立红,强起伏云背景下的弱小目标图像预处理算法,电光与控制,2007,14(1):11~12
[43] Panagopoulos S, Soraghan J J, Small-target detection in sea clutter, Geoscience and Remote Sensing, 2004, 42(7): 1355~1361
[44] Mallats S, A theory for multi-resolution signal decomposition: The wavelet representation, IEEE Trans on Patterns Analysis and MachineIntelligence, 1989, 11 (7): 674~693
[45] Davidson G, Griffiths H D, Wavelet detection scheme for small targets in sea clutter, Electronics Letters, 2002, 38(19): 1128~1230
[46] Xu Yansun, Wavelet transform domain filters: A spatially selective noise filtration technique, IEEE Trans on Image processing, 1994, 3 (6): 747~758
[47]孙广富,张兵,卢焕章,基于窗口预测匹配的序列图像点目标轨迹检测算法,国防科技大学学报,2004,26(2):25~29
[48]黄林梅,张桂林,王新余,基于动态规划的红外运动弱小目标检测算法,红外与激光工程,2004,33(3):303~306
[49] Gan Wang, Rafael M. Inigo, Eugene S Mcvey, A pipeline algorithm for detection and tracking of pixel-sized target trajectories, SPIE, Signal and data processing of small targets 1990 Orlando, FL, 1990: 167~178
[50]万琴,王耀南,基于卡尔曼滤波器的运动目标检测与跟踪,湖南大学学报,2007,34(3):36~40
[51]李开宁,数值计算方法引论,北京,航空工业出版社,2002,71~72
[52] Jacobson D H, Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential game, IEEE Trans on Automat Control, 1973, 18(1): 124~131
[53]彭焱,徐毓,金宏斌,多传感器数据融合系统中时间配准算法分析,雷达与对抗,2005,24(2):16~20
[54] Dempster A P, Upper and lower probabilities induced by a multi~valued mapping, Annals of Mathematical Statistics, 1967, 38(2): 325~339
[55] Ramanaryanan Viswanathan, Varshney Pramod K, Distributed Detection with Multiple Sensors: (PartI) Fundamentals, IEEE, Proceedings of the IEEE International Conference on Pattern Recognition, USA, FL, 1997, 85(1): 54~63
