基于脉冲耦合神经网络的车辆图像分割研究
|
摘要
摘要：车辆图像分割是车辆检测系统中最基本也是最重要的环节,车辆图像分割的质量直接影响后续图像处理的精度和效率。自然光照环境下,满足准确性、实用性要求的车辆图像分割模型始终是智能交通领域研究的热点和难点问题,因此,具有人类视觉特性的图像分割模型是今后智能交通信息处理系统研究的方向。针对上述研究背景,本文在脉冲耦合神经网络(Pulse Coupled Neural Networks, PCNN)模型的基础上,从理论与应用两个方面对具有视觉神经元特性的车辆图像分割方法进行了深入研究。论文主要研究内容和创新归纳如下：
(1)针对传统脉冲耦合神经网络模型车辆图像分割时,车牌区域普遍存在的过分割与欠分割问题,提出了脉冲耦合神经网络模型最优参数的选取方法。通过最大类间方差算法自适应确定PCNN分割模型初始阈值,中心神经元局部邻域灰度均方差更新连接强度系数,Hebb学习规则确定连接加权系数矩阵,实现PCNN模型参数的优化。实验表明参数的优化不仅减少了PCNN模型图像分割时迭代的次数,而且提高了PCNN模型自适应图像分割的质量。
(2)针对车辆图像分割中阴影对车牌图像分割的影响,提出了一种车辆阴影消除模型。该模型将优化的脉冲耦合神经网络与阴影属性相结合,无需建立背景模型与阴影模型。通过对图像灰度通道和色度通道信息分别进行分割,实现不同信息通道的车辆与阴影的分离,并将两个通道的分割结果图像合并,产生最终的消除车辆阴影的图像。实验结果表明该模型在消除车辆阴影的同时,较好地保持了图像中车牌、车标等关键信息。
(3)针对光照和车体漫反射对PCNN模型图像分割的影响,提出了一种具有神经元感受野特性的脉冲耦合神经网络(Receptive Field-Pulse Coupled Neural Networks, RF-PCNN)车辆图像分割模型。该模型通过神经元感受野函数确定PCNN模型反馈域连接矩阵的结构,使其具有方向性和尺度性,从而更好地模拟视觉细胞分割图像的功能。实验结果表明该模型提高了自然环境中车牌图像分割的质量。分割结果中字符具有较高的边界检出率,较好地解决了复杂背景车辆图像分割中车牌区域存在的欠分割与过分割问题。
(4)针对车辆图像分割中车牌所占比例小、位置不固定、大小不一以及分割易受光照影响的问题,提出了一种基于视觉注意机制的脉冲耦合神经网络(Visual Attention Mechanism Pulse Coupled Neural Networks, VAMPCNN)车辆图像分割模型。该模型在RF-PCNN模型的基础上实现了多尺度空间的图像分割,使多尺度目标均具有较好的分割效果,克服了车牌所占比例小、大小不一对图像分割的影响。将视觉注意机制中的数据驱动模式和任务驱动模式相结合,通过对不同尺度空间分割结果中目标特征尺度与最佳尺度的确定,实现多尺度空间中感兴趣目标的精确定位,实验结果表明该模型具有较好的最佳尺度分割定位多目标的功能。
ABSTRACT:Vehicle image segmentation is the most fundamental and important step in a vehicle detection system. The quality of the vehicle image segmentation has a direct impact on the accuracy and efficiency of the subsequent image processing. However, it is always of great importance for intelligence transportation field to investigate an accurate and practical vehicle image segmentation model under the natural light environment. The segmentation model based on human vision is the research direction of intelligent transportation system for information processing in the future.Under this background, a vehicle segmentation method with visual neuron characteristic has been studied on the basis of Pulse Coupled Neural Networks (PCNN) model from both theory and application. The main research contents and innovation contributions of this thesis are summarized as follows:
(1) The vehicle image segmentation using the traditional PCNN model usually suffers from troubles of over-segmentation and under-segmentation in the license plate area. Under this circumstance, a method for choosing optimal parameters in PCNN model is proposed. The initial threshold of PCNN segmentation model is set with Otsu algorithm, the connection coefficients are updated using the mean square difference of neurons within the local area and Hebb rule is used to calculate the connection coefficient matrix. The experimental results demonstrate that the optimized PCNN model can reduce the number of iterations during image segmentation and enhance self-adaptive segmentation effect of PCNN model.
(2) A vehicle shadow elimination model is proposed to reduce the interference from the shadows in the license plate segmentation.The model combine the optimized PCNN with the shadow attributes. Meanwhile, there is no need to construct the background model and the shadow model. By performing the segmentation on both gray and hue component, vehicle and shadow are separated in each information channel. The image with the removed shadow is finally obtained by merging the segmentation results of the two information channel. The experimental results show that the model not only eliminates the vehicle shadow, but also keeps more details of the license plate and the car logo. Shadow elimination rate further validate the effectiveness of the algorithm for eliminating shadows.
(3) To handle the sunlight and diffuse reflection of the vehicle body, a Receptive Field-Pulse Coupled Neural Networks (RF-PCNN) model is proposed, where the feedback domain linking matrix is determined by neurons receptive field model. This new RF-PCNN model has both directivits and scales.The function of visual cells to segment an image can be simulated more efficiently. The experimental results show that the RF-PCNN model improves the effect of license plate image segmentation under natural environment. A high boundary detection rate has been achieved for the characters and the over-segmentation and under-segmentation problems have been solved in the vehicle image segmentation with complex backgrounds.
(4) The segementation effects of the license plate are influenced by many factors, such as small proportion, unfixed locations, variant sizes and variant illuminations. Aiming at solving the above problems, an image segmentation method based on the Visual Attention Mechanism Pulse Coupled Neural Networks (VAMPCNN) is proposed. This model realizes multi-scale space image segmentation on the basis of the RF-PCNN model, which achieves better segmentation effect for multi-scale targets and overcomes the influence of small proportion and variant sizes of license plate on image segmentation.The model combines data-driven mode with the task-driven mode in the visual attention mechanism, Through the determination of the target's characteristic scale and the optimal scale, it can locate the interesting targets in the multi-scale space. The experimental results show that the model has the function to position segmentation multi-targets at optimal scale.
(1)针对传统脉冲耦合神经网络模型车辆图像分割时,车牌区域普遍存在的过分割与欠分割问题,提出了脉冲耦合神经网络模型最优参数的选取方法。通过最大类间方差算法自适应确定PCNN分割模型初始阈值,中心神经元局部邻域灰度均方差更新连接强度系数,Hebb学习规则确定连接加权系数矩阵,实现PCNN模型参数的优化。实验表明参数的优化不仅减少了PCNN模型图像分割时迭代的次数,而且提高了PCNN模型自适应图像分割的质量。
(2)针对车辆图像分割中阴影对车牌图像分割的影响,提出了一种车辆阴影消除模型。该模型将优化的脉冲耦合神经网络与阴影属性相结合,无需建立背景模型与阴影模型。通过对图像灰度通道和色度通道信息分别进行分割,实现不同信息通道的车辆与阴影的分离,并将两个通道的分割结果图像合并,产生最终的消除车辆阴影的图像。实验结果表明该模型在消除车辆阴影的同时,较好地保持了图像中车牌、车标等关键信息。
(3)针对光照和车体漫反射对PCNN模型图像分割的影响,提出了一种具有神经元感受野特性的脉冲耦合神经网络(Receptive Field-Pulse Coupled Neural Networks, RF-PCNN)车辆图像分割模型。该模型通过神经元感受野函数确定PCNN模型反馈域连接矩阵的结构,使其具有方向性和尺度性,从而更好地模拟视觉细胞分割图像的功能。实验结果表明该模型提高了自然环境中车牌图像分割的质量。分割结果中字符具有较高的边界检出率,较好地解决了复杂背景车辆图像分割中车牌区域存在的欠分割与过分割问题。
(4)针对车辆图像分割中车牌所占比例小、位置不固定、大小不一以及分割易受光照影响的问题,提出了一种基于视觉注意机制的脉冲耦合神经网络(Visual Attention Mechanism Pulse Coupled Neural Networks, VAMPCNN)车辆图像分割模型。该模型在RF-PCNN模型的基础上实现了多尺度空间的图像分割,使多尺度目标均具有较好的分割效果,克服了车牌所占比例小、大小不一对图像分割的影响。将视觉注意机制中的数据驱动模式和任务驱动模式相结合,通过对不同尺度空间分割结果中目标特征尺度与最佳尺度的确定,实现多尺度空间中感兴趣目标的精确定位,实验结果表明该模型具有较好的最佳尺度分割定位多目标的功能。
ABSTRACT:Vehicle image segmentation is the most fundamental and important step in a vehicle detection system. The quality of the vehicle image segmentation has a direct impact on the accuracy and efficiency of the subsequent image processing. However, it is always of great importance for intelligence transportation field to investigate an accurate and practical vehicle image segmentation model under the natural light environment. The segmentation model based on human vision is the research direction of intelligent transportation system for information processing in the future.Under this background, a vehicle segmentation method with visual neuron characteristic has been studied on the basis of Pulse Coupled Neural Networks (PCNN) model from both theory and application. The main research contents and innovation contributions of this thesis are summarized as follows:
(1) The vehicle image segmentation using the traditional PCNN model usually suffers from troubles of over-segmentation and under-segmentation in the license plate area. Under this circumstance, a method for choosing optimal parameters in PCNN model is proposed. The initial threshold of PCNN segmentation model is set with Otsu algorithm, the connection coefficients are updated using the mean square difference of neurons within the local area and Hebb rule is used to calculate the connection coefficient matrix. The experimental results demonstrate that the optimized PCNN model can reduce the number of iterations during image segmentation and enhance self-adaptive segmentation effect of PCNN model.
(2) A vehicle shadow elimination model is proposed to reduce the interference from the shadows in the license plate segmentation.The model combine the optimized PCNN with the shadow attributes. Meanwhile, there is no need to construct the background model and the shadow model. By performing the segmentation on both gray and hue component, vehicle and shadow are separated in each information channel. The image with the removed shadow is finally obtained by merging the segmentation results of the two information channel. The experimental results show that the model not only eliminates the vehicle shadow, but also keeps more details of the license plate and the car logo. Shadow elimination rate further validate the effectiveness of the algorithm for eliminating shadows.
(3) To handle the sunlight and diffuse reflection of the vehicle body, a Receptive Field-Pulse Coupled Neural Networks (RF-PCNN) model is proposed, where the feedback domain linking matrix is determined by neurons receptive field model. This new RF-PCNN model has both directivits and scales.The function of visual cells to segment an image can be simulated more efficiently. The experimental results show that the RF-PCNN model improves the effect of license plate image segmentation under natural environment. A high boundary detection rate has been achieved for the characters and the over-segmentation and under-segmentation problems have been solved in the vehicle image segmentation with complex backgrounds.
(4) The segementation effects of the license plate are influenced by many factors, such as small proportion, unfixed locations, variant sizes and variant illuminations. Aiming at solving the above problems, an image segmentation method based on the Visual Attention Mechanism Pulse Coupled Neural Networks (VAMPCNN) is proposed. This model realizes multi-scale space image segmentation on the basis of the RF-PCNN model, which achieves better segmentation effect for multi-scale targets and overcomes the influence of small proportion and variant sizes of license plate on image segmentation.The model combines data-driven mode with the task-driven mode in the visual attention mechanism, Through the determination of the target's characteristic scale and the optimal scale, it can locate the interesting targets in the multi-scale space. The experimental results show that the model has the function to position segmentation multi-targets at optimal scale.
引文
[1]章毓晋.计算机视觉教程[M].北京：人民邮电出版社,2011,100-120.
[2]Marr D. Vision:a computational investigation into the human representation and processing of visual information [M]. Cambridge:The MIT Press,1982,187-217.
[3]郑志刚.高精度摄像机标定和鲁棒立体匹配算法研究[D].合肥：中国科学技术大学,模式识别与智能系统,2008,4,62-72.
[4]李英姿,张飞舟.智能交通系统中地理信息系统的研究[J].中国公路学报,2000,13(3)：97-100.
[5]王笑京,李斌,高海龙等.第十届智能交通系统世界大会概况和我国发展方向的讨论[J].交通运输系统工程与信息,2004,4(2)：9-16.
[6]V. DiLecce, A. Amato. Route planning and user interface for an advanced intelligent transport system [J]. IET Intelligent Transport Systems,2011,5(3):149-158.
[7]陈远.复杂场景中视觉运动目标检测与跟踪[D],武汉：华中科技大学,2008,8,69－75.
[8]鲜海滢.基于图像时空梯度的运动目标检测技术研究[D],成都：电子科技大学,2009,3,1-14.
[9]Tenenbaum J M, Fischler M A, Barrow S T. A structural basis for image description[J]. Comput Graphics Image Process,1980,12(4):407-425.
[10].Keller Christoph G,Dang Thao, Fritz Hans, et al. Active pedestrian safety by automatic braking and evasive steering[J].IEEE Transactions on Intelligent Transportation Systems, 2011,12(4):1292-1304.
[11]Milanes Vicente, Llorca David F, Villagra Jorge, et al. Vision-based active safety system for automatic stopping [J].Expert Systems with Applications,2012,39(12):11234-11242.
[12]Li Linjing, Li Xin, Cheng Changjian, et al. Research collaboration and ITS topic evolution: 10 years at T-ITS [J].IEEE Transactions on Intelligent Transportation Systems,2010,11(3): 517-523.
[13]Kowsari T, Beauchemin S S, Cho J. Real-time vehicle detection and tracking using stereo vision and multi-view adaBoost[C]. IEEE 14th International Intelligent Transportation Systems Conference, Washington, DC, United States, October 5-7,2011,1255-1260.
[14]Gulbudak Kemal, Yayla Pasa, Yayla Yesim. Development of a cornering bench fatigue test for the validation of a lightweight commercial vehicle front hub [J]. Journal of Failure Analysis and Prevention,2011,11(5):514-521.
[15]Frendo F, Rosellini W. Experimental and numerical analysis of the roller-bench endurance test on a motorscooter [J]. Journal of Automobile Engineering,2009,223(5):639-650.
[16]闻帆.基于视觉的交通路口车辆智能检测技术研究[D].哈尔滨：哈尔滨工业大学,2010,6,1－5.
[17]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,2012,5,1－11.
[18]Tian Yushuang, Yap Kim-Hui, He Yu. Vehicle license plate super-resolution using soft learning prior [J]. Multimedia Tools and Applications,2012,60(3):519-535.
[19]Gazcon, Nicolas Fernando; Chesnevar, et al. Automatic vehicle identification for argentinean license plates using intelligent template matching [J] Pattern Recognition Letters,2012, 33(9):1066-1074.
[20]Romic K, Galic I, Baumgartner A. Character recognition based on region pixel concentration for license plate identification[J].Tehnicki Vjesnik,2012,19(2):321-325.
[21]Shapiro L.G, Stockman GC. Computer Vision. [M].Prentice Hall Inc.,2001,233-340.
[22]章毓晋.图像分割[M].北京：科学出版社,2001,1－7.
[23]孙即祥.图象处理[M].北京：科学出版社,2009,128-234.
[24]刘青,汪同庆,李宏友.基于正交高斯赫密特矩的车辆检测算法[J].计算机应用,2009,29(B06)：238-239.
[25]淦玲莉,徐加,张飞.基于最大熵法的汽车毫米波雷达信号的处理[J].探测与控制学报,2006,28(5)：65-68.
[26]潘喆.智能交通x图像阈值分割方法研究[D].南京：南京航空航天大学,2010,16-23.
[27]安明伟,陈启美,郭宗良.基于路况视频的气象能见度检测方法与系统设计[J].仪器仪表学报,2010,5：1148-1153.
[28]陈志猛,刘东权.基于对称性的快速车辆检测方法[J].计算机工程与设计,2012,33(3)：1042-1046.
[29]梁玮,罗剑锋,贾云得,刘万春.一种复杂背景下的多车牌图像分割与识别方法[J].北京理工大学学报,2003,23(1)：91-94.
[30]卓炜,齐春.基于边缘信息的车牌定位[J].中国科技论文在线,2011,6(4)：305-309.
[31]Ji Zexuan,Xia Yong, Chen Qiang, et al. Fuzzy c-means clustering with weighted image patch for image segmentation[J].Applied Soft Computing Journal,2012,12 (6):1659-1667.
[32]Liu Ling-xing,Tan Guan-zheng,Soliman M. Sami. Color image segmentation using mean shift and improved ant clustering [J]. Journal of Central South University of Technology,2012,19 (4):1040-1048.
[33]Li Yangyang,Shi Hongzhu,Jiao Licheng,Liu Ruochen. Quantum evolutionary clustering algorithm based on watershed applied to SAR image segmentation [J]. Neurocomputing,2012, 87:90-98.
[34]Wu Jian,Xia Jie,Chen Jian-ming,Cui Zhi-ming. Adaptive detection of moving vehicle based on on-line clustering [J]. Journal of Computers,2011,6 (10):2045-2052.
[35]Kass M, Witkin A, Terzopoulos D. Snakes:active contour models [J].International Journal of Computer Vision,1987,1(4):321-331.
[36]李培华,张田文.主动轮廓线模型(蛇模型)综述[J].软件学报,2000,11(6)：751-757.
[37]陈波,赖剑煌.用于图像分割的活动轮廓模型综述[J].中国图象图形学报,2007,12(1)：11-20.
[38]Kovacs Andrea, Sziranyi Tamas. Harris function based active contour external force for image segmentation [J].Pattern Recognition Letters,2012,33(9):1180-1187.
[39]赵在新.变分方法与模糊聚类在图像分割中的应用研究[D].长沙：国防科学技术大学,2011,2-7.
[40]Caselles V, Catte F, Coll T. Ageometric model for active contours in image processing [J]. Numerische Mathematik,1993,66:1-31.
[41]Caselles V, Kimmel R, Sapiro G. Geodesicactive contours [J].International Journal of Computer Vision,1997,22(1):61-79.
[42]Mumford D, Shah J. Optimal approximation by piecewise smooth functions and associated variational problems [J].Comm..Pure.Appl.Math.1989,42:577-685.
[43]Greig D, Porteous B, Seheult A. Exactmaximum a posteriori estimation for binary images [J]. Journal of the Royal Statistical Society,1989,51 (2):271-279.
[44]Boykov Y, Funkalea G. Graph cuts and efficient N-D image segmentation [J]. International Journal of Computer Vision,2006,70 (2):109-131.
[45]Boykov Y, Jolly M P. Interactive organ segmentation using graph cuts. Proceedings of the 3rd International Conference on Medical Image Computing and Computer-Assisted Intervention. Pittsburgh, USA:Springer,2000.276-286.
[46]刘松涛,殷福亮.基于图割的图像分割方法及其新进展[J].自动化学报,2012,38(6)：911-922.
[47]高庆吉,张磊.基于交叉视觉皮质模型的非结构化道路检测算法[J].电子学报,2011,39(10)：2366-2371.
[48]Fleyeh Hasan,Bin Mumtaz, Al-Hasanat R. M. Adaptive shadow and highlight invariant colour segmentation for traffic sign recognition based on kohonen SOM[J].Journal of Intelligent Systems,2011,20(1):15-31.
[49]郭金基,瑚琦,顾玲娟.基于遗传退火方法的灰度图像阈值选择算法[J].计算机仿真,2010,4：210-214.
[50]寿天德.视觉信息处理的脑机制[M]，第二版.合肥：科学技术出版社,2010,1-15.
[51]钟志鹏,王涌天,陈靖,等.一个基于移动视觉搜索技术的博物馆导览系统[J].计算机辅助设计与图形学学报,2012,24(4)：555-562.
[52]马义德,绽琨,王兆滨.脉冲耦合神经网络图像处理,第二版.北京：高等教育出版社,2008,4-20.
[53]Hodgkin A L, Huxley A F. A quantitative description of membrane current and its application to conduction and excitation in nerve[J].Journal of Physiology,1952,117:500-544.
[54]FitzHugh R. Impulses and physiological states in theoretical models of nerve membrane [J].Biophysics J,1961,1:445-466.
[55]Nagumo J, Arimoto S, Yoshizawa S. An active pulse transmission line stimulating nerve axon [J]. Proc.IRE,1962,50:2061-2070.
[56]Labbi A, Milanese R, Bosch H. A network of FitzHugh-Nagumo oscillators for object segmentation[C]. NOLTA97:Proc. Of International Symposium on Nonlinear Theory and Applications, Nov.29-Dec.3, Hawaii 1997:581-584.
[57]Eckhorn R, Reitboeck H J, Arndt M, et al. Feature linking via synchronization among distributed assemblies:simulation of results from cat visual cortex [J]. Neural Computation, 1990,2(3):293-307.
[58]Rybak I A, Shevtsova N A, Sandler V A. The model of a neural network visual processor [J]. Neurocomputing,1992,4:93-102.
[59]Parodi O, Combe P, Ducom J C. Temporal encoding in vision:coding by spike arrival times leads to oscillations in the case of moving targets [J]. Biol.Cybern,1996,74:497-509.
[60]姚畅,陈后金.病变视网膜图像血管网络的自动分割[J].电子学报,2010,38(5)：1226-1232.
[61]严春满,郭宝龙,马义德,等.一种新的基于双层PCNN的自适应图像分割算法[J].光电子·激光2011,22(7)：1102-1106.
[62]汪源源,焦静.改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J].光学精密工程,2011,19(6)：1398-1405.
[63]张云强,张培林,王国德.基于背景色彩和PCNN的磨粒图像单通道分割[J].电子测量与仪器学报,2012,26(4)：352-358.
[64]施俊,常谦,钟瑾.基于三维脉冲耦合神经网络模型的医学图像分割[J].应用科学学报,2010,28(6)：609-615.
[65]祝双武,郝重阳.一种基于改进型PCNN的织物疵点图像自适应分割方法[J].电子学报,2012,40(3)：611-616.
[66]Vinod V, Kimbahune M R, Nelesh J. Blood cell image segmentation and counting [J]. International Journal of Engineering Science and Technology,2011,3(3):2448-2453.
[67]Wang Z, Ma Y, Cheng F, et al. Review of pulse-coupled neural networks [J]. Image and Vision Computing,2010,28(1):5-13.
[68]Song Yin-mao, Zhu Xiao-hui, Liu Guo-le. One segmentation algorithm of multi-target image based on improved PCNN[C].IEEE The 2nd Intelligent Systems and Applications (ISA), Wuhan, China,22-23 May,2010,510-513.
[69]H. Berg, R. Olsson, T. Lindblad, et al. Automatic design of pulse coupled neurons for image segmentation [J]. Neurocomputing,2008,71(10):1980-1993.
[70]王志慧,赵保军,沈庭芝.基于MMPN和可调节链接强度的图像融合[J].电子学报,2010,38(5)：1162-1166.
[71]J.C. Fu, C.C. Chen, J.W. Chai, et al. Image segmentation by EM-based adaptive pulse coupled neural networks in brain magnetic resonance imaging [J]. Computerized Medical Imaging and Graphics,2010,34(4):308-320.
[72]Yuli Chen, Sung-kee Park, Yide Ma, et al. A new automatic parameter setting method of a simplified PCNN for image segmentation[J]. IEEE Transactions on Neural Networks,2011, 22(6):880-891.
[73]魏伟一,李战明.基于改进PCNN和互信息熵的自动图像分割[J].计算机工程,2010,36(13)：199-204.
[74]卢桂馥,王勇,窦易文.一种参数自动寻优的PCNN图像分割算法[J].计算机工程与应用,2010,46(13)：145-157.
[75]谭颖芳,周冬明,赵东风等Unit-Linking PCNN和图像熵的彩色图像分割与边缘检测[J].计算机工程与应用,2009,45(12)：174-180.
[76]Masato Yonekawa, Hiroaki Kurokawa. An automatic parameter adjustment method of pulse coupled neural network for image segmentation[C].IEEE 19th International Conference on Artificial Neural Networks (ICANN 2009), Cyprus, Sep.14-17,2009,834-843.
[77]Chen Jun, Tadashi Shibata. A neuron-MOS-based VLSI implementation of pulse coupled neural networks for image feature generation [J]. IEEE Transactions on Circuits and Systems-I:Regular Papers,2010,57(6):1143-1151.
[78]邓翔宇,马义德.PCNN参数自适应设定及其模型的改进[J].电子学报,2012,40(5)：955－964.
[79]R. Eckhorn. Neural mechanisms of scene segmentation:recordings from the visual cortex suggest basic circuits for linking field models [J]. Neural Networks,1999,10:464-479.
[80]R. Eckhorn, A. M. Gail, A. Bruns, et al. Different types of signal coupling in the visual cortex rrelated to neural mechanisms of associative processing and perception [J]. Neural Networks, 2004,15:1039-1052.
[81]R. Eckhorn, A. Gail, A. Bruns. Dynamic cortical cooperation related to visual perception [J]. Neural Networks,2003,2:1563-1568.
[82]J. L. Johnson. Pulse-coupled neural nets:translation, rotation, scale, distortion and intensity signal invariance for images [J]. Applied Optics,1994,33(26):6239-6253.
[83]Xiao Zhiheng, Zhou Shichong. Automatic segmentation of breast tumor in ultrasound image with simplified PCNN and improved fuzzy mutual information[C]. Visual Communications and Image Processing 2010. Huangshan, China:SPIE,2010,7744:241-245.
[84]马义德,王兆滨,张新国,等.一种生物彩色图像自动分割新方案[J].哈尔滨工业大学学报,2009,41(9)：173-175.
[85]宋寅卯,刘国乐.一种改进的PCNN图像分割算法[J].电路与系统学报,2010,15(1)：77-81.
[86]赵峙江,赵春晖,张志宏.一种新的PCNN模型参数估算方法[J].电子学报,2007,35(5)：996-1000.
[87]Zhang Yu-dong, Wu Le-nan, Wang Shui-hua, et al. Color image enhancement based on HVS and PCNN [J]. Science China Information Sciences,2010,53(10):1963-1976.
[88]武治国,王延杰,李桂菊.应用小波变换的自适应脉冲耦合神经网络在图像融合中的应用[J].光学精密工程,2010,18(3)：708-715.
[89]邓翔宇.基于PCNN的图像边缘检测方法[J].自动化与仪器仪表,2012,3：130-134.
[90]刘晨晨,李晨,张之猛.基于PCNN的声纳图像纹理特征提取[J].自动化仪表,2009,30(2)：18-20.
[91]马义德,李廉,绽琨,等.脉冲耦合神经网络与数字图像处理[M].北京：科学出版社.2008,57-68.
[92]Otsu N. A threshold selection method from gray-level histogram [J].IEEE Trans. on System, Man and Cybernetics,1979,9(1):62-66.
[93]姚畅.眼底图像分割方法的研究及其应用[D].北京：北京交通大学,2009,52-55.
[94]高明俊,高康林.基于图像PCNN去噪和保持边缘的算法研究[J].数字技术与应用2011,11：135-137.
[95]张志宏,马光胜.PCNN模型参数优化与多阈值图像分割[J].哈尔滨工业大学学报,2009,41(3)：240-242.
[96]侯媛彬,杜京义,汪梅.神经网络[M].西安：西安电子科技大学出版社,2007：21-25.
[97]Fredric M. Ham Ivica Kostanic.叶世伟,王海娟译.神经计算原理[M].北京：机械工业出版社,2007,16-66.
[98]Jung C. R. Efficient background subtraction and shadow removal for monochromatic video sequences [J]. IEEE Transaction on Multimedia,2009,11(3):571-577.
[99]Argasm M, Toral V S, Milla J M, et al. A shadow removal algorithm for vehicle detection based on reflectance ratio and edge density[C].2010 13th International IEEE Annual Conference on Intelligent Transportation Systems. Madeira Island:Annual Conference Proceedings,2010:1123-1128.
[100]黄鑫娟,周洁敏.基于光度特性和多梯度分析的运动阴影去除法[J].计算机应用,2010,30(2)：370-373.
[101]Gao Liang, Xing Jian-ping, Luo Xi-ling. Moving cast shadow elimination based on luminance and texture features for traffic flow[C]. IEEE 5th International Conference on Communications and Networking. Beijing, China:IEEE Press,2010:1023-1026.
[102]Zhigang Liu, Fei Zhao, Hua Yang. A new method of moving shadow elimination combining texture and chrominance of moving foreground region based on criterion[C].The 8th World Congress on Intelligent Control and Automation. Jinan, China:IEEE Press, 2010:6282-6286.
[103]Xing Chao, Li Yan-jun, Zhang Ke, et al. Shadow detecting using particle swarm optimization and the kolmogorov test [J]. Computers & Mathematics with Applications,2011, 62(7):2704-2711.
[104]Szczepanski S, Wojcikowski M, Pankiewicz B, et al. FPGA and ASIC implementation of the algorithm for traffic monitoring in urban areas [J]. Bulletin of the Polish Academy of Sciences Technical,2011,59(2):137-140.
[105]孙君顶,赵珊.图像低层特征提取与检索技术[M].北京：电子工业出版社,2009,1-7.
[106]陈志刚,陈爱华,崔跃利,等.多尺度无监督彩色图像分割[J].光子学报,2011,40(10)：1553-1559.
[107]李慧娜,郭超峰.灰度共生矩阵在指纹图像分割中的应用[J].数据采集与处理,2012,1：63-67.
[108]Zhou Kai-jun, Yang Chun-hua, Gui Wei-hua, et al. Clustering-driven watershed adaptive segmentation of bubble image [J]. Journal of Central South University of Technology, 2010,17(5):1049-1057.
[109]余孟泽,刘正熙,骆键,等.融合纹理特征和阴影属性的阴影检测方法[J].计算机工程与设计,2011,32(10)：3431-3434.
[110]Prati A, Mikic I, Trivedi M M, et al. Detecting moving shadows:algorithms and evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25(7):918-923.
[111]孙剑芬.视频监控系统中运动目标检测算法的研究[D].无锡：江南大学,2008,37-39.
[112]董蓉,李勃,陈启美.路况视频中HSV彩色不变量阴影检测法研究与改进[J].中国图象图形学报,2009,14(12)：2483-2488.
[113]辛慧杰,刘明才,牟连泳,等.基于阴影属性的运动阴影检测方法[J].大连民族学院学报,2010,12(3)：254-257.
[114]Cucchiara R, Grana C, Piccardi M, et al. Improving shadow suppression in moving object detection with HSV color information[C]. IEEE International Conference on Intelligent Transportation Systems, Ocaland,USA,2001:334-339.
[115]顾晓东,郭仕德,余道衡.基于PCNN的图像阴影处理新方法[J].电子与信息学报,2004,26(3)：479-483.
[116]王玥,王树根.高分辨率遥感影像阴影检测与补偿的主成分分析方法[J].应用科学学报,2010,28(2)：136-141.
[117]Liu Shangwang, He Dongjian, Liang Xinhong. An improved hybrid model for automatic salient region detection. Signal Processing Letters[J].2012,19(4):207-210.
[118]付朝阳,郭雷,常威威.基于小波变换和多通道脉冲耦合神经网络的高光谱图像融合[J].吉林大学学报,2011,41(3)：938-843.
[119]辛国江,邹北骥,李建锋,等.结合最大方差比准则和PCNN模型的图像分割[J].中国图象图形学报,2011,16(7)：1310-1316.
[120]姚畅,陈后金,荆涛,等.一种基于改进的PCNN的视网膜血管树提取方法[J].光电子·激光,2011,22(11)：1745-1750.
[121]寿天德.视觉信息处理的脑机制[M].合肥：中国科学技术大学出版社,2010：150-170.
[122]Kuffler S W. Discharge Patterns and Functional Organization of Mammalian Retina [J]. Neurophysiology,1953,16:37-68.
[123]R.W.Rodieck, JJ.Stone. Analysis of receptive fields of cat retina ganglin cells[J]. Neurophysiology,1965,28:833-848.
[124]J.G.Daugman. Principles of visual neuronal receptive field organization:two-dimensional spectral consequences[C]. IEEE International Conference on Systems, Man and Cybernetics, New York, USA,1984:457-464.
[125]汪云九,齐翔林.初级视觉的Gabor函数模型的研究进展[J].生物物理学报1993,9(3)：508-513.
[126]窦燕.基于空间和物体的视觉注意计算方法及实验研究[D].秦皇岛：燕山大学,2010,12-13.
[127]祝文骏.基于视觉皮层网络的物体整体特征分析与算法研究[D].上海：上海交通大学,2011,11－14.
[128]John L, Johnson, Mary Lou Padgett. PCNN models and applications [J].Transactions on Neural Networks,1999,10(3):480-498.
[129]于江波,陈后金.PCNN模型的改进及其在医学图像处理中的应用[J].电子与信息学报,2007,29(10)：2316-2320.
[130]刘国英,马国锐,王雷光,等.基于Markov随机场的小波域图像建模及分割[M].北京：科学出版社,2010：15-31.
[131]Pan Chen,Park Dong Sun,Yang Yong, et al. Leukocyte image segmentation by visual attention and extreme learning machine[J].Neural Computing and Applications,2012,21(6): 1217-1227.
[132]Itti Laurent, Koch Christof, Niebur Ernst. Model of saliency-based visual attention for rapid scene analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998,20(11):1254-1259
[133]罗四维.视觉信息认知计算理论[M].北京：科学出版社,2010：181-219.
[134]罗四维.视觉感知系统信息处理理论[M].北京：电子工业出版社,2006：107-123.
[135]刘琼,秦世引,李志成.视觉选择性注意的模型化计算及其应用前景[J].科技导报,2010,28(1)：107-116.
[136]HU M K. Visual pattern recognition by moment invariants [J]. IEEE Transactions on Information Theory,1962,8(2):179-187.
[137]杨娜,韩焱.矩在复杂构件射线图像识别中的应用[J].探测与控制学报,2007,29(4)：42-44.
[138]潘泉,程咏梅,杜亚娟,等.离散不变矩算法及其在目标识别中的应用[J].电子与信息学报,2001,23(1)：30-36.
[139]冯占国,徐玉如.基于不变性特征的水下目标特征提取[J].哈尔滨工程大学学报,2007,28(12)：1343-1347.
[140]刘勃.基于脉冲耦合神经网络的图像处理若干问题研究[D].西安：西安电子科技大学,2011,70-77.
[141]章毓晋.图像分析[M].第二版.北京：清华大学出版社,2005：177-201.
[2]Marr D. Vision:a computational investigation into the human representation and processing of visual information [M]. Cambridge:The MIT Press,1982,187-217.
[3]郑志刚.高精度摄像机标定和鲁棒立体匹配算法研究[D].合肥：中国科学技术大学,模式识别与智能系统,2008,4,62-72.
[4]李英姿,张飞舟.智能交通系统中地理信息系统的研究[J].中国公路学报,2000,13(3)：97-100.
[5]王笑京,李斌,高海龙等.第十届智能交通系统世界大会概况和我国发展方向的讨论[J].交通运输系统工程与信息,2004,4(2)：9-16.
[6]V. DiLecce, A. Amato. Route planning and user interface for an advanced intelligent transport system [J]. IET Intelligent Transport Systems,2011,5(3):149-158.
[7]陈远.复杂场景中视觉运动目标检测与跟踪[D],武汉：华中科技大学,2008,8,69－75.
[8]鲜海滢.基于图像时空梯度的运动目标检测技术研究[D],成都：电子科技大学,2009,3,1-14.
[9]Tenenbaum J M, Fischler M A, Barrow S T. A structural basis for image description[J]. Comput Graphics Image Process,1980,12(4):407-425.
[10].Keller Christoph G,Dang Thao, Fritz Hans, et al. Active pedestrian safety by automatic braking and evasive steering[J].IEEE Transactions on Intelligent Transportation Systems, 2011,12(4):1292-1304.
[11]Milanes Vicente, Llorca David F, Villagra Jorge, et al. Vision-based active safety system for automatic stopping [J].Expert Systems with Applications,2012,39(12):11234-11242.
[12]Li Linjing, Li Xin, Cheng Changjian, et al. Research collaboration and ITS topic evolution: 10 years at T-ITS [J].IEEE Transactions on Intelligent Transportation Systems,2010,11(3): 517-523.
[13]Kowsari T, Beauchemin S S, Cho J. Real-time vehicle detection and tracking using stereo vision and multi-view adaBoost[C]. IEEE 14th International Intelligent Transportation Systems Conference, Washington, DC, United States, October 5-7,2011,1255-1260.
[14]Gulbudak Kemal, Yayla Pasa, Yayla Yesim. Development of a cornering bench fatigue test for the validation of a lightweight commercial vehicle front hub [J]. Journal of Failure Analysis and Prevention,2011,11(5):514-521.
[15]Frendo F, Rosellini W. Experimental and numerical analysis of the roller-bench endurance test on a motorscooter [J]. Journal of Automobile Engineering,2009,223(5):639-650.
[16]闻帆.基于视觉的交通路口车辆智能检测技术研究[D].哈尔滨：哈尔滨工业大学,2010,6,1－5.
[17]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,2012,5,1－11.
[18]Tian Yushuang, Yap Kim-Hui, He Yu. Vehicle license plate super-resolution using soft learning prior [J]. Multimedia Tools and Applications,2012,60(3):519-535.
[19]Gazcon, Nicolas Fernando; Chesnevar, et al. Automatic vehicle identification for argentinean license plates using intelligent template matching [J] Pattern Recognition Letters,2012, 33(9):1066-1074.
[20]Romic K, Galic I, Baumgartner A. Character recognition based on region pixel concentration for license plate identification[J].Tehnicki Vjesnik,2012,19(2):321-325.
[21]Shapiro L.G, Stockman GC. Computer Vision. [M].Prentice Hall Inc.,2001,233-340.
[22]章毓晋.图像分割[M].北京：科学出版社,2001,1－7.
[23]孙即祥.图象处理[M].北京：科学出版社,2009,128-234.
[24]刘青,汪同庆,李宏友.基于正交高斯赫密特矩的车辆检测算法[J].计算机应用,2009,29(B06)：238-239.
[25]淦玲莉,徐加,张飞.基于最大熵法的汽车毫米波雷达信号的处理[J].探测与控制学报,2006,28(5)：65-68.
[26]潘喆.智能交通x图像阈值分割方法研究[D].南京：南京航空航天大学,2010,16-23.
[27]安明伟,陈启美,郭宗良.基于路况视频的气象能见度检测方法与系统设计[J].仪器仪表学报,2010,5：1148-1153.
[28]陈志猛,刘东权.基于对称性的快速车辆检测方法[J].计算机工程与设计,2012,33(3)：1042-1046.
[29]梁玮,罗剑锋,贾云得,刘万春.一种复杂背景下的多车牌图像分割与识别方法[J].北京理工大学学报,2003,23(1)：91-94.
[30]卓炜,齐春.基于边缘信息的车牌定位[J].中国科技论文在线,2011,6(4)：305-309.
[31]Ji Zexuan,Xia Yong, Chen Qiang, et al. Fuzzy c-means clustering with weighted image patch for image segmentation[J].Applied Soft Computing Journal,2012,12 (6):1659-1667.
[32]Liu Ling-xing,Tan Guan-zheng,Soliman M. Sami. Color image segmentation using mean shift and improved ant clustering [J]. Journal of Central South University of Technology,2012,19 (4):1040-1048.
[33]Li Yangyang,Shi Hongzhu,Jiao Licheng,Liu Ruochen. Quantum evolutionary clustering algorithm based on watershed applied to SAR image segmentation [J]. Neurocomputing,2012, 87:90-98.
[34]Wu Jian,Xia Jie,Chen Jian-ming,Cui Zhi-ming. Adaptive detection of moving vehicle based on on-line clustering [J]. Journal of Computers,2011,6 (10):2045-2052.
[35]Kass M, Witkin A, Terzopoulos D. Snakes:active contour models [J].International Journal of Computer Vision,1987,1(4):321-331.
[36]李培华,张田文.主动轮廓线模型(蛇模型)综述[J].软件学报,2000,11(6)：751-757.
[37]陈波,赖剑煌.用于图像分割的活动轮廓模型综述[J].中国图象图形学报,2007,12(1)：11-20.
[38]Kovacs Andrea, Sziranyi Tamas. Harris function based active contour external force for image segmentation [J].Pattern Recognition Letters,2012,33(9):1180-1187.
[39]赵在新.变分方法与模糊聚类在图像分割中的应用研究[D].长沙：国防科学技术大学,2011,2-7.
[40]Caselles V, Catte F, Coll T. Ageometric model for active contours in image processing [J]. Numerische Mathematik,1993,66:1-31.
[41]Caselles V, Kimmel R, Sapiro G. Geodesicactive contours [J].International Journal of Computer Vision,1997,22(1):61-79.
[42]Mumford D, Shah J. Optimal approximation by piecewise smooth functions and associated variational problems [J].Comm..Pure.Appl.Math.1989,42:577-685.
[43]Greig D, Porteous B, Seheult A. Exactmaximum a posteriori estimation for binary images [J]. Journal of the Royal Statistical Society,1989,51 (2):271-279.
[44]Boykov Y, Funkalea G. Graph cuts and efficient N-D image segmentation [J]. International Journal of Computer Vision,2006,70 (2):109-131.
[45]Boykov Y, Jolly M P. Interactive organ segmentation using graph cuts. Proceedings of the 3rd International Conference on Medical Image Computing and Computer-Assisted Intervention. Pittsburgh, USA:Springer,2000.276-286.
[46]刘松涛,殷福亮.基于图割的图像分割方法及其新进展[J].自动化学报,2012,38(6)：911-922.
[47]高庆吉,张磊.基于交叉视觉皮质模型的非结构化道路检测算法[J].电子学报,2011,39(10)：2366-2371.
[48]Fleyeh Hasan,Bin Mumtaz, Al-Hasanat R. M. Adaptive shadow and highlight invariant colour segmentation for traffic sign recognition based on kohonen SOM[J].Journal of Intelligent Systems,2011,20(1):15-31.
[49]郭金基,瑚琦,顾玲娟.基于遗传退火方法的灰度图像阈值选择算法[J].计算机仿真,2010,4：210-214.
[50]寿天德.视觉信息处理的脑机制[M]，第二版.合肥：科学技术出版社,2010,1-15.
[51]钟志鹏,王涌天,陈靖,等.一个基于移动视觉搜索技术的博物馆导览系统[J].计算机辅助设计与图形学学报,2012,24(4)：555-562.
[52]马义德,绽琨,王兆滨.脉冲耦合神经网络图像处理,第二版.北京：高等教育出版社,2008,4-20.
[53]Hodgkin A L, Huxley A F. A quantitative description of membrane current and its application to conduction and excitation in nerve[J].Journal of Physiology,1952,117:500-544.
[54]FitzHugh R. Impulses and physiological states in theoretical models of nerve membrane [J].Biophysics J,1961,1:445-466.
[55]Nagumo J, Arimoto S, Yoshizawa S. An active pulse transmission line stimulating nerve axon [J]. Proc.IRE,1962,50:2061-2070.
[56]Labbi A, Milanese R, Bosch H. A network of FitzHugh-Nagumo oscillators for object segmentation[C]. NOLTA97:Proc. Of International Symposium on Nonlinear Theory and Applications, Nov.29-Dec.3, Hawaii 1997:581-584.
[57]Eckhorn R, Reitboeck H J, Arndt M, et al. Feature linking via synchronization among distributed assemblies:simulation of results from cat visual cortex [J]. Neural Computation, 1990,2(3):293-307.
[58]Rybak I A, Shevtsova N A, Sandler V A. The model of a neural network visual processor [J]. Neurocomputing,1992,4:93-102.
[59]Parodi O, Combe P, Ducom J C. Temporal encoding in vision:coding by spike arrival times leads to oscillations in the case of moving targets [J]. Biol.Cybern,1996,74:497-509.
[60]姚畅,陈后金.病变视网膜图像血管网络的自动分割[J].电子学报,2010,38(5)：1226-1232.
[61]严春满,郭宝龙,马义德,等.一种新的基于双层PCNN的自适应图像分割算法[J].光电子·激光2011,22(7)：1102-1106.
[62]汪源源,焦静.改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J].光学精密工程,2011,19(6)：1398-1405.
[63]张云强,张培林,王国德.基于背景色彩和PCNN的磨粒图像单通道分割[J].电子测量与仪器学报,2012,26(4)：352-358.
[64]施俊,常谦,钟瑾.基于三维脉冲耦合神经网络模型的医学图像分割[J].应用科学学报,2010,28(6)：609-615.
[65]祝双武,郝重阳.一种基于改进型PCNN的织物疵点图像自适应分割方法[J].电子学报,2012,40(3)：611-616.
[66]Vinod V, Kimbahune M R, Nelesh J. Blood cell image segmentation and counting [J]. International Journal of Engineering Science and Technology,2011,3(3):2448-2453.
[67]Wang Z, Ma Y, Cheng F, et al. Review of pulse-coupled neural networks [J]. Image and Vision Computing,2010,28(1):5-13.
[68]Song Yin-mao, Zhu Xiao-hui, Liu Guo-le. One segmentation algorithm of multi-target image based on improved PCNN[C].IEEE The 2nd Intelligent Systems and Applications (ISA), Wuhan, China,22-23 May,2010,510-513.
[69]H. Berg, R. Olsson, T. Lindblad, et al. Automatic design of pulse coupled neurons for image segmentation [J]. Neurocomputing,2008,71(10):1980-1993.
[70]王志慧,赵保军,沈庭芝.基于MMPN和可调节链接强度的图像融合[J].电子学报,2010,38(5)：1162-1166.
[71]J.C. Fu, C.C. Chen, J.W. Chai, et al. Image segmentation by EM-based adaptive pulse coupled neural networks in brain magnetic resonance imaging [J]. Computerized Medical Imaging and Graphics,2010,34(4):308-320.
[72]Yuli Chen, Sung-kee Park, Yide Ma, et al. A new automatic parameter setting method of a simplified PCNN for image segmentation[J]. IEEE Transactions on Neural Networks,2011, 22(6):880-891.
[73]魏伟一,李战明.基于改进PCNN和互信息熵的自动图像分割[J].计算机工程,2010,36(13)：199-204.
[74]卢桂馥,王勇,窦易文.一种参数自动寻优的PCNN图像分割算法[J].计算机工程与应用,2010,46(13)：145-157.
[75]谭颖芳,周冬明,赵东风等Unit-Linking PCNN和图像熵的彩色图像分割与边缘检测[J].计算机工程与应用,2009,45(12)：174-180.
[76]Masato Yonekawa, Hiroaki Kurokawa. An automatic parameter adjustment method of pulse coupled neural network for image segmentation[C].IEEE 19th International Conference on Artificial Neural Networks (ICANN 2009), Cyprus, Sep.14-17,2009,834-843.
[77]Chen Jun, Tadashi Shibata. A neuron-MOS-based VLSI implementation of pulse coupled neural networks for image feature generation [J]. IEEE Transactions on Circuits and Systems-I:Regular Papers,2010,57(6):1143-1151.
[78]邓翔宇,马义德.PCNN参数自适应设定及其模型的改进[J].电子学报,2012,40(5)：955－964.
[79]R. Eckhorn. Neural mechanisms of scene segmentation:recordings from the visual cortex suggest basic circuits for linking field models [J]. Neural Networks,1999,10:464-479.
[80]R. Eckhorn, A. M. Gail, A. Bruns, et al. Different types of signal coupling in the visual cortex rrelated to neural mechanisms of associative processing and perception [J]. Neural Networks, 2004,15:1039-1052.
[81]R. Eckhorn, A. Gail, A. Bruns. Dynamic cortical cooperation related to visual perception [J]. Neural Networks,2003,2:1563-1568.
[82]J. L. Johnson. Pulse-coupled neural nets:translation, rotation, scale, distortion and intensity signal invariance for images [J]. Applied Optics,1994,33(26):6239-6253.
[83]Xiao Zhiheng, Zhou Shichong. Automatic segmentation of breast tumor in ultrasound image with simplified PCNN and improved fuzzy mutual information[C]. Visual Communications and Image Processing 2010. Huangshan, China:SPIE,2010,7744:241-245.
[84]马义德,王兆滨,张新国,等.一种生物彩色图像自动分割新方案[J].哈尔滨工业大学学报,2009,41(9)：173-175.
[85]宋寅卯,刘国乐.一种改进的PCNN图像分割算法[J].电路与系统学报,2010,15(1)：77-81.
[86]赵峙江,赵春晖,张志宏.一种新的PCNN模型参数估算方法[J].电子学报,2007,35(5)：996-1000.
[87]Zhang Yu-dong, Wu Le-nan, Wang Shui-hua, et al. Color image enhancement based on HVS and PCNN [J]. Science China Information Sciences,2010,53(10):1963-1976.
[88]武治国,王延杰,李桂菊.应用小波变换的自适应脉冲耦合神经网络在图像融合中的应用[J].光学精密工程,2010,18(3)：708-715.
[89]邓翔宇.基于PCNN的图像边缘检测方法[J].自动化与仪器仪表,2012,3：130-134.
[90]刘晨晨,李晨,张之猛.基于PCNN的声纳图像纹理特征提取[J].自动化仪表,2009,30(2)：18-20.
[91]马义德,李廉,绽琨,等.脉冲耦合神经网络与数字图像处理[M].北京：科学出版社.2008,57-68.
[92]Otsu N. A threshold selection method from gray-level histogram [J].IEEE Trans. on System, Man and Cybernetics,1979,9(1):62-66.
[93]姚畅.眼底图像分割方法的研究及其应用[D].北京：北京交通大学,2009,52-55.
[94]高明俊,高康林.基于图像PCNN去噪和保持边缘的算法研究[J].数字技术与应用2011,11：135-137.
[95]张志宏,马光胜.PCNN模型参数优化与多阈值图像分割[J].哈尔滨工业大学学报,2009,41(3)：240-242.
[96]侯媛彬,杜京义,汪梅.神经网络[M].西安：西安电子科技大学出版社,2007：21-25.
[97]Fredric M. Ham Ivica Kostanic.叶世伟,王海娟译.神经计算原理[M].北京：机械工业出版社,2007,16-66.
[98]Jung C. R. Efficient background subtraction and shadow removal for monochromatic video sequences [J]. IEEE Transaction on Multimedia,2009,11(3):571-577.
[99]Argasm M, Toral V S, Milla J M, et al. A shadow removal algorithm for vehicle detection based on reflectance ratio and edge density[C].2010 13th International IEEE Annual Conference on Intelligent Transportation Systems. Madeira Island:Annual Conference Proceedings,2010:1123-1128.
[100]黄鑫娟,周洁敏.基于光度特性和多梯度分析的运动阴影去除法[J].计算机应用,2010,30(2)：370-373.
[101]Gao Liang, Xing Jian-ping, Luo Xi-ling. Moving cast shadow elimination based on luminance and texture features for traffic flow[C]. IEEE 5th International Conference on Communications and Networking. Beijing, China:IEEE Press,2010:1023-1026.
[102]Zhigang Liu, Fei Zhao, Hua Yang. A new method of moving shadow elimination combining texture and chrominance of moving foreground region based on criterion[C].The 8th World Congress on Intelligent Control and Automation. Jinan, China:IEEE Press, 2010:6282-6286.
[103]Xing Chao, Li Yan-jun, Zhang Ke, et al. Shadow detecting using particle swarm optimization and the kolmogorov test [J]. Computers & Mathematics with Applications,2011, 62(7):2704-2711.
[104]Szczepanski S, Wojcikowski M, Pankiewicz B, et al. FPGA and ASIC implementation of the algorithm for traffic monitoring in urban areas [J]. Bulletin of the Polish Academy of Sciences Technical,2011,59(2):137-140.
[105]孙君顶,赵珊.图像低层特征提取与检索技术[M].北京：电子工业出版社,2009,1-7.
[106]陈志刚,陈爱华,崔跃利,等.多尺度无监督彩色图像分割[J].光子学报,2011,40(10)：1553-1559.
[107]李慧娜,郭超峰.灰度共生矩阵在指纹图像分割中的应用[J].数据采集与处理,2012,1：63-67.
[108]Zhou Kai-jun, Yang Chun-hua, Gui Wei-hua, et al. Clustering-driven watershed adaptive segmentation of bubble image [J]. Journal of Central South University of Technology, 2010,17(5):1049-1057.
[109]余孟泽,刘正熙,骆键,等.融合纹理特征和阴影属性的阴影检测方法[J].计算机工程与设计,2011,32(10)：3431-3434.
[110]Prati A, Mikic I, Trivedi M M, et al. Detecting moving shadows:algorithms and evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25(7):918-923.
[111]孙剑芬.视频监控系统中运动目标检测算法的研究[D].无锡：江南大学,2008,37-39.
[112]董蓉,李勃,陈启美.路况视频中HSV彩色不变量阴影检测法研究与改进[J].中国图象图形学报,2009,14(12)：2483-2488.
[113]辛慧杰,刘明才,牟连泳,等.基于阴影属性的运动阴影检测方法[J].大连民族学院学报,2010,12(3)：254-257.
[114]Cucchiara R, Grana C, Piccardi M, et al. Improving shadow suppression in moving object detection with HSV color information[C]. IEEE International Conference on Intelligent Transportation Systems, Ocaland,USA,2001:334-339.
[115]顾晓东,郭仕德,余道衡.基于PCNN的图像阴影处理新方法[J].电子与信息学报,2004,26(3)：479-483.
[116]王玥,王树根.高分辨率遥感影像阴影检测与补偿的主成分分析方法[J].应用科学学报,2010,28(2)：136-141.
[117]Liu Shangwang, He Dongjian, Liang Xinhong. An improved hybrid model for automatic salient region detection. Signal Processing Letters[J].2012,19(4):207-210.
[118]付朝阳,郭雷,常威威.基于小波变换和多通道脉冲耦合神经网络的高光谱图像融合[J].吉林大学学报,2011,41(3)：938-843.
[119]辛国江,邹北骥,李建锋,等.结合最大方差比准则和PCNN模型的图像分割[J].中国图象图形学报,2011,16(7)：1310-1316.
[120]姚畅,陈后金,荆涛,等.一种基于改进的PCNN的视网膜血管树提取方法[J].光电子·激光,2011,22(11)：1745-1750.
[121]寿天德.视觉信息处理的脑机制[M].合肥：中国科学技术大学出版社,2010：150-170.
[122]Kuffler S W. Discharge Patterns and Functional Organization of Mammalian Retina [J]. Neurophysiology,1953,16:37-68.
[123]R.W.Rodieck, JJ.Stone. Analysis of receptive fields of cat retina ganglin cells[J]. Neurophysiology,1965,28:833-848.
[124]J.G.Daugman. Principles of visual neuronal receptive field organization:two-dimensional spectral consequences[C]. IEEE International Conference on Systems, Man and Cybernetics, New York, USA,1984:457-464.
[125]汪云九,齐翔林.初级视觉的Gabor函数模型的研究进展[J].生物物理学报1993,9(3)：508-513.
[126]窦燕.基于空间和物体的视觉注意计算方法及实验研究[D].秦皇岛：燕山大学,2010,12-13.
[127]祝文骏.基于视觉皮层网络的物体整体特征分析与算法研究[D].上海：上海交通大学,2011,11－14.
[128]John L, Johnson, Mary Lou Padgett. PCNN models and applications [J].Transactions on Neural Networks,1999,10(3):480-498.
[129]于江波,陈后金.PCNN模型的改进及其在医学图像处理中的应用[J].电子与信息学报,2007,29(10)：2316-2320.
[130]刘国英,马国锐,王雷光,等.基于Markov随机场的小波域图像建模及分割[M].北京：科学出版社,2010：15-31.
[131]Pan Chen,Park Dong Sun,Yang Yong, et al. Leukocyte image segmentation by visual attention and extreme learning machine[J].Neural Computing and Applications,2012,21(6): 1217-1227.
[132]Itti Laurent, Koch Christof, Niebur Ernst. Model of saliency-based visual attention for rapid scene analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998,20(11):1254-1259
[133]罗四维.视觉信息认知计算理论[M].北京：科学出版社,2010：181-219.
[134]罗四维.视觉感知系统信息处理理论[M].北京：电子工业出版社,2006：107-123.
[135]刘琼,秦世引,李志成.视觉选择性注意的模型化计算及其应用前景[J].科技导报,2010,28(1)：107-116.
[136]HU M K. Visual pattern recognition by moment invariants [J]. IEEE Transactions on Information Theory,1962,8(2):179-187.
[137]杨娜,韩焱.矩在复杂构件射线图像识别中的应用[J].探测与控制学报,2007,29(4)：42-44.
[138]潘泉,程咏梅,杜亚娟,等.离散不变矩算法及其在目标识别中的应用[J].电子与信息学报,2001,23(1)：30-36.
[139]冯占国,徐玉如.基于不变性特征的水下目标特征提取[J].哈尔滨工程大学学报,2007,28(12)：1343-1347.
[140]刘勃.基于脉冲耦合神经网络的图像处理若干问题研究[D].西安：西安电子科技大学,2011,70-77.
[141]章毓晋.图像分析[M].第二版.北京：清华大学出版社,2005：177-201.
© 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 |