基于Gabor小波的车辆识别与跟踪技术研究
|
摘要
在智能交通系统中,基于视频的检测跟踪系统具有易于安装、工作稳定、可视信息丰富和便于实现无人监控的特点,是目前国内外研究的热点。本论文在分析和总结现有的识别与跟踪方法的基础上,对交通监控系统中的运动车辆的识别以及车辆的跟踪问题进行了研究。
本文对傅立叶变换、小波变换和Gabor小波变换进行了比较, Gabor变换在分析数字图像中局部区域的频率和方向信息具有优异的性能,在计算机视觉和纹理分割中已经得到了广泛的应用。本文对二维Gabor滤波器的性能进行了分析,设计了一个多通道的Gabor滤波器,对其参数进行了选择,采用多通道的Gabor滤波器对图像的纹理特征进行了提取,用一种特征向量的方法进行描述。
本文在分析常用的车型识别方法的基础上,根据车型的纹理分析,提出了一种用Gabor小波提取特征点与BP神经网络算法相结合的分类识别技术。首先对视频图像序列进行采集,采用一种存在运动目标情况下的背景重建算法,获取动态背景并实时更新,能较好地抑制外界环境变化带来的影响。然后用背景差法确定目标位置。为了去除噪声对图像进行中值滤波,最后截取出80×60标准的目标图像。由于不同车型所提取的Gabor特征点的能量值相关度很低,本文以轿车、卡车、面包车和客车车型为例建立了四种标准车型的数据库,最后用提取到目标特征和标准数据库进行匹配。针对易误识的车型,需要进一步细分车型和提高Gabor小波的分辨率,但是Gabor特征点的数据量会大大增加。为了保证系统的实时性,本文在增加Gabor小波分辨尺度的同时,设计了一种神经网络细分类器,对特征点进行了训练识别。实验表明,本文方法不仅系统的识别精度高,而且实时性好。
针对传统全模板匹配跟踪计算耗时大的缺点,本文采用了基于Kalman滤波器的跟踪方法。首先利用Kalman滤波器预测车辆在下一帧中的可能位置,然后在预测区域利用Gabor小波特征点进行匹配,精确定位车辆。在车辆目标发生平移、尺度变化等情况下,采用仿射变换模型对目标进行矫正。为了进一步提高跟踪速度,在实验中对提取出的全部特征点进行筛选,选用部分典型特征点与数据库中的标准车型模板进行特征匹配。实验结果显示,本文方法有良好的跟踪效果,并且车辆在短时间被遮挡的情况下也能有效跟踪。
In intelligent transportation systems, detection and tracking system based on video sequence has the features of simple installation, working stability, visual information-rich and easy to realize unmanned monitoring. It is currently a hot research both at home and abroad. In this paper, we have analysis and summarized the existing methods of identification and tracking in intelligent transportation systems. Based on this, we have a research on recognition and tracing of moving vehicles in traffic monitoring system.
In this paper, Fourier transform, wavelet transform and Gabor wavelet transform are compared. Gabor transform has excellent properties in the analysis of the local area frequency and the direction information in digital image. In computer vision and texture segmentation it also has been widely used. In this paper, the performance of two-dimensional Gabor filter was analyzed, a multi-channel Gabor filter was designed, and the parameters of which is chosen. The texture features of the image are extracted by the multi-channel Gabor filter, which was descript by a feature vector.
Based on the analysis of common identification methods, according to the texture model, this paper presents an identification technology which was combined by features extraction using Gabor wavelet and BP neural network algorithm for the classification of vehicle types. First of all, the video image sequence was collected. A background reconstruction algorithm is used in the case of moving targets in the sequences, which can acquire and update the dynamic background real-time. It can suppress the impact of outside environmental change. The background subtraction was employed to locate the target. For removing the noise, the images were filtered by median filtering. Finally, an 80×60 standard target image was intercepted. As the correlation degree of feature points’energy value which was extracted from different vehicle types is low, the database of four standard vehicle types including car, trucks, vans and bus was established. The extracted target features were matched with the standard database at last. For vehicles which were easy mistaken recognized, the vehicle types need to be further divided and the discrimination of Gabor wavelets needs to be improved. However the amount of Gabor feature points would be greatly increased. In order to ensure real-time systems, the discrimination of Gabor wavelet was increased. At the same time a BP neural network classifier was designed to train and identify the feature points. Experiments show that this method not only has a high-precision and a good real-time.
The tracking of traditional template matching consumes a lot of time, for overcome this shortcoming, a tracking method based on Kalman filter was used. First, the possible vehicle location of the next frame was predicted by Kalman filter. The vehicle was located precisely by the method of matching the Gabor feature points in predicting region. Affine transformation model was introduced to correct targets in the case of target translation and scaling change. To further enhance the tracking speed, all feature points have been screened in the experiment. Some points of typical characteristics were selected to match with the standard vehicle templates in the database. The experimental results show that this method has good tracking results, and the vehicle which was blocked in a short time can be effectively tracked.
本文对傅立叶变换、小波变换和Gabor小波变换进行了比较, Gabor变换在分析数字图像中局部区域的频率和方向信息具有优异的性能,在计算机视觉和纹理分割中已经得到了广泛的应用。本文对二维Gabor滤波器的性能进行了分析,设计了一个多通道的Gabor滤波器,对其参数进行了选择,采用多通道的Gabor滤波器对图像的纹理特征进行了提取,用一种特征向量的方法进行描述。
本文在分析常用的车型识别方法的基础上,根据车型的纹理分析,提出了一种用Gabor小波提取特征点与BP神经网络算法相结合的分类识别技术。首先对视频图像序列进行采集,采用一种存在运动目标情况下的背景重建算法,获取动态背景并实时更新,能较好地抑制外界环境变化带来的影响。然后用背景差法确定目标位置。为了去除噪声对图像进行中值滤波,最后截取出80×60标准的目标图像。由于不同车型所提取的Gabor特征点的能量值相关度很低,本文以轿车、卡车、面包车和客车车型为例建立了四种标准车型的数据库,最后用提取到目标特征和标准数据库进行匹配。针对易误识的车型,需要进一步细分车型和提高Gabor小波的分辨率,但是Gabor特征点的数据量会大大增加。为了保证系统的实时性,本文在增加Gabor小波分辨尺度的同时,设计了一种神经网络细分类器,对特征点进行了训练识别。实验表明,本文方法不仅系统的识别精度高,而且实时性好。
针对传统全模板匹配跟踪计算耗时大的缺点,本文采用了基于Kalman滤波器的跟踪方法。首先利用Kalman滤波器预测车辆在下一帧中的可能位置,然后在预测区域利用Gabor小波特征点进行匹配,精确定位车辆。在车辆目标发生平移、尺度变化等情况下,采用仿射变换模型对目标进行矫正。为了进一步提高跟踪速度,在实验中对提取出的全部特征点进行筛选,选用部分典型特征点与数据库中的标准车型模板进行特征匹配。实验结果显示,本文方法有良好的跟踪效果,并且车辆在短时间被遮挡的情况下也能有效跟踪。
In intelligent transportation systems, detection and tracking system based on video sequence has the features of simple installation, working stability, visual information-rich and easy to realize unmanned monitoring. It is currently a hot research both at home and abroad. In this paper, we have analysis and summarized the existing methods of identification and tracking in intelligent transportation systems. Based on this, we have a research on recognition and tracing of moving vehicles in traffic monitoring system.
In this paper, Fourier transform, wavelet transform and Gabor wavelet transform are compared. Gabor transform has excellent properties in the analysis of the local area frequency and the direction information in digital image. In computer vision and texture segmentation it also has been widely used. In this paper, the performance of two-dimensional Gabor filter was analyzed, a multi-channel Gabor filter was designed, and the parameters of which is chosen. The texture features of the image are extracted by the multi-channel Gabor filter, which was descript by a feature vector.
Based on the analysis of common identification methods, according to the texture model, this paper presents an identification technology which was combined by features extraction using Gabor wavelet and BP neural network algorithm for the classification of vehicle types. First of all, the video image sequence was collected. A background reconstruction algorithm is used in the case of moving targets in the sequences, which can acquire and update the dynamic background real-time. It can suppress the impact of outside environmental change. The background subtraction was employed to locate the target. For removing the noise, the images were filtered by median filtering. Finally, an 80×60 standard target image was intercepted. As the correlation degree of feature points’energy value which was extracted from different vehicle types is low, the database of four standard vehicle types including car, trucks, vans and bus was established. The extracted target features were matched with the standard database at last. For vehicles which were easy mistaken recognized, the vehicle types need to be further divided and the discrimination of Gabor wavelets needs to be improved. However the amount of Gabor feature points would be greatly increased. In order to ensure real-time systems, the discrimination of Gabor wavelet was increased. At the same time a BP neural network classifier was designed to train and identify the feature points. Experiments show that this method not only has a high-precision and a good real-time.
The tracking of traditional template matching consumes a lot of time, for overcome this shortcoming, a tracking method based on Kalman filter was used. First, the possible vehicle location of the next frame was predicted by Kalman filter. The vehicle was located precisely by the method of matching the Gabor feature points in predicting region. Affine transformation model was introduced to correct targets in the case of target translation and scaling change. To further enhance the tracking speed, all feature points have been screened in the experiment. Some points of typical characteristics were selected to match with the standard vehicle templates in the database. The experimental results show that this method has good tracking results, and the vehicle which was blocked in a short time can be effectively tracked.
引文
[1]李舜酩,沈垣,毛建国等.智能车辆发展及其关键技术研究现状[J].传感器与微系统,2009,28(1):1-3.
[2]周兵.运动目标检测及其在视频监控中的应用.北京航空航天大学学位论文,2003年.
[3] Iketani A, Kuno Y, Shimada N, et al. Real time Surveillance System Detecting Persons in Complex Scenes[J]. In Proceedings of Image Analysis and Processing.1999: 1112-1115.
[4] Lipton A, Fujiyoshi H and Patil R. Moving target classification and tracking from real-time video[C]. In. Proc IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998:8-14.
[5]边明远,陈思忠,罗汉军.智能交通系统(ITS)及其发展[J].武汉理工大学学报信息与管理工程版,2001,23 (1) : 67-70.
[6]王年,任彬等.基于神经网络的汽车车型图像自动识别[J].中国图象图形学报, 1999, 8(A)(3) : 37-40.
[7] Sheng W, Yang Q, Guo Y. Cooperative driving based on inter-vehicle communications experimental platform and algorithm[C]. IEEE Conference on IRS,Beijing,China,2006: 5073-5078.
[8]高浩军,杜宇人.基于背景重建的序列图像车辆目标检测方法[J].扬州大学学报自然科学版, 2007,10 (1): 55-58.
[9] Yuren Du, Aijun Zhou. Real time detection and recognition of multiple vehicles[C]. Proceedings of 2008 2nd International Symposium on Test Automation & Instrumentation, vol.3, Beijing China, Nov, 2008: 1489-1492.
[10] Iketani A, Kuno Y, Shimada N, et al. Real time Surveillance System Detecting Persons in Complex Scenes[C]. In Proceedings of Image Analysis and Processing, 1999: 1112-1115
[11] T. Hu, C. Liyanage, De Silva. A hybrid approach of NN and HMM for facial emotion classification[J]. Pattern Recognition Letters, 23, 2002: 1303-1310.
[12]樊鑫,梁德群,张旗.引入统计先验的人脸图像恢复.计算机辅助设计与图形学学报, 2004(16): 497-502.
[13] Ken Tabb. Neil Davey. The recognition and analysis of animate objects using neural networks and active contour models [J]. Neurocomputing 43, 2002: 145-172.
[14] J Han, K-K Ma. Rotation-invariant and scale-invariant Gabor featuresfor texture image retrieval[J]. Image and Vision Computing (S0262-8856), 25(9), 2007: 1474-1481.
[15] XIA Li-min. Vehicle Shape recovery and Recognition Using Generic Models[C], Proceedings of the 4th world congress on intelligent control and automation, 2002: 1055-1059.
[16]王学文,丁小青,刘长松.基于Gabor变换的高鲁棒汉字识别新方法[J].电子学报, 2002(9): 1317-1322.
[17] C Yang, R Duraiswami, L Davis. Efficient Mean-Shift Tracking via a New Similarity Measure[C]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, Vo1.1:176-183.
[18]邱书波,王化祥,梁志伟.一种新的B-Snake算法在目标轮廓跟踪中的应用[J].中国图像图形学报,2005,10(5): 585-589.
[19] Moravec. H. P. Toward automatic visual obstacle avoidance[C]. International Joint Conference on Artificial Intelligent, 2006: 584-587.
[20] R B Fisher. PETS04 Surveillance Ground Truth Data Set[C]. In Proceeding of Sixth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, 2004: 1-5.
[21] Feyrer S, Zell A. Detection, Tracking, and Pursuit of Humans with an Autonomous Mobile Robot [J].In Proc. IEEE/RSJ Int. Conf. On Intelligent Robots and Systems (IROS’99): 864-869.
[22] T Maurer, C. v. d. Malsburg. Tracking and learning graphs on image sequences of faces [J]. In Int Conf. On Automatic Face-and Gestrue-Recognition, Killington, Vermont, USA, 2007, Oct: 14-16.
[23] T, Chateau, J, TLapreste. Real-time vehicle with occlusion and illumination variations [A]. Processing of the 7th International Conference on Pattern Recognition [C] .2004, 4: 763-766.
[24] X Lei, Z Guangxi, Real time vehicle tracking on Kalman filter in ITS [A]. Proc.of 2005 Internal Conference on Communications Systems[c].2005: 886-891.
[25] N Paragios, R Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects [J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002.22: 266-280.
[26] N Peterfreund. Robust tracking of position and velocity with kalman snakes [J]. IEEE Transactions on pattern Analysis and Machine Intelligence.1999, 21: 564-569.
[27] Gregory D.Hager, Peter V. Belbumeur. Efficient Region Tracking With Parametric Models of Geometry and Illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998,20 (10): 1025-1038.
[28]张江山,朱光喜.一种基于Kalman滤波的视频对象跟踪方法[J].中国图像图形学报, 2002, 7 (6): 606-609.
[29]董学志,宋建中,韩广良.一种利用Gabor小波特征的目标跟踪方法[J].光学技术, 2003, 29 (4): 484-486.
[30] T. Kanade, T. Sato, E. K. Hughes and M. A. Smith. Video OCR for digital news archive[C]. In Proc. IEEE Workshop on Content-Based Access of Image and Video Databases.1998: 52-60.
[31]杨福生.小波变换的工程分析与应用[M].科学出版社,2001.
[32]孙延奎.小波分析及其应用[M].机械工业出版社,2005.
[33] Reza Keyhani, Mohamed Deriche and Ed Palmer. A High Impedance fault Detector Using a Neural Network and Subband[C]. International Symposium on Signal Processing and its Applications(ISSPA) Malaysia13- 16 August 2001: 458-461.
[34] C. H. Lee, Y. Juen, W. Liang. A literature Survey of Wavelet in PowerEngineering Applications[C]. Proc. Natl. Sci. Counc. RoC (A), Vol. 24, No.4, 2000: 249-258.
[35] Ayman E. Ibrahim. Tamer A. Kawady, Hatem A Darwish, Abdel-Maksoud Taalab. Generalized 1-D Gabor Transform Application to Power System Signal Analysis[C]. 2006 IEEE International Symposium on Industrial Electronics, July 2006, Montréal, Quebec, Canada. ISIE’06: 9 -13.
[36]袁峰,杜宇人,吴振宇.基于Gabor小波和神经网络的图像目标识别[J].扬州大学学报自然科学版, 2009,12 (2):53-56.
[37] P Ribeiro, J Santos-Victor. Human Activities Recognition from Video: modeling, feature selection and classification architecture [J]. In Proceeding of Workshop on Human Activity Recognition and Modeling, 2005: 61-70.
[38] D Tweed, W Fang, R Fisher. Exploring Techniques for Behaviour Recognition via the CAVIAR Modular Vision Framework [J]. In Proceeding of Workshop on Human Activity Recognition and Modeling, 2005: 97-104.
[39]蒋晓瑜.小波变换在特征级多重图像融合与目标分类中的应用[J].红外技术, 2004, 26(1):1-4.
[40] Haihong Zhang, Bailing Zhang, Weimin Huang, and Qi Tian. Gabor Wavelet Associative Memory for Face Recognition[C]. IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 16(1), 2005: 275-278.
[41] Lin-Lin Huang, Akinobu Shimizu, and Hidefumi Kobatake. Classification-Based Face Detection Using Gabor Filter Features[C]. Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004 IEEE: 1-6.
[42] C. Liu. A Bayesian Discriminating Features Methods for Face Detection[C]. IEEE Trans. Pattern Anal. Mach. Intell, 2003, Vol.25: 725-730.
[43] Dang-Hui Lids, Kin-Man Lain, Lan-Sun Shen. SAMPLING GABOR FEATURES FOR FACE RECOGNITION[C], IEEE Int. Conf. Neural Networks & Si nal Processing Nanjing, China, December 2003: 14-17.
[44]杜宇人,高浩军.基于车辆轮廓定位匹配的车型识别方法[J].扬州大学学报自然科学版, 2007.2.10 (2): 62-65.
[45] Monacos, S.P., Portillo, A.A. A high frame rate CCD camera with region-of-interest Capability [C], Aerospace Conference, 2001:1513-1522.
[46]LI Yun-hao, ZHANG Mao-jun, YANG Bin. Noise analysis in camera calibration [C], International Conferences on Info-tech and Info-net, 2001: 536-542.
[47]张建华,杨建国,尹旭全等.用图像处理技术提取交通车辆移动轨迹[J].计算机工程与应用, 2004, 40(21): 213-215.
[48] JuCheng Yang, ByoungJun Min and DongSun Park. Fingerprint Verification Based on Absolute Distance and Intelligent BPNN[C]. Frontiers in the Convergence of Bioscience and Information Technologies 2007: 676-681.
[49] May-Ping Loh, Ya-Ping Wong and Chee-Onn Wong. Facial Expression Recognition for E-earning Systems using Gabor Wavelet & Neural Network[J]. Proceedings of the Sixth International onference on Advanced Learning Technologies, 2006: 88-92.
[50] Hagan, M. T.等著;戴葵等译.神经网络设计[M], 2002: 197-221.
[51] I Haritaoglu, D Harwood, L Davis. W4: Real-time Surveillance of People and Their Activities[C]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(8):809-830.
[52] I Cohen, G Medioni. Detecting and tracking moving objects for video surveillance[C]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999, Vol. 2:319-325.
[53]杜宇人,周爱军.一种遮挡情况下运动车辆的跟踪算法[J].扬州大学学报自然科学版, 2009.12(1): 52-55.
[2]周兵.运动目标检测及其在视频监控中的应用.北京航空航天大学学位论文,2003年.
[3] Iketani A, Kuno Y, Shimada N, et al. Real time Surveillance System Detecting Persons in Complex Scenes[J]. In Proceedings of Image Analysis and Processing.1999: 1112-1115.
[4] Lipton A, Fujiyoshi H and Patil R. Moving target classification and tracking from real-time video[C]. In. Proc IEEE Workshop on Applications of Computer Vision, Princeton, NJ, 1998:8-14.
[5]边明远,陈思忠,罗汉军.智能交通系统(ITS)及其发展[J].武汉理工大学学报信息与管理工程版,2001,23 (1) : 67-70.
[6]王年,任彬等.基于神经网络的汽车车型图像自动识别[J].中国图象图形学报, 1999, 8(A)(3) : 37-40.
[7] Sheng W, Yang Q, Guo Y. Cooperative driving based on inter-vehicle communications experimental platform and algorithm[C]. IEEE Conference on IRS,Beijing,China,2006: 5073-5078.
[8]高浩军,杜宇人.基于背景重建的序列图像车辆目标检测方法[J].扬州大学学报自然科学版, 2007,10 (1): 55-58.
[9] Yuren Du, Aijun Zhou. Real time detection and recognition of multiple vehicles[C]. Proceedings of 2008 2nd International Symposium on Test Automation & Instrumentation, vol.3, Beijing China, Nov, 2008: 1489-1492.
[10] Iketani A, Kuno Y, Shimada N, et al. Real time Surveillance System Detecting Persons in Complex Scenes[C]. In Proceedings of Image Analysis and Processing, 1999: 1112-1115
[11] T. Hu, C. Liyanage, De Silva. A hybrid approach of NN and HMM for facial emotion classification[J]. Pattern Recognition Letters, 23, 2002: 1303-1310.
[12]樊鑫,梁德群,张旗.引入统计先验的人脸图像恢复.计算机辅助设计与图形学学报, 2004(16): 497-502.
[13] Ken Tabb. Neil Davey. The recognition and analysis of animate objects using neural networks and active contour models [J]. Neurocomputing 43, 2002: 145-172.
[14] J Han, K-K Ma. Rotation-invariant and scale-invariant Gabor featuresfor texture image retrieval[J]. Image and Vision Computing (S0262-8856), 25(9), 2007: 1474-1481.
[15] XIA Li-min. Vehicle Shape recovery and Recognition Using Generic Models[C], Proceedings of the 4th world congress on intelligent control and automation, 2002: 1055-1059.
[16]王学文,丁小青,刘长松.基于Gabor变换的高鲁棒汉字识别新方法[J].电子学报, 2002(9): 1317-1322.
[17] C Yang, R Duraiswami, L Davis. Efficient Mean-Shift Tracking via a New Similarity Measure[C]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, Vo1.1:176-183.
[18]邱书波,王化祥,梁志伟.一种新的B-Snake算法在目标轮廓跟踪中的应用[J].中国图像图形学报,2005,10(5): 585-589.
[19] Moravec. H. P. Toward automatic visual obstacle avoidance[C]. International Joint Conference on Artificial Intelligent, 2006: 584-587.
[20] R B Fisher. PETS04 Surveillance Ground Truth Data Set[C]. In Proceeding of Sixth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, 2004: 1-5.
[21] Feyrer S, Zell A. Detection, Tracking, and Pursuit of Humans with an Autonomous Mobile Robot [J].In Proc. IEEE/RSJ Int. Conf. On Intelligent Robots and Systems (IROS’99): 864-869.
[22] T Maurer, C. v. d. Malsburg. Tracking and learning graphs on image sequences of faces [J]. In Int Conf. On Automatic Face-and Gestrue-Recognition, Killington, Vermont, USA, 2007, Oct: 14-16.
[23] T, Chateau, J, TLapreste. Real-time vehicle with occlusion and illumination variations [A]. Processing of the 7th International Conference on Pattern Recognition [C] .2004, 4: 763-766.
[24] X Lei, Z Guangxi, Real time vehicle tracking on Kalman filter in ITS [A]. Proc.of 2005 Internal Conference on Communications Systems[c].2005: 886-891.
[25] N Paragios, R Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects [J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002.22: 266-280.
[26] N Peterfreund. Robust tracking of position and velocity with kalman snakes [J]. IEEE Transactions on pattern Analysis and Machine Intelligence.1999, 21: 564-569.
[27] Gregory D.Hager, Peter V. Belbumeur. Efficient Region Tracking With Parametric Models of Geometry and Illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998,20 (10): 1025-1038.
[28]张江山,朱光喜.一种基于Kalman滤波的视频对象跟踪方法[J].中国图像图形学报, 2002, 7 (6): 606-609.
[29]董学志,宋建中,韩广良.一种利用Gabor小波特征的目标跟踪方法[J].光学技术, 2003, 29 (4): 484-486.
[30] T. Kanade, T. Sato, E. K. Hughes and M. A. Smith. Video OCR for digital news archive[C]. In Proc. IEEE Workshop on Content-Based Access of Image and Video Databases.1998: 52-60.
[31]杨福生.小波变换的工程分析与应用[M].科学出版社,2001.
[32]孙延奎.小波分析及其应用[M].机械工业出版社,2005.
[33] Reza Keyhani, Mohamed Deriche and Ed Palmer. A High Impedance fault Detector Using a Neural Network and Subband[C]. International Symposium on Signal Processing and its Applications(ISSPA) Malaysia13- 16 August 2001: 458-461.
[34] C. H. Lee, Y. Juen, W. Liang. A literature Survey of Wavelet in PowerEngineering Applications[C]. Proc. Natl. Sci. Counc. RoC (A), Vol. 24, No.4, 2000: 249-258.
[35] Ayman E. Ibrahim. Tamer A. Kawady, Hatem A Darwish, Abdel-Maksoud Taalab. Generalized 1-D Gabor Transform Application to Power System Signal Analysis[C]. 2006 IEEE International Symposium on Industrial Electronics, July 2006, Montréal, Quebec, Canada. ISIE’06: 9 -13.
[36]袁峰,杜宇人,吴振宇.基于Gabor小波和神经网络的图像目标识别[J].扬州大学学报自然科学版, 2009,12 (2):53-56.
[37] P Ribeiro, J Santos-Victor. Human Activities Recognition from Video: modeling, feature selection and classification architecture [J]. In Proceeding of Workshop on Human Activity Recognition and Modeling, 2005: 61-70.
[38] D Tweed, W Fang, R Fisher. Exploring Techniques for Behaviour Recognition via the CAVIAR Modular Vision Framework [J]. In Proceeding of Workshop on Human Activity Recognition and Modeling, 2005: 97-104.
[39]蒋晓瑜.小波变换在特征级多重图像融合与目标分类中的应用[J].红外技术, 2004, 26(1):1-4.
[40] Haihong Zhang, Bailing Zhang, Weimin Huang, and Qi Tian. Gabor Wavelet Associative Memory for Face Recognition[C]. IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 16(1), 2005: 275-278.
[41] Lin-Lin Huang, Akinobu Shimizu, and Hidefumi Kobatake. Classification-Based Face Detection Using Gabor Filter Features[C]. Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004 IEEE: 1-6.
[42] C. Liu. A Bayesian Discriminating Features Methods for Face Detection[C]. IEEE Trans. Pattern Anal. Mach. Intell, 2003, Vol.25: 725-730.
[43] Dang-Hui Lids, Kin-Man Lain, Lan-Sun Shen. SAMPLING GABOR FEATURES FOR FACE RECOGNITION[C], IEEE Int. Conf. Neural Networks & Si nal Processing Nanjing, China, December 2003: 14-17.
[44]杜宇人,高浩军.基于车辆轮廓定位匹配的车型识别方法[J].扬州大学学报自然科学版, 2007.2.10 (2): 62-65.
[45] Monacos, S.P., Portillo, A.A. A high frame rate CCD camera with region-of-interest Capability [C], Aerospace Conference, 2001:1513-1522.
[46]LI Yun-hao, ZHANG Mao-jun, YANG Bin. Noise analysis in camera calibration [C], International Conferences on Info-tech and Info-net, 2001: 536-542.
[47]张建华,杨建国,尹旭全等.用图像处理技术提取交通车辆移动轨迹[J].计算机工程与应用, 2004, 40(21): 213-215.
[48] JuCheng Yang, ByoungJun Min and DongSun Park. Fingerprint Verification Based on Absolute Distance and Intelligent BPNN[C]. Frontiers in the Convergence of Bioscience and Information Technologies 2007: 676-681.
[49] May-Ping Loh, Ya-Ping Wong and Chee-Onn Wong. Facial Expression Recognition for E-earning Systems using Gabor Wavelet & Neural Network[J]. Proceedings of the Sixth International onference on Advanced Learning Technologies, 2006: 88-92.
[50] Hagan, M. T.等著;戴葵等译.神经网络设计[M], 2002: 197-221.
[51] I Haritaoglu, D Harwood, L Davis. W4: Real-time Surveillance of People and Their Activities[C]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(8):809-830.
[52] I Cohen, G Medioni. Detecting and tracking moving objects for video surveillance[C]. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999, Vol. 2:319-325.
[53]杜宇人,周爱军.一种遮挡情况下运动车辆的跟踪算法[J].扬州大学学报自然科学版, 2009.12(1): 52-55.