城区复杂背景条件下的车辆检测算法研究
|
摘要
在智能车辆的信息感知中,对前方行驶车辆的检测是其核心任务和重要前提之一。本文以智能主动安全预警系统为背景,以城区复杂背景条件下行驶的车辆为研究对象,对小波变换在目标检测领域中的应用进行了讨论和研究,并基于以上理论提出了一种基于单目视觉的车辆检测的新方法。
在车辆检测算法的研究方面,首先用三层金字塔高斯滤波器对原始图像进行平滑,然后采用一阶导数算子——3×3的Sobel算子提取平滑后的图像中包含的边缘信息。在得到图像全局轮廓的基础上,根据投影映射原理和统计数据求得图像中车宽阈值,运用“投票”机制来求取图像中存在的轮廓对称轴,并将对称轴位置映射到一个一维向量中。然后利用小波模极大值原理,通过小波变换检测出一维投票结果向量中的信号突变点,在整个像平面的对称轴集合中探测出候选车辆对称轴。得到候选车辆对称轴后,为了产生可用于确认判别的车辆外接矩阵Region of Interests(ROI),采用了边缘特征作为车辆左右边界定位的依据,并根据底部阴影特征来定位下边界,而对定位准确度要求较低的上边界则简单采用外形高宽比来检测。最后,通过基于局部信息熵和局部灰度对称性测度的假设验证对ROI区域进行验证并对验证后的车辆区域进行滤波,得到最终检测结果。
大量的实验数据表明,本文算法具有较高的检测精度,较高的算法稳定性和运行鲁棒性,能较好地满足实际应用的需求。同时,由于本文算法是在全局图像中进行车辆检测,并未采用车道线等通常的约束条件,因此本文算法可良好地应用于城区道路等复杂环境下的车辆检测。
The detection of the forward steering vehicles is one of the key tasks of the information perception process in Intelligent Transportation System. In this thesis, we investigate into the vehicle detection under the complicated traffic scenarios of urban roads and present a monocular-based method applying to vehicle detection.
In the vehicle detection section, we first adopt a three-rank pyramidal Gauss filter to smooth the original image and use a Sobel 3*3 operator to gain the vertical edges of vehicle contour as global feature. After the imaging width threshold of vehicles is calculated, a so-called“voting”mechanism is applied to map the symmetrical axes of edges into a 1-D vector. After the study of experiment data and relevant academic technologies, we detect the vehicle symmetry axes based on Wavelet Transform Module Maximum(WTMM) theory. In order to generate the Region of Interests(ROI) for latter vehicle validation, we combine multi-features of vehicle as judgment bases to detect its external rectangle. Horizontal contour symmetry, bottom shadow and shape scale are utilized respectively to detect the left, right, bottom and upper boundary. Then, vehicle validation process is accomplished by local entropy and local gray scale symmetry estimate. Finally, The validated ROI area is filtered to obtain the ultimate detection results.
The algorithm was tested under different traffic scenarios (e.g., simply structured highway, complex urban street, varying sunlight conditions), especially under the complicated traffic circumstance of urban roads. The approving experimental results show that the method is effective, stabilized and robust. Additionally, it is fast enough to be used in real-time Intelligent Transportation System. Thus, the method could be well used in vehicle detection under urban traffic scenarios.
在车辆检测算法的研究方面,首先用三层金字塔高斯滤波器对原始图像进行平滑,然后采用一阶导数算子——3×3的Sobel算子提取平滑后的图像中包含的边缘信息。在得到图像全局轮廓的基础上,根据投影映射原理和统计数据求得图像中车宽阈值,运用“投票”机制来求取图像中存在的轮廓对称轴,并将对称轴位置映射到一个一维向量中。然后利用小波模极大值原理,通过小波变换检测出一维投票结果向量中的信号突变点,在整个像平面的对称轴集合中探测出候选车辆对称轴。得到候选车辆对称轴后,为了产生可用于确认判别的车辆外接矩阵Region of Interests(ROI),采用了边缘特征作为车辆左右边界定位的依据,并根据底部阴影特征来定位下边界,而对定位准确度要求较低的上边界则简单采用外形高宽比来检测。最后,通过基于局部信息熵和局部灰度对称性测度的假设验证对ROI区域进行验证并对验证后的车辆区域进行滤波,得到最终检测结果。
大量的实验数据表明,本文算法具有较高的检测精度,较高的算法稳定性和运行鲁棒性,能较好地满足实际应用的需求。同时,由于本文算法是在全局图像中进行车辆检测,并未采用车道线等通常的约束条件,因此本文算法可良好地应用于城区道路等复杂环境下的车辆检测。
The detection of the forward steering vehicles is one of the key tasks of the information perception process in Intelligent Transportation System. In this thesis, we investigate into the vehicle detection under the complicated traffic scenarios of urban roads and present a monocular-based method applying to vehicle detection.
In the vehicle detection section, we first adopt a three-rank pyramidal Gauss filter to smooth the original image and use a Sobel 3*3 operator to gain the vertical edges of vehicle contour as global feature. After the imaging width threshold of vehicles is calculated, a so-called“voting”mechanism is applied to map the symmetrical axes of edges into a 1-D vector. After the study of experiment data and relevant academic technologies, we detect the vehicle symmetry axes based on Wavelet Transform Module Maximum(WTMM) theory. In order to generate the Region of Interests(ROI) for latter vehicle validation, we combine multi-features of vehicle as judgment bases to detect its external rectangle. Horizontal contour symmetry, bottom shadow and shape scale are utilized respectively to detect the left, right, bottom and upper boundary. Then, vehicle validation process is accomplished by local entropy and local gray scale symmetry estimate. Finally, The validated ROI area is filtered to obtain the ultimate detection results.
The algorithm was tested under different traffic scenarios (e.g., simply structured highway, complex urban street, varying sunlight conditions), especially under the complicated traffic circumstance of urban roads. The approving experimental results show that the method is effective, stabilized and robust. Additionally, it is fast enough to be used in real-time Intelligent Transportation System. Thus, the method could be well used in vehicle detection under urban traffic scenarios.
引文
[1] Zehang Sun, George Bebis, Ronald Miller. Monocular Precrash Vehicle Detection: Features and Classifiers[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,VOL.15, NO.7, JULY 2006.
[2] Tan Xiao-jun, Shen Wei, Guo Zhi-hao. Vision-based Method for Traffic flow Surveillance on Highway[J]. Computer Applications, 2005, 25(5): 1215-1218.
[3] Raphael L, Didier A. Real Time Obstacle Detection in Stereovision on Non Flat Road Geometry Through“V-disparity”Representation[C]. IEEE Symposium on Intelligent Vehicles, 2002: 646-651.
[4] Broggi A, Bertozzi M, Fascioli A. Self-calibration of a Stereo Vision System for Automotive Applications[C]. IEEE International Conference on Robotics and Automation, 2001: 3698-3703.
[5] Sun Z, Miller R, Bebis G, Dimea D. A Real-time Precrash Vehicle Detection System[J]. IEEE Int. Workshop on Application of Computer Vision, 2002(12): 171-176.
[6] Broggi Albert, Cem Pietro, Antonello Pier Claudio. Multi-Resolution Vehicle Detection Using Artificial Vision[C]. IEEE Intelligent Vehicles Symposium, 2004: 310-314.
[7] Liu Tie, Zheng Nanning, Zhao Li, et al. Learning Based Symmetric Features Selection for Vehicle Detection[C]. IEEE Intelligent Vehicle Symposium, 2005: 124-129.
[8] Handmann U, Kalinke T, Tzomakas C, et al. An Image Processing System for Driver Assistance[J]. Image and Vision Computing, 2000,18: 367-376.
[9] Ten Kate T K, van Leewen M B, et al. Mid-range and Distant Vehicle Detection with a Mobile Camera[C]. IEEE Symposium on Intelligent Vehicles, 2004:72-77.
[10] Y.Park. Shape-resolving Local Thresholding for Object Detection[J].Pattern Recognition Letters, 2001, 22(5) : 883-890.
[11] J.M.Blosseville, C Krafft, F Lenoir, et al. TITAN: New Traffic Measurements by Image Processing[C]. Proc. of IFAC Transportation Systems, 1999, 14(1) : 277-296.
[12] T.Abramczuk. A Microcomputer based TV Detector for Road Traffic[J].In Symposium on Road Research Program, T, 1984, 3(2) : 145-147.
[13] W.Kasparzak. An Iconic Classification Scheme for Video-based Traffic Sensor Tasks[C]. W Skarbek. CAIP 2001, Springer, Berlin, 2001.725-732.
[14] M.Fathy, M.Y.Siyal. An Image Detection Technique Based on Morphological Edge Detection and Background Differencing for Real-time Traffic Analysis[J]. Pattern Recognition Letters,1995, 16(2) :1321-1330.
[15] JoonWoongLee. A Machine Vision System for Lane Departure Detection[J]. Computer Vision and Image Understanding, 2002,86(1):52-78.
[16] M Bertozzi, A Broggi, S Castelluccio. A Real-time Oriented System for Vehicle Detection[J]. Journal of System Architecture,1997,43(3):317-325.
[17] C.Setchell, E L Dagless. Vision-based Road traffic Monitoring Sensor[J]. IEEE Proceedings Vision, Image and Signal Processing, 2001,148(1): 78-84.
[18] E.C DiMauro, T F Cootes, C J Taylor, et al. Active Shape Model Search Using Pairwise Geometric Histograms[C]. Proc.Of BritishMachine Vision Conference, 1996, 51(6): 353-362.
[19] G.D.Sullivan, KD Baker. Model-based VehicleDetection and Classification Using Orthographic Approximations[J]. Image and VisionComputing, 1997, 15(8) : 649-654.
[20] Husnain Malik, Farrukh Naeem, Zeeshan Zuberi, Rizwan ul Haq. Vision Based Driving Simulation[C]. Proceedings of the 2004 International Conference on Cyberworlds.lEEE.2004.
[21] Sergiu Nedeschi, Rolf Schmidt, Radu Danescu. High Accuracy Stereo Vision System for Far Distance Obstacle Detection[J].lEEE.2004.
[22] U. Franke and S. Heinrich. Fast Obstacle Detection for Urban Traffic Situations[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 3, NO. 3, SEPTEMEBER 2002.
[23] Luke Fletcher, Lars Petersson and Alexander Zelinsky. Driver Assistance Systems based on Vision In and Out of Vehicles[J].lEEE.2003.
[24] R.Mech, M.Wollborn, A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera[J], Signal Processing, 1998,66(2): 203-217.
[25] Alexander Kirchner, Christian Ameling. Integrated obstacle and road tracking using a laser scanne[C]. Proceedings of the IEEE intelligent vehicle symposium 2000, Dearborn(MI), USA, October 3~5, 2000:675~681.
[26] Alexander Kirchner, Christian Ameling. Integrated obstacle and road tracking using a laser scanner. Proceedings of the IEEE intelligent vehicle symposium 2000, Dearborn(MI), USA, October 3~5, 2000:675~681.
[27]王荣本,李斌,储江伟.世界智能车辆行驶安全保障技术的研究发展[J].公路交通科技.2002, 19(2): 88-92.
[28]陈照章,成立,朱湘临.我国道路交通安全的现状及其对策[J].中国安全科学学报.2002,12(6):14-17.
[29]李克强,侯德藻,高锋等.中国智能交通系统(ITS)与智能汽车技术发展概况[J] .汽车技术.2002年第25期: 23-28.
[30]李晓霞,李百川,侯德藻,陈光武.汽车追尾碰撞预警系统研究[J],中国公路学报.2001,14(3):93~95.
[31] Hideo Mori, N.Moghadam Charkari.Shadow and rhythm as sign patterns of obstacle detection[C].IEEE International Symposium on Industrial Electronics.1993:271-277.
[32] E.D.Dickmanns, Behringer R. et al. The seeing passenger car‘VaMoRs-P’[C]. IEEE Symposium on Intellignet Vehicles.1994:68-73.
[33] Yue Du, Nikolaos P.Papanikolopoulos. Real-Time Vehicle Following through a Novel Symmetry-Based Approach[C]. IEEE International Conference on Robotics and Automation. 1997:3160-3165.
[34] Michael Schwarzinger, Thomas Zielke, et al. Vision-based car-following: Detection, tracking, and identification[C]. IEEE Proceedings on Intelligent Vehicles '92 Symposium. 24~29.
[35] Uwe Handmann, Thomas Kalinke. Fusion of texture and contour based methods for object recognition[C]. IEEE Conference on Intelligent Transportation System. 1997:876~881.
[36] W.von Seelen, C.Curio, J.Gayko, et al. Scene analysis and organization of behavior in driver assistance systems[C]. IEEE Proceedings on Image Processing 2000. 3: 524~527.
[37] N.D.Matthews,P.E.An,D.Charnley,C,J.Harris. Vehicle detection and recognition in greyscale Imagery. Control Engineering Practice[J], 1996, 4(4): 473~479.
[38] U.Handmann, T.Kalinke, C.Tzomakas, et al. An image processing system for driver assistance. Image and Vision Computing[J], 2000, 18(5): 367~376.
[39] D.Guo, T.Fraichard, et al. Color modeling by spherical influence field in sensing driving environment[C]. IEEE Symposium on Intelligent Vehicles 2000. Dearborn, USA. 249~254.
[40] M.Bertozzi, A.Broggi, S.Castelluccio. A real-time oriented system for vehicle detection[J]. Journal of Systems Architecture, 1997, 43(1-5): 317~325.
[41] J.Badenas, M Bober, F Pla. Motion and Intensity based Segmentation and Its Application to Traffic Monitoring[C]. Proceedings of the International Conference on Image Analysis and Proceedings ICIAP’97, Florence, Italy, IAPR, 1997. 502-509.
[42]郭定先,李敏,何光普.小波变化模极大值法检测信号突变点[J].电气应用.2006年第25卷第11期:90-92.
[43]李旭超,朱善安.基于小波模极大值和Neyman-Pearson准则阈值的图像去噪[J].中国图像图形学报.2005年第10卷第8期:964-969.
[44]董泽,谢华,韩璞等.小波变化模极大值消噪算法的研究[J].电力科学与工程.2005年第3期:12-16.
[45] S Mallat, Zhang S. Characterization of Signal from Multiscale Edge[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1992, 14(7): 681-693.
[46] S Mallat, Huang W L. Singularity Detection and Processing with Wavelet[J]. IEEE Transactions on IT, 1992, 14(7): 710-732.
[47] Sun Z, Miller R, Bebis G, Dimea D. A Real-time Precrash Vehicle Detection System[J]. IEEE International Workshop on Application of Computer Vision, 2002(12): 171-176.
[48] M J Shensa. The Discrete Wavelet Transform: Wedding The a trous and Mallat Algorithms [C]. IEEE Trans. Sig. Process, Oct. 1992, 40: 2462-2482.
[49] Handmann U, Kalinke T, Tzomakas C, et al. An Image Processing System for Driver Assistance [J]. Image and Vision Computing, 2000, 18: 367-376.
[50] Ten Kate T K, van Leewen M B, Moro-Ellenberger S E, et al. Mid-range and Distant Vehicle Detection with a Mobile Camera[J]. In: Proceedings of IEEE Symposium on Intelligent Vehicles, Parma, Italy, 2004: 72-77.
[2] Tan Xiao-jun, Shen Wei, Guo Zhi-hao. Vision-based Method for Traffic flow Surveillance on Highway[J]. Computer Applications, 2005, 25(5): 1215-1218.
[3] Raphael L, Didier A. Real Time Obstacle Detection in Stereovision on Non Flat Road Geometry Through“V-disparity”Representation[C]. IEEE Symposium on Intelligent Vehicles, 2002: 646-651.
[4] Broggi A, Bertozzi M, Fascioli A. Self-calibration of a Stereo Vision System for Automotive Applications[C]. IEEE International Conference on Robotics and Automation, 2001: 3698-3703.
[5] Sun Z, Miller R, Bebis G, Dimea D. A Real-time Precrash Vehicle Detection System[J]. IEEE Int. Workshop on Application of Computer Vision, 2002(12): 171-176.
[6] Broggi Albert, Cem Pietro, Antonello Pier Claudio. Multi-Resolution Vehicle Detection Using Artificial Vision[C]. IEEE Intelligent Vehicles Symposium, 2004: 310-314.
[7] Liu Tie, Zheng Nanning, Zhao Li, et al. Learning Based Symmetric Features Selection for Vehicle Detection[C]. IEEE Intelligent Vehicle Symposium, 2005: 124-129.
[8] Handmann U, Kalinke T, Tzomakas C, et al. An Image Processing System for Driver Assistance[J]. Image and Vision Computing, 2000,18: 367-376.
[9] Ten Kate T K, van Leewen M B, et al. Mid-range and Distant Vehicle Detection with a Mobile Camera[C]. IEEE Symposium on Intelligent Vehicles, 2004:72-77.
[10] Y.Park. Shape-resolving Local Thresholding for Object Detection[J].Pattern Recognition Letters, 2001, 22(5) : 883-890.
[11] J.M.Blosseville, C Krafft, F Lenoir, et al. TITAN: New Traffic Measurements by Image Processing[C]. Proc. of IFAC Transportation Systems, 1999, 14(1) : 277-296.
[12] T.Abramczuk. A Microcomputer based TV Detector for Road Traffic[J].In Symposium on Road Research Program, T, 1984, 3(2) : 145-147.
[13] W.Kasparzak. An Iconic Classification Scheme for Video-based Traffic Sensor Tasks[C]. W Skarbek. CAIP 2001, Springer, Berlin, 2001.725-732.
[14] M.Fathy, M.Y.Siyal. An Image Detection Technique Based on Morphological Edge Detection and Background Differencing for Real-time Traffic Analysis[J]. Pattern Recognition Letters,1995, 16(2) :1321-1330.
[15] JoonWoongLee. A Machine Vision System for Lane Departure Detection[J]. Computer Vision and Image Understanding, 2002,86(1):52-78.
[16] M Bertozzi, A Broggi, S Castelluccio. A Real-time Oriented System for Vehicle Detection[J]. Journal of System Architecture,1997,43(3):317-325.
[17] C.Setchell, E L Dagless. Vision-based Road traffic Monitoring Sensor[J]. IEEE Proceedings Vision, Image and Signal Processing, 2001,148(1): 78-84.
[18] E.C DiMauro, T F Cootes, C J Taylor, et al. Active Shape Model Search Using Pairwise Geometric Histograms[C]. Proc.Of BritishMachine Vision Conference, 1996, 51(6): 353-362.
[19] G.D.Sullivan, KD Baker. Model-based VehicleDetection and Classification Using Orthographic Approximations[J]. Image and VisionComputing, 1997, 15(8) : 649-654.
[20] Husnain Malik, Farrukh Naeem, Zeeshan Zuberi, Rizwan ul Haq. Vision Based Driving Simulation[C]. Proceedings of the 2004 International Conference on Cyberworlds.lEEE.2004.
[21] Sergiu Nedeschi, Rolf Schmidt, Radu Danescu. High Accuracy Stereo Vision System for Far Distance Obstacle Detection[J].lEEE.2004.
[22] U. Franke and S. Heinrich. Fast Obstacle Detection for Urban Traffic Situations[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 3, NO. 3, SEPTEMEBER 2002.
[23] Luke Fletcher, Lars Petersson and Alexander Zelinsky. Driver Assistance Systems based on Vision In and Out of Vehicles[J].lEEE.2003.
[24] R.Mech, M.Wollborn, A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera[J], Signal Processing, 1998,66(2): 203-217.
[25] Alexander Kirchner, Christian Ameling. Integrated obstacle and road tracking using a laser scanne[C]. Proceedings of the IEEE intelligent vehicle symposium 2000, Dearborn(MI), USA, October 3~5, 2000:675~681.
[26] Alexander Kirchner, Christian Ameling. Integrated obstacle and road tracking using a laser scanner. Proceedings of the IEEE intelligent vehicle symposium 2000, Dearborn(MI), USA, October 3~5, 2000:675~681.
[27]王荣本,李斌,储江伟.世界智能车辆行驶安全保障技术的研究发展[J].公路交通科技.2002, 19(2): 88-92.
[28]陈照章,成立,朱湘临.我国道路交通安全的现状及其对策[J].中国安全科学学报.2002,12(6):14-17.
[29]李克强,侯德藻,高锋等.中国智能交通系统(ITS)与智能汽车技术发展概况[J] .汽车技术.2002年第25期: 23-28.
[30]李晓霞,李百川,侯德藻,陈光武.汽车追尾碰撞预警系统研究[J],中国公路学报.2001,14(3):93~95.
[31] Hideo Mori, N.Moghadam Charkari.Shadow and rhythm as sign patterns of obstacle detection[C].IEEE International Symposium on Industrial Electronics.1993:271-277.
[32] E.D.Dickmanns, Behringer R. et al. The seeing passenger car‘VaMoRs-P’[C]. IEEE Symposium on Intellignet Vehicles.1994:68-73.
[33] Yue Du, Nikolaos P.Papanikolopoulos. Real-Time Vehicle Following through a Novel Symmetry-Based Approach[C]. IEEE International Conference on Robotics and Automation. 1997:3160-3165.
[34] Michael Schwarzinger, Thomas Zielke, et al. Vision-based car-following: Detection, tracking, and identification[C]. IEEE Proceedings on Intelligent Vehicles '92 Symposium. 24~29.
[35] Uwe Handmann, Thomas Kalinke. Fusion of texture and contour based methods for object recognition[C]. IEEE Conference on Intelligent Transportation System. 1997:876~881.
[36] W.von Seelen, C.Curio, J.Gayko, et al. Scene analysis and organization of behavior in driver assistance systems[C]. IEEE Proceedings on Image Processing 2000. 3: 524~527.
[37] N.D.Matthews,P.E.An,D.Charnley,C,J.Harris. Vehicle detection and recognition in greyscale Imagery. Control Engineering Practice[J], 1996, 4(4): 473~479.
[38] U.Handmann, T.Kalinke, C.Tzomakas, et al. An image processing system for driver assistance. Image and Vision Computing[J], 2000, 18(5): 367~376.
[39] D.Guo, T.Fraichard, et al. Color modeling by spherical influence field in sensing driving environment[C]. IEEE Symposium on Intelligent Vehicles 2000. Dearborn, USA. 249~254.
[40] M.Bertozzi, A.Broggi, S.Castelluccio. A real-time oriented system for vehicle detection[J]. Journal of Systems Architecture, 1997, 43(1-5): 317~325.
[41] J.Badenas, M Bober, F Pla. Motion and Intensity based Segmentation and Its Application to Traffic Monitoring[C]. Proceedings of the International Conference on Image Analysis and Proceedings ICIAP’97, Florence, Italy, IAPR, 1997. 502-509.
[42]郭定先,李敏,何光普.小波变化模极大值法检测信号突变点[J].电气应用.2006年第25卷第11期:90-92.
[43]李旭超,朱善安.基于小波模极大值和Neyman-Pearson准则阈值的图像去噪[J].中国图像图形学报.2005年第10卷第8期:964-969.
[44]董泽,谢华,韩璞等.小波变化模极大值消噪算法的研究[J].电力科学与工程.2005年第3期:12-16.
[45] S Mallat, Zhang S. Characterization of Signal from Multiscale Edge[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1992, 14(7): 681-693.
[46] S Mallat, Huang W L. Singularity Detection and Processing with Wavelet[J]. IEEE Transactions on IT, 1992, 14(7): 710-732.
[47] Sun Z, Miller R, Bebis G, Dimea D. A Real-time Precrash Vehicle Detection System[J]. IEEE International Workshop on Application of Computer Vision, 2002(12): 171-176.
[48] M J Shensa. The Discrete Wavelet Transform: Wedding The a trous and Mallat Algorithms [C]. IEEE Trans. Sig. Process, Oct. 1992, 40: 2462-2482.
[49] Handmann U, Kalinke T, Tzomakas C, et al. An Image Processing System for Driver Assistance [J]. Image and Vision Computing, 2000, 18: 367-376.
[50] Ten Kate T K, van Leewen M B, Moro-Ellenberger S E, et al. Mid-range and Distant Vehicle Detection with a Mobile Camera[J]. In: Proceedings of IEEE Symposium on Intelligent Vehicles, Parma, Italy, 2004: 72-77.