基于单目视觉的道路感知技术研究与实现
|
摘要
随着现代经济的发展,城市化、汽车化的加快,迫切需要交通管理方法的现代化,这样就产生了对智能交通系统(ITS)的研究。车辆辅助驾驶是智能交通系统的重要组成部分,以其自主式车辆事故预警和行驶导航机制,在提高汽车的主动安全性能和减少交通事故方面有着广阔的应用前景。采用计算机视觉技术的辅助驾驶系统,由于探测范围的完整性和宽广性,具有优越的性价比,是辅助驾驶系统的重点发展方向之一。车载辅助驾驶系统旨在向驾驶员提供驾驶道路环境信息、碰撞预警等信息,在过去十几年里,基于视觉的道路感知技术被越来越多地应用于辅助驾驶系统中,因此研究道路的感知技术对车载辅助驾驶系统具有重要的意义。
本文研究的内容是基于车载单目视觉的道路感知技术,研究内容分为三大部分,第一部分建立了3D空间道路成像模型,研究了基于道路模型的图像几何变换,成功地变换成了俯视图,实现了车道偏离警告系统(Lane Departure Warning System: LDWS)中自车在鸟瞰图进行车道的定位,并为其它算法如基于俯视图的车辆、车道识别等提供了基础。第二部分实现了采用基于Retinex算法对低对比度灰度图像的预处理,提出了使之用在特征提取中来提高对象的识别率。最后一部分重点研究了基于边缘的道路检测算法,总结了目前道路的主要检测算法,改进了基于链码的直线检测算法,设计和实现了一种车道线检测算法,从而检测出道路车道区域。
实验结果表明该方法得到了较好的识别效果,很好地识别出了道路车道区域,从而为LDWS系统融合多种道路识别算法提供了重要的依据。
Modern management methods are needed to administer traffic on account of the economical development and the speedup of urbanization and motorization, which begets the research on Intelligent Transportation System-ITS. Driver Assistance System is important issues with applications to Intelligent Transportation System(ITS). Owing to its intrinsic Pre-Accident Warning mechanism, Driver Assistance System has bright prospects, especially in high quality active automobile safety and accident avoidance measurement. The Driver-Assistance System that employs Computer Vision technology is one of the booming research fields, due to their extensive signal detection range, integrity and excellent "Quality-Cost" ratio. Over the past decades of years, vision-based road apperceive algorithms has been used in driver assistance system. On-board automotive driver assistance system is aiming to alert a driver about driving environments, and other information. So the study of vision-based road apperception algorithms is very important to the vehicle assistant system.
The research topic of the thesis is on-board monocular vision-based road apperception technology. It consists of three parts, in the first part, perspective projection model of 3D-road is established. Based on it, the original images can be transformed into bird-eye images, which can fit the lane location results based on bird-eye view, and provide the base for other algorithms such as vehicles、lines detection based IPM image. In the second part, Retinex algorithm is implemented for preprocessing of low-contrast gray images, and has been used in feature extraction methods to improve object detection results. In the last part, after summarizing the current road detection algorithms, an edge-based road detection algorithm is studied, and a chain-based line detection algorithm is improved, then a roadway-lines detection algorithm is designed and implemented, and detect the roadway region.
Experiments show that this method could get a satisfactory result and is useful for the fusion of other road detection algorithms in LDWS.
本文研究的内容是基于车载单目视觉的道路感知技术,研究内容分为三大部分,第一部分建立了3D空间道路成像模型,研究了基于道路模型的图像几何变换,成功地变换成了俯视图,实现了车道偏离警告系统(Lane Departure Warning System: LDWS)中自车在鸟瞰图进行车道的定位,并为其它算法如基于俯视图的车辆、车道识别等提供了基础。第二部分实现了采用基于Retinex算法对低对比度灰度图像的预处理,提出了使之用在特征提取中来提高对象的识别率。最后一部分重点研究了基于边缘的道路检测算法,总结了目前道路的主要检测算法,改进了基于链码的直线检测算法,设计和实现了一种车道线检测算法,从而检测出道路车道区域。
实验结果表明该方法得到了较好的识别效果,很好地识别出了道路车道区域,从而为LDWS系统融合多种道路识别算法提供了重要的依据。
Modern management methods are needed to administer traffic on account of the economical development and the speedup of urbanization and motorization, which begets the research on Intelligent Transportation System-ITS. Driver Assistance System is important issues with applications to Intelligent Transportation System(ITS). Owing to its intrinsic Pre-Accident Warning mechanism, Driver Assistance System has bright prospects, especially in high quality active automobile safety and accident avoidance measurement. The Driver-Assistance System that employs Computer Vision technology is one of the booming research fields, due to their extensive signal detection range, integrity and excellent "Quality-Cost" ratio. Over the past decades of years, vision-based road apperceive algorithms has been used in driver assistance system. On-board automotive driver assistance system is aiming to alert a driver about driving environments, and other information. So the study of vision-based road apperception algorithms is very important to the vehicle assistant system.
The research topic of the thesis is on-board monocular vision-based road apperception technology. It consists of three parts, in the first part, perspective projection model of 3D-road is established. Based on it, the original images can be transformed into bird-eye images, which can fit the lane location results based on bird-eye view, and provide the base for other algorithms such as vehicles、lines detection based IPM image. In the second part, Retinex algorithm is implemented for preprocessing of low-contrast gray images, and has been used in feature extraction methods to improve object detection results. In the last part, after summarizing the current road detection algorithms, an edge-based road detection algorithm is studied, and a chain-based line detection algorithm is improved, then a roadway-lines detection algorithm is designed and implemented, and detect the roadway region.
Experiments show that this method could get a satisfactory result and is useful for the fusion of other road detection algorithms in LDWS.
引文
1.王征平,邵迈,蔡少渠.智能运输系统的产生与发展[J],智能交通,2003,(3)：48—50
2.孙晋文.智能运输系统与汽车的智能化技术[J],汽车研究与开发,2000,(3)：15—16
3. http://col.njtu.edu.cn/shihang/yang/yangzhaoxia/wwwroot/its/ch01_201-TS_ZS/ch01
4. Vehicle-highway automation activities in the United States. US Dept of Transportation,1997
5. Tokuyama H. Asia-pacific projects status and plans. US Dept of Transportation,1997
6. Bertozzi M, Broggi A, Cellario M, Fascioli A, Lombardi P, Porta M. Artificial vision in road vehicles[J], Invited Paper Publisher Item Identifier,2002,90(7):1258-1271
7. Margrit Betke, Esin Haritaoglu, Larry S. Davis. Real-time multiple vehicle detection and tracking from a moving vehicle[J], Machine Vision and Applications,2000,12: 69-83
8. Juan Carlos Rojas, Jill D. Crisman. Vehicle detection in color images[J], Northeastern University Boston, Massachussets, U.S.A.0-7803-4269-0/97 1998 IEEE
9. C. Knoeppel, A. S chanz B.Michaeli.s, Robust Vehicle Detection at Large Distance Using Low Resolution Cameras[J], Proceedings of the IEEE Intelligent Vehicles Symposium 2000 Dearborn (MI), USA October,2000:3-5
10. M. Bertozzi, A.Broggi, A. Fascioli'S. Nichele. Stereo Vision-based Vehicle Detection[J], Proceedings of the IEEE Intelligent Vehicles Symposium 2000 Dearborn (MI), USA October,2000:3-5
11. Massimo Bertozzi, AlbertO Broggi, Gianni Conte. Alessandra Fasciolj obstacle and lane detection on Argo[J], Department of Information University of Parma, Parma, Italy
12. J. M. Collado, C. Hilario A. de la Escalera J. M Armingol. Model Based Vehicle Detection for Intelligent Vehicles[J],2004 IEEE Intelligent Vehicles Symposium University of Parma Parma, Italy,2004:14-17
13.施树明,储江伟,李斌,郭烈,王荣本.基于单目视觉的前方车辆探测方法[J],农业机械学报,2000,35(4)：5—8
14.陶词.基于统计特征的车辆识别算法的研究与实现[D].沈阳东北大学,2005
15. Massimo Bertozzi, Alberto Broggi, Alessandra Fascioli. Stereo Inverse Perspective Mapping[J], Theory and Applications, Image and Vision Computing Journal, 16(8):585-590, June 1998
16. M. Bertozzi and A. Broggi, GOLD:A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection, IEEE Trans-actions on Image Processing, 1998, vol.7, No.1, pp.62-81
17. P. Cerri and P. Grisleri, Free Space Detection on Highways using Time Correlation between Stabilized Sub-pixel precision IPM Images, in IEEE Proc. Int. Conf. on Robotics and Automation, Barcelona, Spain, April 2005, pp.2223-2228
18.G.Y. Jiang. Lane and obstacle detection based on fast inverse perspective mapping algorithm", IEEE Int. Conf. on Systems Man. And Cybernetics, vol.4,2000
19. Marcos Nieto, Luis Salgado. Stabilization of Inverse Perspective Mapping Images based on Robust Vanishing Point Estimation[J], Proceedings of the 2007 IEEE Intelligent Vehicles Symposium Istanbul, Turkey, June 13-15,2007
20. Zhang Z Y. A flexible new technique for camera calibration[J], Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334
21.马颂德,张正友.计算机视觉—计算理论与算法基础[M],北京：科学出版社,1998，52-71
22.王丹.车辆辅助驾驶-运动中二维到三维映射算法的研究与实现[D],沈阳东北大学,2006
23.王萍,张春,罗颖昕.一种雾天图像低对比度增强的快速算法[J],计算机应用,26(1)：152-153,156
24. Kim J K, Kim L S. An Advanced Contrast Enhancement Using Partially Overlapped Sub—block Histogram Equalization[J], IEEE Tran. Circuits and Video Technology, 2001,11(4):475-484
25. Chang DC, Wu W. Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation[J], IEEE Trans. Medical Imaging,1998, 17(4):518-531
26.吴颖谦,施鹏飞,基于小波变换的低对比度图像增强[J].红外与激光工程,2003,32(1)：4—7
27.柯丽,张明慧.基于小波变换的CR图像增强[J].光电子·澈光,2005,16(8)：889-992
28. Jose Salvado, Bruno Roque. Intelligent Signal Processing[J],2005 IEEE International Workshop on 1-3 Sept.2005 Page(s):200-205
29. Arianna Mencattini, Federica Caselli, Marcello Salmeri, and Roberto Lojacono. Wavelet based adapitive algorithm for mammographic images enchacement and denoising [J] Image Processing,2005:114-124
30.焦李成,谭山.图像的多尺度几何分析：回顾和展望[J].电子学报,2003,31(12A)：1975-1981
31. E.Land. The Retinex,American Scientist,vol.52,no.2,pp.247-264, June 1964
32. E. Land and J.McCann. Lightness and Retinex theory. Journal of The Optical Society of America, vol.61,no.l,pp.1-11,January 1971
33. E. Land. An alternative technique for the computation of the designator in the retinex theory of color vision. Proc. Nat. Acad, Sci, vol.83, P3078-3080,1986
34. Brian Funt, Florian Ciurea, and John McCann. Retinex in Matlab[J]. Proceedings of the IS&T/SID Eighth Color Imaging Conference:Color Science, Systems and Applications,2000, pp:112-121
35. Funt, B, Ciurea, F, McCann, J. Retinex in Matlab[J]. Journal of the Electronic Imaging, pp 48-57, Jan.2004
36. Daniel J. Jobson, Zia-ur Rahman, Glenn A. Woodell. A Multiscale Retinex for Bridging the Gap Between Color Images and the Human Observation of Scenes[J]. IEEE Transaction on Image Processing, vol.6, no.7, July 1997
37. Daniel J. Jobson, Zia-ur Rahman, Glenn A. Woodell.Properties and Performance of a Center/Surround Retinex [J]. IEEE Transaction on Image Processing, vol.6, no.3, March 1997
38.A.C. Hurlbert. Formal connections between lightness algorithms[J]. J. Opt. Soc. Amer. A, vol.3, pp.1684-1693,1986
39. Z. Rahman, G. A. Woodell, and D. J. Jobson. A Comparison of the Multiscale Retinex With Other Image Enhancement Techniques[J]. Proceedings of the IS&T 50th Anniversary Conference, May 1997
40. http://dragon.larc.nasa.gov/
41.艾海舟,武勃等译.图像处理、分析与机器视觉(第二版)[M],北京：人民邮电出版社
42. G. Stein,O. Mano, A. Shashua. A robust method for computing vehicle ego-motion[J]. In IEEE Intelligent Vehicles Symposium (IV2000),2000
43. Klaus Hansen, Jens Damgaard Andersen. Understanding the Hough Transform: Hough Cell Support and Its Utilisation [J]. Image and Vision Computing,1997,15 (3):205-218
44. John Immerk·r. Some Remarks on the StraightLine Hough Transform [J]. Pattern Recognition Letters,1998,19 (12):1133-1135
45. H Freeman. Boundary Encoding and Processing[M]. Picture Processing and Psychop ictorics, Academic, New York,1970.241-266
46.顾创,翁富良,吴立德.直线链码的线性提取算法[J].模式识别与人工智能,1990,3(2)：34-38
47. Jianxing Yuan, Ching Y Suen. An Optimal Algorithm for Identifying Line Segments from a Sequence of Chain Codes [J]. PatterRecognition,1995,28 (5):635-646
48.史册,徐胜荣,荆仁杰等.实时图像处理中一种快速的直线检测算法[J].浙江大学学报(工学版),1999,33(5)：482-486
49.孙涵,任明武,杨静宇.一种快速实用的直线检测算法[J].计算机应用研究.2006,2,256-260
50.孙涵,任明武,唐振民,杨静宇.基于机器视觉的智能车辆导航综述[J].公路交通科技.2005,5,132-135
51. V Kastrinaki, M Zervakis, KKalaitzakis. A Survey of Video PrecessingTechniques for Traffic Applications [J]. Image and Vision Computing,2003,21:359-381
52.杨明,陆建业,王宏,张钹.基于视觉的道路跟踪[J].模式识别与人工智能,2001,14(2)：186—193
53. J D Crisman, C E Thorpe. SCARF:A Color Vision System That Tracks Roads and Intersections[J]. IEEE Transactions on Robotics and Automation,1993,9(1):49-58
54. Foedisch M,Takeuchi. Adaptive Real-Time Road Detection Using Neural Networks Intelligent Transportation Systems[J]. The 7th International IEEE Conference on 3-6 Oct.2004 Page(s):167-172
55. Lai A.H.S,Yung, N.H.C. Lane detection by orientation and length discrimination Systems, Man and Cybernetics[J]. IEEE Transactions on Volume 30, Issue 4, Aug. 2000 Page(s):539-548
56. G. W. Cook and E. J. Delp. Multiresolution sequential edge linking[J]. Proc. IEEE ICIP'95, vol.1, pp.41-44,1995
57. S. Vasudevan, R. L. Cannon, and J. C. Bezdek. Heuristics for intermediate level road finding algorithms[J]. Int. J. Comput. Vis., Graph, Image Process, vol.44, pp. 175-190,1998
58.左森,郭晓松,万敬,郭君斌.基于支持向量机的实时路面检测算法[J].计算机工程.2007,4,225-227
2.孙晋文.智能运输系统与汽车的智能化技术[J],汽车研究与开发,2000,(3)：15—16
3. http://col.njtu.edu.cn/shihang/yang/yangzhaoxia/wwwroot/its/ch01_201-TS_ZS/ch01
4. Vehicle-highway automation activities in the United States. US Dept of Transportation,1997
5. Tokuyama H. Asia-pacific projects status and plans. US Dept of Transportation,1997
6. Bertozzi M, Broggi A, Cellario M, Fascioli A, Lombardi P, Porta M. Artificial vision in road vehicles[J], Invited Paper Publisher Item Identifier,2002,90(7):1258-1271
7. Margrit Betke, Esin Haritaoglu, Larry S. Davis. Real-time multiple vehicle detection and tracking from a moving vehicle[J], Machine Vision and Applications,2000,12: 69-83
8. Juan Carlos Rojas, Jill D. Crisman. Vehicle detection in color images[J], Northeastern University Boston, Massachussets, U.S.A.0-7803-4269-0/97 1998 IEEE
9. C. Knoeppel, A. S chanz B.Michaeli.s, Robust Vehicle Detection at Large Distance Using Low Resolution Cameras[J], Proceedings of the IEEE Intelligent Vehicles Symposium 2000 Dearborn (MI), USA October,2000:3-5
10. M. Bertozzi, A.Broggi, A. Fascioli'S. Nichele. Stereo Vision-based Vehicle Detection[J], Proceedings of the IEEE Intelligent Vehicles Symposium 2000 Dearborn (MI), USA October,2000:3-5
11. Massimo Bertozzi, AlbertO Broggi, Gianni Conte. Alessandra Fasciolj obstacle and lane detection on Argo[J], Department of Information University of Parma, Parma, Italy
12. J. M. Collado, C. Hilario A. de la Escalera J. M Armingol. Model Based Vehicle Detection for Intelligent Vehicles[J],2004 IEEE Intelligent Vehicles Symposium University of Parma Parma, Italy,2004:14-17
13.施树明,储江伟,李斌,郭烈,王荣本.基于单目视觉的前方车辆探测方法[J],农业机械学报,2000,35(4)：5—8
14.陶词.基于统计特征的车辆识别算法的研究与实现[D].沈阳东北大学,2005
15. Massimo Bertozzi, Alberto Broggi, Alessandra Fascioli. Stereo Inverse Perspective Mapping[J], Theory and Applications, Image and Vision Computing Journal, 16(8):585-590, June 1998
16. M. Bertozzi and A. Broggi, GOLD:A Parallel Real-Time Stereo Vision System for Generic Obstacle and Lane Detection, IEEE Trans-actions on Image Processing, 1998, vol.7, No.1, pp.62-81
17. P. Cerri and P. Grisleri, Free Space Detection on Highways using Time Correlation between Stabilized Sub-pixel precision IPM Images, in IEEE Proc. Int. Conf. on Robotics and Automation, Barcelona, Spain, April 2005, pp.2223-2228
18.G.Y. Jiang. Lane and obstacle detection based on fast inverse perspective mapping algorithm", IEEE Int. Conf. on Systems Man. And Cybernetics, vol.4,2000
19. Marcos Nieto, Luis Salgado. Stabilization of Inverse Perspective Mapping Images based on Robust Vanishing Point Estimation[J], Proceedings of the 2007 IEEE Intelligent Vehicles Symposium Istanbul, Turkey, June 13-15,2007
20. Zhang Z Y. A flexible new technique for camera calibration[J], Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334
21.马颂德,张正友.计算机视觉—计算理论与算法基础[M],北京：科学出版社,1998，52-71
22.王丹.车辆辅助驾驶-运动中二维到三维映射算法的研究与实现[D],沈阳东北大学,2006
23.王萍,张春,罗颖昕.一种雾天图像低对比度增强的快速算法[J],计算机应用,26(1)：152-153,156
24. Kim J K, Kim L S. An Advanced Contrast Enhancement Using Partially Overlapped Sub—block Histogram Equalization[J], IEEE Tran. Circuits and Video Technology, 2001,11(4):475-484
25. Chang DC, Wu W. Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation[J], IEEE Trans. Medical Imaging,1998, 17(4):518-531
26.吴颖谦,施鹏飞,基于小波变换的低对比度图像增强[J].红外与激光工程,2003,32(1)：4—7
27.柯丽,张明慧.基于小波变换的CR图像增强[J].光电子·澈光,2005,16(8)：889-992
28. Jose Salvado, Bruno Roque. Intelligent Signal Processing[J],2005 IEEE International Workshop on 1-3 Sept.2005 Page(s):200-205
29. Arianna Mencattini, Federica Caselli, Marcello Salmeri, and Roberto Lojacono. Wavelet based adapitive algorithm for mammographic images enchacement and denoising [J] Image Processing,2005:114-124
30.焦李成,谭山.图像的多尺度几何分析：回顾和展望[J].电子学报,2003,31(12A)：1975-1981
31. E.Land. The Retinex,American Scientist,vol.52,no.2,pp.247-264, June 1964
32. E. Land and J.McCann. Lightness and Retinex theory. Journal of The Optical Society of America, vol.61,no.l,pp.1-11,January 1971
33. E. Land. An alternative technique for the computation of the designator in the retinex theory of color vision. Proc. Nat. Acad, Sci, vol.83, P3078-3080,1986
34. Brian Funt, Florian Ciurea, and John McCann. Retinex in Matlab[J]. Proceedings of the IS&T/SID Eighth Color Imaging Conference:Color Science, Systems and Applications,2000, pp:112-121
35. Funt, B, Ciurea, F, McCann, J. Retinex in Matlab[J]. Journal of the Electronic Imaging, pp 48-57, Jan.2004
36. Daniel J. Jobson, Zia-ur Rahman, Glenn A. Woodell. A Multiscale Retinex for Bridging the Gap Between Color Images and the Human Observation of Scenes[J]. IEEE Transaction on Image Processing, vol.6, no.7, July 1997
37. Daniel J. Jobson, Zia-ur Rahman, Glenn A. Woodell.Properties and Performance of a Center/Surround Retinex [J]. IEEE Transaction on Image Processing, vol.6, no.3, March 1997
38.A.C. Hurlbert. Formal connections between lightness algorithms[J]. J. Opt. Soc. Amer. A, vol.3, pp.1684-1693,1986
39. Z. Rahman, G. A. Woodell, and D. J. Jobson. A Comparison of the Multiscale Retinex With Other Image Enhancement Techniques[J]. Proceedings of the IS&T 50th Anniversary Conference, May 1997
40. http://dragon.larc.nasa.gov/
41.艾海舟,武勃等译.图像处理、分析与机器视觉(第二版)[M],北京：人民邮电出版社
42. G. Stein,O. Mano, A. Shashua. A robust method for computing vehicle ego-motion[J]. In IEEE Intelligent Vehicles Symposium (IV2000),2000
43. Klaus Hansen, Jens Damgaard Andersen. Understanding the Hough Transform: Hough Cell Support and Its Utilisation [J]. Image and Vision Computing,1997,15 (3):205-218
44. John Immerk·r. Some Remarks on the StraightLine Hough Transform [J]. Pattern Recognition Letters,1998,19 (12):1133-1135
45. H Freeman. Boundary Encoding and Processing[M]. Picture Processing and Psychop ictorics, Academic, New York,1970.241-266
46.顾创,翁富良,吴立德.直线链码的线性提取算法[J].模式识别与人工智能,1990,3(2)：34-38
47. Jianxing Yuan, Ching Y Suen. An Optimal Algorithm for Identifying Line Segments from a Sequence of Chain Codes [J]. PatterRecognition,1995,28 (5):635-646
48.史册,徐胜荣,荆仁杰等.实时图像处理中一种快速的直线检测算法[J].浙江大学学报(工学版),1999,33(5)：482-486
49.孙涵,任明武,杨静宇.一种快速实用的直线检测算法[J].计算机应用研究.2006,2,256-260
50.孙涵,任明武,唐振民,杨静宇.基于机器视觉的智能车辆导航综述[J].公路交通科技.2005,5,132-135
51. V Kastrinaki, M Zervakis, KKalaitzakis. A Survey of Video PrecessingTechniques for Traffic Applications [J]. Image and Vision Computing,2003,21:359-381
52.杨明,陆建业,王宏,张钹.基于视觉的道路跟踪[J].模式识别与人工智能,2001,14(2)：186—193
53. J D Crisman, C E Thorpe. SCARF:A Color Vision System That Tracks Roads and Intersections[J]. IEEE Transactions on Robotics and Automation,1993,9(1):49-58
54. Foedisch M,Takeuchi. Adaptive Real-Time Road Detection Using Neural Networks Intelligent Transportation Systems[J]. The 7th International IEEE Conference on 3-6 Oct.2004 Page(s):167-172
55. Lai A.H.S,Yung, N.H.C. Lane detection by orientation and length discrimination Systems, Man and Cybernetics[J]. IEEE Transactions on Volume 30, Issue 4, Aug. 2000 Page(s):539-548
56. G. W. Cook and E. J. Delp. Multiresolution sequential edge linking[J]. Proc. IEEE ICIP'95, vol.1, pp.41-44,1995
57. S. Vasudevan, R. L. Cannon, and J. C. Bezdek. Heuristics for intermediate level road finding algorithms[J]. Int. J. Comput. Vis., Graph, Image Process, vol.44, pp. 175-190,1998
58.左森,郭晓松,万敬,郭君斌.基于支持向量机的实时路面检测算法[J].计算机工程.2007,4,225-227