基于机器视觉的着火点定位方法研究
|
摘要
近年来,随着技术进步和嵌入式图像处理系统的发展,图像型火灾探测有望成为在大型工厂、仓库、森林等大空间和野外开放空间进行火灾探测的重要手段,研究基于机器视觉的着火点自动定位问题,可以为火灾的早期发现、自动灭火提供支持,具有重要的应用价值。
论文基于机器视觉定位技术,系统地讨论了图像预处理技术、摄像机模型、摄像机标定、极线校正、立体匹配、三维重建等关键问题,并在此基础上提出了着火点的单目摄像头二维定位、双目立体视觉定位方法,并在VisualC++开发平台下,以Intel公司开发的开源计算机视觉库OpenCV作为定位系统的开发工具,构建了着火点定位系统。实验证明该系统稳定性高、适应性强、实时性好、定位准确,可应用于自动灭火系统。
In recent years, as technology advances and the development of embedded image processing system, image-based fire detection is expected to be an important means of fire detection in large factories, warehouses, forests and other large open and outdoor space. The research based on burning point auto-localization of machine vision, and can give a support for the early detection of fire or automatic fire-fighting, and has an important application value.
The paper is based on the locating technology of machine vision, Systematically discussed the key issues such as the image pre-processing techniques, camera model, camera calibration, epipolar calibration, stereo matching, three-dimensional reconstruction, and on this basis, proposed the method of burning point localization such as Two-dimensional localization based on Monocular Camera and Binocular stereo vision localization. And we use Intel's open source computer vision library OpenCV as a locating system development tools to achieve burning point locating system in Visual C++development platform. Through experiments it proved that the system can be applied to fire automation system with high stability, strong adaptability and good locating accuracy.
论文基于机器视觉定位技术,系统地讨论了图像预处理技术、摄像机模型、摄像机标定、极线校正、立体匹配、三维重建等关键问题,并在此基础上提出了着火点的单目摄像头二维定位、双目立体视觉定位方法,并在VisualC++开发平台下,以Intel公司开发的开源计算机视觉库OpenCV作为定位系统的开发工具,构建了着火点定位系统。实验证明该系统稳定性高、适应性强、实时性好、定位准确,可应用于自动灭火系统。
In recent years, as technology advances and the development of embedded image processing system, image-based fire detection is expected to be an important means of fire detection in large factories, warehouses, forests and other large open and outdoor space. The research based on burning point auto-localization of machine vision, and can give a support for the early detection of fire or automatic fire-fighting, and has an important application value.
The paper is based on the locating technology of machine vision, Systematically discussed the key issues such as the image pre-processing techniques, camera model, camera calibration, epipolar calibration, stereo matching, three-dimensional reconstruction, and on this basis, proposed the method of burning point localization such as Two-dimensional localization based on Monocular Camera and Binocular stereo vision localization. And we use Intel's open source computer vision library OpenCV as a locating system development tools to achieve burning point locating system in Visual C++development platform. Through experiments it proved that the system can be applied to fire automation system with high stability, strong adaptability and good locating accuracy.
引文
[1]孙丽华,刘力辉,冉海潮.火灾探测技术的发展[J].河北科技大学学报,2002,9：36-39.
[2]宋卫国,范维澄,吴龙标.基于人工神经网络的火灾图像探测方法[J].火灾科学,1999,8(3)：49～56.
[3]R.F.Richards, B.N.Murk, O.A.Plumb. Fire Detection, Location and Heat Release Rate Through Inverse Problem Solution.Part I:Theory[J]. Fire Safety Journal,1997,28: 323～350.
[4]R.F.Richards, R.T.Ribail, A.W.Bakkom, O.A.Plumb.Fire Detection, Location and Heat Release Rate Through Inverse Problem Solution.Part II:Experiment[J]. Fire Safety Journal,1997,28 (4):351～378.
[5]冉海潮.火灾图像的模糊识别探测方法[J].模糊系统与数学,2001,9(15)：102～104.
[6]CHENThou-ho, YIN Yen-hui, HUANG Shi-feng. The Smoke Detection for Early Fire-Alarming System Base on Video Processing[C]. Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processingire Safety Journal, Japan,2006:427～430.
[7]郑南宁,计算机视觉与模式识别[M].北京：国防工业出版社,1998.
[8]贾永红,计算机图像处理与分析[M].武汉：武汉大学出版社,2001.9.
[9]CastlemanKR.数字图像处理[M].北京：电子工业出版社,1998.
[10]Rafael C.Gonzalez, Richard E.Woods.数字图像处理[M].北京：电子工业出版社,2003.
[11]何东健,耿楠,张义宽.数字图像处理[M].西安：西安电子科技大学出版社,2003.01.
[12]杨晖,曲秀杰.图像分割方法综述[M].电脑开发与应用,2005,18(3)：21—23.
[13]Linda G.Shapiro, GeorgeC.Stockman. Computer Vision. Beijing:MeehnaieIndustry Publishing ComPany,2005.
[14](美)Rafael C.Gonzalez.数字图像处理(第二版)[M].北京：电子工业出版社,2005,9.
[15]陈兵旗.Visual C++实用图像处理[M].北京：清华大学出版社,2004,3.
[16]张远鹏,董海,周文灵.计算机图像处理技术基础[M].北京：北京大学出版社,1996,6.
[17]姚伟祥.火灾探测一种模糊神经网络方法[J].自然科学进展,1999,9(8)：739-754.
[18]郑南宁.计算机视觉与模式识别[M].北京：国防工业出版社,1998.
[19]马颂德,张正友.计算机视觉一计算理论与算法基础[M].北京：科学出版社,1998.
[20]Zhang Z.Y. A Flexible New Technique for Camera Calibration[J]. IEEE Transactions on Pat tern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[21]E. Malis and R. Cipolla. Multi-view constraints between collineations:application to self-calibration from unknown Planar struetures.In EuroPean Conferenee on ComPuter Vision, June2000.
[22]E.Malis and R.Cipolla. Self-calibration of zooming cameras observing an unknown Planar structure. In Proc.15th International Conference on Paten Recognition(ICPR'OO), Barcelona, Spain,1:85-88, September 2000.
[23]Criminisi, I.Reid and A.Zisserman. A plane measuring device. In Proc. Of the 8th British Maehine Vision Conferenee(BMVC'97)UK, SePtember1997.
[24]Z.Zhang.Parameter Estimation Techniques:A tutorial with Application to Conic Fiting. Reseach report INRIA N02676, October 1995.
[25].Chung-yi Tseng. Problemes Inverses en Scienee Atmospherique:Inversion, AnalyseetASsimilation,附录A1.2矩阵的分解.台湾中央研究院.
[26]R.I.Hartley. In defence of the 8-point algorithm. In Proc.5th International Conference on ComPuter Vision, Pages 1064-1070, Boston, USA, June 1995.
[27]M. Pollefeys. Self-Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequenees. PhD thesis, ESAI-PSI, KatholiekeUniversiteit Leuven, Beigium,1999.
[28]B.Triggs. Auto calibration and the absolute quadric. In Proceedings of the Fifth IEEE Conference on Computer Vision and Patern Recognition, PuertoRieo, USA, Pages609-614,1997.
[29]Z.Y Zhang. Flexible Camera Calibration by Viewing a Plane from Unknown Orientations. In Proe.7th International Conference on Computer Vision, Kerkyra, Greece, Pages 666-673, September 1999.
[30]R.I.Hartley, Theory and practice of projective rectification, International Journal of Computer Vision,1999,35(2):115～127.
[31]Fusiello, E.Trucco, A. Verri, A compact algorithm for rectification of stereo pairs, Machine Vision and Applications,2000,12(1):16～22.
[32]http://www-rocq.inria.fr/-tarel/syntim/
[33]http://cat.middlebury.edu/stereo/newdata.html
[34]C.Sun, Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques, International Journal of Computer Vision,2002.
[35]C.L.Zitnick, T.Kanade, A cooperative algorithm for stereo matching and occlusion detection, Proceedings IEEE Transactions Pattern Analysis and Machine Intelligence, 2000,22(7):675～684.
[36]M.Z.Brown, D.Burschka, Advances in computational stereo, IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(8):993～1008.
[37]Veksler, Fast variable window for stereo correspondence using integral images, Computational Vision and Active Perception Laboratory(CVAP),2003.
[38]T.Kanade, M.Okutomi, A stereo matching algorithm with an adaptive window:Theory and experiment, IEEE Transactions on Pattern Analysis and Machinelntelligence, 1994,16(9):920～932.
[39]刘正东,杨静宇,自适应窗口的时间规整立体匹配算法,计算机辅助设计与图形学学报,2005,17(2)：291～294.
[40]L.D.Stefano, M.Marchionni, S.Mattoccia, A fast area-based stereo matching algorithm, Image and Vision Computing,2004, Vol.22:983～1005.
[41]R:Szeliskil, D.Scharstein, Symmetric sub-pixel stereo matching, ProceedingsEuropean Conference Computer Vision,2002:525～540.
[42]B.D.Lucas, T.Kanade, An iterative image registration technique with an application to stereo vision, Proceedings Int'l Joint Conf.Artificial Intelligence,1981:674～679.
[43]V.S.Kluth, G.W.Kunkel, U.A.Rauhala, Global least squares matching, Proceedings International Geoscience and Remote Sensing Symposium,1992, Vol.2:
[44]夏永泉,刘正东,杨静宇,一种基于正交矩的立体匹配方法,系统仿真学报,2005,17(9)：2082～2084.
[45]李德广,李科杰,一种快速立体视觉边缘匹配算法,计算机应用,2005,25(4)：763～765.
[46]C.Schmid, A.Zisserman, The geometry and matching of curves in multiple views, Proceedings European Conference on Computer Vision,1998:104～118.
[47]V.Venkateswar, R.Chellappa, Hierarchical stereo and motion correspondence using feature groupings, International Journal of Computer Vision,1995, Vol.15:245～269.
[48]陈君,戚飞虎,一种新的基于特征点的立体匹配算法,中国图象图形学报,2005, 10(11):1411～1414.
[49]S.Birchfield, C.Tomasi, Depth discontinuities by pixel-to-pixel stereo, International Journal of Computer Vision,1999,35(3):269～293.
[50]B.Cyganek, J.Borgosz, Maximum disparity threshold estimation for stereo imaging systems via variogram analysis, ICCS 2003, Lecture Notes In Computer Science 2657:591～600.
[51]C.Sun, Fast stereo matching using rectangular subregioning and 3Dmaximum-surface techniques, International Journal of Computer Vision,2002.
[52]C.Tomasi, R.Manduchi, Stereo matching as a nearest-neighbor problem, IEEETrans. Pattern Analysis and Machine Intelligence,1998, Vol.20:333-340.
[53]C.Silva, J.Santos, Intrinsic images for dense stereo matching with occlusions, Proceedings European Conferebce Computer Vision,2000.
[54]Y.Boykov, O.Veksler, R.Zabih, Fast approximate energy minimization via graph cuts, IEEE Transactions on Pattern Analysis and Machine Intelligence,2001, 23(11):1222-1239.
[55]Y.Boykov, V.Kolmogoroy, An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision, Proceedings Third Int'l Workshop Energy Minimization Methods in Computer Vision and Pattern Recognition,2001.
[56]V.Kolmogorov, R.Zabih, Computing visual correspondence with occlusions using graph cuts, Proceedings Int'l Conference Computer Vision,2001.
[57]A.R.Mansouri, A.Mitiche, J.Konrad, Selective image diffusion:application to disparity estimation, Proceedings Int'1 Conference Image Processing,1998, Vol.3:284～288.
[58]D.Scharstein, R.Szeliski, Stereo matching with non-linear diffusion, International Journal of Computer Vision,1998,28(2):155～174.
[59]J.Sun, N.N.Zheng, H.Y.Shum, Stereo matching using belief propagation, IEEETransactions on Pattern Analysis and Machine Intelligence,2003,25(7):787～800.
[60]Faugeras, R.Keriven, Variational principles,surface evolution,PDE's,level setmethods,and the stereo problem, IEEE Transactions.Image Processing,1998, Vol.7:336～344.
[61]F.Bigone, O.Henricsson, P.Fua, Automatic extraction of generic house roofs from high resolution aeriallmagery, Proceedings European Conference Computer Vision, 1996:85～96.
[62]B.Cyganek, J.Borgosz, A comparative study of performance and implementation ofsome area-based stereo algorithms, Proceedings of the 9th International Conference on Computer Analysis of Images and Patterns,2001, Vol.2124:709～716.
[63]D.Scharsitein, R.Szelisi, A taxonomy and evaluation of dense two-frame stereocorrespondence algorithms, International Journal of Computer Vision,2002, 47(1/2/3):7-42.
[64]周秀芝,文贡坚,王润生,自适应窗口快速立体匹配,中国图象图形学报,2006,29(3)：473～479.
[65]H.Hirschmuller, Improvements in real-time correlation-based stereo vision, Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision,2001.
[66]Fusiello, V.Roberto, Efficient stereo with multiple windowing, IEEE Conference on Computer Vision and Pattern Recognition,1997:858～863.
[67]Intel Corporation. Open Source Computer Vision Library Reference Manual [Z].2001.
[68]Gary Bradski, Adrian Kaehler. Learning OpenCV[M]. Beijing.O'REILLY,2008:1.
[2]宋卫国,范维澄,吴龙标.基于人工神经网络的火灾图像探测方法[J].火灾科学,1999,8(3)：49～56.
[3]R.F.Richards, B.N.Murk, O.A.Plumb. Fire Detection, Location and Heat Release Rate Through Inverse Problem Solution.Part I:Theory[J]. Fire Safety Journal,1997,28: 323～350.
[4]R.F.Richards, R.T.Ribail, A.W.Bakkom, O.A.Plumb.Fire Detection, Location and Heat Release Rate Through Inverse Problem Solution.Part II:Experiment[J]. Fire Safety Journal,1997,28 (4):351～378.
[5]冉海潮.火灾图像的模糊识别探测方法[J].模糊系统与数学,2001,9(15)：102～104.
[6]CHENThou-ho, YIN Yen-hui, HUANG Shi-feng. The Smoke Detection for Early Fire-Alarming System Base on Video Processing[C]. Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processingire Safety Journal, Japan,2006:427～430.
[7]郑南宁,计算机视觉与模式识别[M].北京：国防工业出版社,1998.
[8]贾永红,计算机图像处理与分析[M].武汉：武汉大学出版社,2001.9.
[9]CastlemanKR.数字图像处理[M].北京：电子工业出版社,1998.
[10]Rafael C.Gonzalez, Richard E.Woods.数字图像处理[M].北京：电子工业出版社,2003.
[11]何东健,耿楠,张义宽.数字图像处理[M].西安：西安电子科技大学出版社,2003.01.
[12]杨晖,曲秀杰.图像分割方法综述[M].电脑开发与应用,2005,18(3)：21—23.
[13]Linda G.Shapiro, GeorgeC.Stockman. Computer Vision. Beijing:MeehnaieIndustry Publishing ComPany,2005.
[14](美)Rafael C.Gonzalez.数字图像处理(第二版)[M].北京：电子工业出版社,2005,9.
[15]陈兵旗.Visual C++实用图像处理[M].北京：清华大学出版社,2004,3.
[16]张远鹏,董海,周文灵.计算机图像处理技术基础[M].北京：北京大学出版社,1996,6.
[17]姚伟祥.火灾探测一种模糊神经网络方法[J].自然科学进展,1999,9(8)：739-754.
[18]郑南宁.计算机视觉与模式识别[M].北京：国防工业出版社,1998.
[19]马颂德,张正友.计算机视觉一计算理论与算法基础[M].北京：科学出版社,1998.
[20]Zhang Z.Y. A Flexible New Technique for Camera Calibration[J]. IEEE Transactions on Pat tern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[21]E. Malis and R. Cipolla. Multi-view constraints between collineations:application to self-calibration from unknown Planar struetures.In EuroPean Conferenee on ComPuter Vision, June2000.
[22]E.Malis and R.Cipolla. Self-calibration of zooming cameras observing an unknown Planar structure. In Proc.15th International Conference on Paten Recognition(ICPR'OO), Barcelona, Spain,1:85-88, September 2000.
[23]Criminisi, I.Reid and A.Zisserman. A plane measuring device. In Proc. Of the 8th British Maehine Vision Conferenee(BMVC'97)UK, SePtember1997.
[24]Z.Zhang.Parameter Estimation Techniques:A tutorial with Application to Conic Fiting. Reseach report INRIA N02676, October 1995.
[25].Chung-yi Tseng. Problemes Inverses en Scienee Atmospherique:Inversion, AnalyseetASsimilation,附录A1.2矩阵的分解.台湾中央研究院.
[26]R.I.Hartley. In defence of the 8-point algorithm. In Proc.5th International Conference on ComPuter Vision, Pages 1064-1070, Boston, USA, June 1995.
[27]M. Pollefeys. Self-Calibration and Metric 3D Reconstruction from Uncalibrated Image Sequenees. PhD thesis, ESAI-PSI, KatholiekeUniversiteit Leuven, Beigium,1999.
[28]B.Triggs. Auto calibration and the absolute quadric. In Proceedings of the Fifth IEEE Conference on Computer Vision and Patern Recognition, PuertoRieo, USA, Pages609-614,1997.
[29]Z.Y Zhang. Flexible Camera Calibration by Viewing a Plane from Unknown Orientations. In Proe.7th International Conference on Computer Vision, Kerkyra, Greece, Pages 666-673, September 1999.
[30]R.I.Hartley, Theory and practice of projective rectification, International Journal of Computer Vision,1999,35(2):115～127.
[31]Fusiello, E.Trucco, A. Verri, A compact algorithm for rectification of stereo pairs, Machine Vision and Applications,2000,12(1):16～22.
[32]http://www-rocq.inria.fr/-tarel/syntim/
[33]http://cat.middlebury.edu/stereo/newdata.html
[34]C.Sun, Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques, International Journal of Computer Vision,2002.
[35]C.L.Zitnick, T.Kanade, A cooperative algorithm for stereo matching and occlusion detection, Proceedings IEEE Transactions Pattern Analysis and Machine Intelligence, 2000,22(7):675～684.
[36]M.Z.Brown, D.Burschka, Advances in computational stereo, IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(8):993～1008.
[37]Veksler, Fast variable window for stereo correspondence using integral images, Computational Vision and Active Perception Laboratory(CVAP),2003.
[38]T.Kanade, M.Okutomi, A stereo matching algorithm with an adaptive window:Theory and experiment, IEEE Transactions on Pattern Analysis and Machinelntelligence, 1994,16(9):920～932.
[39]刘正东,杨静宇,自适应窗口的时间规整立体匹配算法,计算机辅助设计与图形学学报,2005,17(2)：291～294.
[40]L.D.Stefano, M.Marchionni, S.Mattoccia, A fast area-based stereo matching algorithm, Image and Vision Computing,2004, Vol.22:983～1005.
[41]R:Szeliskil, D.Scharstein, Symmetric sub-pixel stereo matching, ProceedingsEuropean Conference Computer Vision,2002:525～540.
[42]B.D.Lucas, T.Kanade, An iterative image registration technique with an application to stereo vision, Proceedings Int'l Joint Conf.Artificial Intelligence,1981:674～679.
[43]V.S.Kluth, G.W.Kunkel, U.A.Rauhala, Global least squares matching, Proceedings International Geoscience and Remote Sensing Symposium,1992, Vol.2:
[44]夏永泉,刘正东,杨静宇,一种基于正交矩的立体匹配方法,系统仿真学报,2005,17(9)：2082～2084.
[45]李德广,李科杰,一种快速立体视觉边缘匹配算法,计算机应用,2005,25(4)：763～765.
[46]C.Schmid, A.Zisserman, The geometry and matching of curves in multiple views, Proceedings European Conference on Computer Vision,1998:104～118.
[47]V.Venkateswar, R.Chellappa, Hierarchical stereo and motion correspondence using feature groupings, International Journal of Computer Vision,1995, Vol.15:245～269.
[48]陈君,戚飞虎,一种新的基于特征点的立体匹配算法,中国图象图形学报,2005, 10(11):1411～1414.
[49]S.Birchfield, C.Tomasi, Depth discontinuities by pixel-to-pixel stereo, International Journal of Computer Vision,1999,35(3):269～293.
[50]B.Cyganek, J.Borgosz, Maximum disparity threshold estimation for stereo imaging systems via variogram analysis, ICCS 2003, Lecture Notes In Computer Science 2657:591～600.
[51]C.Sun, Fast stereo matching using rectangular subregioning and 3Dmaximum-surface techniques, International Journal of Computer Vision,2002.
[52]C.Tomasi, R.Manduchi, Stereo matching as a nearest-neighbor problem, IEEETrans. Pattern Analysis and Machine Intelligence,1998, Vol.20:333-340.
[53]C.Silva, J.Santos, Intrinsic images for dense stereo matching with occlusions, Proceedings European Conferebce Computer Vision,2000.
[54]Y.Boykov, O.Veksler, R.Zabih, Fast approximate energy minimization via graph cuts, IEEE Transactions on Pattern Analysis and Machine Intelligence,2001, 23(11):1222-1239.
[55]Y.Boykov, V.Kolmogoroy, An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision, Proceedings Third Int'l Workshop Energy Minimization Methods in Computer Vision and Pattern Recognition,2001.
[56]V.Kolmogorov, R.Zabih, Computing visual correspondence with occlusions using graph cuts, Proceedings Int'l Conference Computer Vision,2001.
[57]A.R.Mansouri, A.Mitiche, J.Konrad, Selective image diffusion:application to disparity estimation, Proceedings Int'1 Conference Image Processing,1998, Vol.3:284～288.
[58]D.Scharstein, R.Szeliski, Stereo matching with non-linear diffusion, International Journal of Computer Vision,1998,28(2):155～174.
[59]J.Sun, N.N.Zheng, H.Y.Shum, Stereo matching using belief propagation, IEEETransactions on Pattern Analysis and Machine Intelligence,2003,25(7):787～800.
[60]Faugeras, R.Keriven, Variational principles,surface evolution,PDE's,level setmethods,and the stereo problem, IEEE Transactions.Image Processing,1998, Vol.7:336～344.
[61]F.Bigone, O.Henricsson, P.Fua, Automatic extraction of generic house roofs from high resolution aeriallmagery, Proceedings European Conference Computer Vision, 1996:85～96.
[62]B.Cyganek, J.Borgosz, A comparative study of performance and implementation ofsome area-based stereo algorithms, Proceedings of the 9th International Conference on Computer Analysis of Images and Patterns,2001, Vol.2124:709～716.
[63]D.Scharsitein, R.Szelisi, A taxonomy and evaluation of dense two-frame stereocorrespondence algorithms, International Journal of Computer Vision,2002, 47(1/2/3):7-42.
[64]周秀芝,文贡坚,王润生,自适应窗口快速立体匹配,中国图象图形学报,2006,29(3)：473～479.
[65]H.Hirschmuller, Improvements in real-time correlation-based stereo vision, Proceedings of the IEEE Workshop on Stereo and Multi-Baseline Vision,2001.
[66]Fusiello, V.Roberto, Efficient stereo with multiple windowing, IEEE Conference on Computer Vision and Pattern Recognition,1997:858～863.
[67]Intel Corporation. Open Source Computer Vision Library Reference Manual [Z].2001.
[68]Gary Bradski, Adrian Kaehler. Learning OpenCV[M]. Beijing.O'REILLY,2008:1.