水下图像实时拼接方法的研究
|
摘要
目前,水下图像拼接技术存在实时性欠缺、鲁棒性不高的问题,极大地影响了水下视觉技术的发展。本文提出一种水下图像拼接方法,目的是对水下图像进行实时、鲁棒地镶嵌,以获取大范围、无缝隙的水下拼合图像。首先加入针对水下图像的预处理环节;然后对鲁棒性好但处理速度慢的SIFT算法进行改进,将基于SURF算法的图像配准方法应用于水下图像配准;最后,使用基于分水岭变换与最大流/最小截方法的搜寻最佳缝合线的水下图像融合算法实现图像融合,完成水下图像拼接。实验结果显示,水下图像预处理方法可以有效的改善水下图像质量,并为后续的图像配准做好准备;基于SURF算法的水下图像配准算法,在提升图像配准速度方面效果明显,具有很好的实时性,并且在图像配准的准确度方面与基于SIFT算法的方法相当,同时具有较好的鲁棒性;基于分水岭变换与最大流/最小截方法的搜寻最佳缝合线的水下图像快速融合算法,可以有效地消除融合鬼影,消除或减弱拼接缝隙,改善拼接质量。
本方法满足对水下图像拼接技术实时性、鲁棒性和自动性的需要,为海下航行器完成特定的海洋探索、海洋监测任务,特别是在水下视觉导航方面提供一定的帮助,体现工程实用性。
Currently, underwater images mosaic technology has problems of the lack of real-time performance and low robustness which greatly influenced the development of underwater vision techniques. This paper presented an underwater image mosaic method, which aims to in real-time and robustly, complete underwater images mosaic to obtain the large-scale, seamless mosaic images underwater. First, an underwater image preprocessing method was added. Then, SIFT algorithm, which has good robustness, but slow processing speed, was improved. Images registration method based on SURF algorithm was applied to underwater images registration. Finally, optimal seam finding underwater images fusion method based on watershed transformation and max-flow/min-cut was used to achieve underwater images fusion and complete underwater mosaic. The experimental results showed that underwater image preprocessing method can effectively improve image quality and be prepared for following underwater images registration. Underwater image registration method based on SURF algorithm which can obviously speed up image registration has good real-time performance and considerable robustness. And compared with SIFT-based image registration method, their accuracy was almost equal. Optimal seam finding underwater images fusion method based on watershed transformation and max-flow/min-cut can effectively eliminate ghosting, clear or weaken stitching seam, improving images mosaic quality.
The presented method of underwater image mosaic method meets the needs of real-time performance, robustness, and automation, which can help underwater vehicles to complete specific marine inspection and ocean exploration tasks, especially in underwater visual navigation, reflecting engineering practicability.
本方法满足对水下图像拼接技术实时性、鲁棒性和自动性的需要,为海下航行器完成特定的海洋探索、海洋监测任务,特别是在水下视觉导航方面提供一定的帮助,体现工程实用性。
Currently, underwater images mosaic technology has problems of the lack of real-time performance and low robustness which greatly influenced the development of underwater vision techniques. This paper presented an underwater image mosaic method, which aims to in real-time and robustly, complete underwater images mosaic to obtain the large-scale, seamless mosaic images underwater. First, an underwater image preprocessing method was added. Then, SIFT algorithm, which has good robustness, but slow processing speed, was improved. Images registration method based on SURF algorithm was applied to underwater images registration. Finally, optimal seam finding underwater images fusion method based on watershed transformation and max-flow/min-cut was used to achieve underwater images fusion and complete underwater mosaic. The experimental results showed that underwater image preprocessing method can effectively improve image quality and be prepared for following underwater images registration. Underwater image registration method based on SURF algorithm which can obviously speed up image registration has good real-time performance and considerable robustness. And compared with SIFT-based image registration method, their accuracy was almost equal. Optimal seam finding underwater images fusion method based on watershed transformation and max-flow/min-cut can effectively eliminate ghosting, clear or weaken stitching seam, improving images mosaic quality.
The presented method of underwater image mosaic method meets the needs of real-time performance, robustness, and automation, which can help underwater vehicles to complete specific marine inspection and ocean exploration tasks, especially in underwater visual navigation, reflecting engineering practicability.
引文
[1] K. Richmond,“REAL-TIME VISUAL MOSAICKING AND NAVIGATION ON THE SEA FLOOR”, PhD thesis, Stanford University, 2009
[2]贺彬,王国宇.不同视点海底图像拼接算法[J].微计算机信息,2005,12(3):152-154
[3] N. Gracias, S. Van der Zwaan, A. Bernardino, and J. Santos-Vitor,“Results on underwater mosaic-based navigation”. In MTS/IEEE Oceans, 2002, volume3:1588–1594.
[4] J. Santos-Victor and J. Sentiero. The role of vision for underwater vehicles. In Proceedings of IEEE International Symposium on Autonomous Underwater Vehicle Technology AUVT94, Boston, USA, July 1994
[5] A. Leone, C. Distante, A. Mastrolia, and G. Indiveri,“A fully automated approach for underwater mosaicking,”Oceans MTS/IEEE, Boston, Sep 2006
[6] N.Gracias, S.Zwaan, A.Bernardino, and J.Santos-Victor. Mosaic based Navigation for Autonomous Underwater Vehicles. IEEE Journal of Oceanic Engineering, 200328(4):609–624.
[7]余宏生,金伟其.数字图像镶嵌方法研究进展[J],红外技术, 2009, 31(6): 348-353
[8] Kou Xinyu, Wang Zhong, Chen Mingzhou, Ye Shenhua,“A ways-free registration method and its application in 3-D data fusion”, Proceedings of SPIE, 2001, Vol.4553: 280-285
[9]王娟,师军,吴宪祥.图像镶嵌方法综述[J].计算机应用研究,2008,25(7):1940～1943.
[10] Chen Mingzhou, Wang Zhong,“Grid-code-based fast matching method in active binocular vison”, Proceedings of SPIE, 2001, Vol.4552: 253-258
[11]蔡丽欢,廖英豪,郭东辉.图像镶嵌方法及其关键技术研究[ J ].计算机技术与发展, 2008,18(3): 1-4.
[12] D. G. Lowe,“Object recognition from local scale-invariant features. In International Conference on Computer Vision, Corfu, Greece, 1999:1150–1157.
[13] D. G. Lowe,“Distinctive image features from scale-invariant keypoints,”International Journal of Computer Vision, 2004,60(2): 91–110.
[14] M. Brown and D. Lowe,“Recognising panoramas,”in IEEE International Conference on Computer Vision, ICCV2005, IEEE, 2005, vol.2:1218–1225.
[15] K. Mikolajczyk and C. Schmid,“A Performance Evaluation of Local Descriptors”, IEE Transactions on Pattern Analysis and Machine Intelligence, Oct. 2005,Vol.27, No.10.
[16] Kudzinava,M., Garcia,R., Marti,J,“Feature-Based Matching of Underwater Images”In: International Workshop on Marine Technology”, 2007:96-97
[17] R. Garcia, T. Nicosevici and X.Cufi,“On the way to solve lighting problems in underwater imaging,”IEEE OCEAN 02, 2002:1018-1024.
[18]周定富,何明一,杨青.一种基于特征点的稳健无缝图像镶嵌算法.测控技术,2009,28(6):32-36
[19] R. Haywood, "Acquisition of a micro scale photographic survey using an autonomous submersible," Proc. of IEEE OCEANS Conf, 1986, vol. 18:1423-1426.
[20] Y. Rzhanov, R. G. Cutter, Jr., and L. Huff,“Sensor-assisted video mosaicing for sea?oor mapping,”in Proceedings of the 2001 International Conference on Image Processing, , IEEE, Oct 2001, vol.2:411–414.
[21] H. Singh, J. Howland, and O. Pizarro.“Advances in large-area photomosaicking underwater,”IEEE Journal of Oceanic Engineering, July 2004, vol.29:872–886.
[22] Pizarro and H. Singh,“Toward large-area mosaicing for underwater scientific applications,”IEEE Journal of Oceanic Engineering, Oct.2003, vol.28:651–672.
[23] LEONE A, DISTANTE C, MASTROLIA A, et al.. A fully automated approach for underwater mosaicking[C]. Oceans MTS/IEEE, Boston, USA: IEEE, 2006:1-6.
[24] R. Marks, S. Rock, and M. Lee,“Real-time video mosaicking of the ocean?oor,”IEEE Journal of Oceanic Engineering, July 1995, vol.20:229–241.
[25] R. L. Marks, S. M. Rock, and M. J. Lee,“Real-time video mosaicking of the ocean floor,”in Proceedings of IEEE Symposium on Autonomous Underwater Vehicle Technology, Cambridge, MA, IEEE,July 1994.
[26] H. Bay et al.,“SURF: Speeded up robust features”, Proc. ECCV’06, 2006:404-417.
[27] H. Bay, T. Tuytelaars, L. Van Gool,“Surf: Speeded up robust features”, in European Conference on Computer Vision,2006
[28] SZELISKI R. Video mosaics for vitural enviroments[J]. IEEE Computer Graphics and Application, 1996, 16(2): 22-30
[29]方贤勇,图像拼接技术研究:[硕士学位论文],浙江;浙江大学,2005
[30]罗三定,贺俊耀.基于SURF和KLT跟踪的图像拼接算法[J],计算机工程,2010,36(1):215-217
[31]赵振兵电气设备红外与可见光图像的配准方法研究:[硕士学位论文],河北:华北电力大学,2009
[32]张锐娟,图像配准理论及算法研究:[硕士学位论文],陕西:西安电子科技大学,2009
[33]张锐娟,张建奇,杨翠.基于SURF的图像配准方法研究[J],红外与激光工程,2009,38(1):160-165
[34]李勤,俞信.适合于生物图像的图像融合算法研究[J].光学学报, 20(4): 495-500
[35]王彦敏,基于分水岭和欧拉数原理的智能计数方法的研究与开发:[硕士学位论文],北京;北京化工大学,2006
[36] H.Digbael and C.Lantuejoul,Iterative algorithms.In Actes du second Symposimu EuorPenas Analyses Qunatitative des Mierosurtetures en Seiences des Materiux,Biologie et Medecine,Caen,4-7 Oetober 1977(1978),J-L. Chennant,Ed.,Stuttgart,85-99
[37] C.Lantuejoul, Lasquelettisation etson application aux measure topologiques polyeristallines.PhD thesis, Ecolede Mines, Paris, 1978
[38] S. Beucher and C. lantuejoul, Use of watersheds in contour detection. In Proc. international Workshop on Image Processing, Real-Time Edge and Motion Detection/Estimation, Rennes, Setember, 1979
[39] Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations.IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583-598.
[40]杨柳青,基于分水岭变换和Contourlet变换的图像分割方法研究:[硕士学位论文],陕西;西安电子科技大学,2009
[41]侯叶,郭宝龙.基于图切割的快速运动分割方法[J].系统工程与电子技术,2009,31(12): 2998-3001
[42] Boykov Y, Kolmogorov V. An experimental comparision of min-cut/ max-flow algorithms for energy minimization in vision[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137
[43] Greig D, Porteous B, Seheult A. Exact maximum a posteriori estimation for binary images[J]. Journal of the Royal Statistical Society, Series, 1989, 1989, 51(2): 271-279
[44] L.Ford, D.Fulkerson, Flows in Networks, Princeton University Press,1962
[45] Boykov Y, Velsker O, et al., Fast Approximate Energy Minimization Via Graph Cuts, Internaional Conference on Computer Vision, Corfu, Greece, 1999: 377-384
[46] Meyer, Fernand, "Topographic distance and watershed lines," Signal Processing , Vol. 38, July 1994, pp. 113-125
[47]杨俊飞.着眼于构建和谐海洋,全面加强国家海洋战略能力的建设[C],第六届军事海洋战略与发展论坛,中国大连:中国海洋学会军事海洋学专业委员会,2009,1-5
[2]贺彬,王国宇.不同视点海底图像拼接算法[J].微计算机信息,2005,12(3):152-154
[3] N. Gracias, S. Van der Zwaan, A. Bernardino, and J. Santos-Vitor,“Results on underwater mosaic-based navigation”. In MTS/IEEE Oceans, 2002, volume3:1588–1594.
[4] J. Santos-Victor and J. Sentiero. The role of vision for underwater vehicles. In Proceedings of IEEE International Symposium on Autonomous Underwater Vehicle Technology AUVT94, Boston, USA, July 1994
[5] A. Leone, C. Distante, A. Mastrolia, and G. Indiveri,“A fully automated approach for underwater mosaicking,”Oceans MTS/IEEE, Boston, Sep 2006
[6] N.Gracias, S.Zwaan, A.Bernardino, and J.Santos-Victor. Mosaic based Navigation for Autonomous Underwater Vehicles. IEEE Journal of Oceanic Engineering, 200328(4):609–624.
[7]余宏生,金伟其.数字图像镶嵌方法研究进展[J],红外技术, 2009, 31(6): 348-353
[8] Kou Xinyu, Wang Zhong, Chen Mingzhou, Ye Shenhua,“A ways-free registration method and its application in 3-D data fusion”, Proceedings of SPIE, 2001, Vol.4553: 280-285
[9]王娟,师军,吴宪祥.图像镶嵌方法综述[J].计算机应用研究,2008,25(7):1940～1943.
[10] Chen Mingzhou, Wang Zhong,“Grid-code-based fast matching method in active binocular vison”, Proceedings of SPIE, 2001, Vol.4552: 253-258
[11]蔡丽欢,廖英豪,郭东辉.图像镶嵌方法及其关键技术研究[ J ].计算机技术与发展, 2008,18(3): 1-4.
[12] D. G. Lowe,“Object recognition from local scale-invariant features. In International Conference on Computer Vision, Corfu, Greece, 1999:1150–1157.
[13] D. G. Lowe,“Distinctive image features from scale-invariant keypoints,”International Journal of Computer Vision, 2004,60(2): 91–110.
[14] M. Brown and D. Lowe,“Recognising panoramas,”in IEEE International Conference on Computer Vision, ICCV2005, IEEE, 2005, vol.2:1218–1225.
[15] K. Mikolajczyk and C. Schmid,“A Performance Evaluation of Local Descriptors”, IEE Transactions on Pattern Analysis and Machine Intelligence, Oct. 2005,Vol.27, No.10.
[16] Kudzinava,M., Garcia,R., Marti,J,“Feature-Based Matching of Underwater Images”In: International Workshop on Marine Technology”, 2007:96-97
[17] R. Garcia, T. Nicosevici and X.Cufi,“On the way to solve lighting problems in underwater imaging,”IEEE OCEAN 02, 2002:1018-1024.
[18]周定富,何明一,杨青.一种基于特征点的稳健无缝图像镶嵌算法.测控技术,2009,28(6):32-36
[19] R. Haywood, "Acquisition of a micro scale photographic survey using an autonomous submersible," Proc. of IEEE OCEANS Conf, 1986, vol. 18:1423-1426.
[20] Y. Rzhanov, R. G. Cutter, Jr., and L. Huff,“Sensor-assisted video mosaicing for sea?oor mapping,”in Proceedings of the 2001 International Conference on Image Processing, , IEEE, Oct 2001, vol.2:411–414.
[21] H. Singh, J. Howland, and O. Pizarro.“Advances in large-area photomosaicking underwater,”IEEE Journal of Oceanic Engineering, July 2004, vol.29:872–886.
[22] Pizarro and H. Singh,“Toward large-area mosaicing for underwater scientific applications,”IEEE Journal of Oceanic Engineering, Oct.2003, vol.28:651–672.
[23] LEONE A, DISTANTE C, MASTROLIA A, et al.. A fully automated approach for underwater mosaicking[C]. Oceans MTS/IEEE, Boston, USA: IEEE, 2006:1-6.
[24] R. Marks, S. Rock, and M. Lee,“Real-time video mosaicking of the ocean?oor,”IEEE Journal of Oceanic Engineering, July 1995, vol.20:229–241.
[25] R. L. Marks, S. M. Rock, and M. J. Lee,“Real-time video mosaicking of the ocean floor,”in Proceedings of IEEE Symposium on Autonomous Underwater Vehicle Technology, Cambridge, MA, IEEE,July 1994.
[26] H. Bay et al.,“SURF: Speeded up robust features”, Proc. ECCV’06, 2006:404-417.
[27] H. Bay, T. Tuytelaars, L. Van Gool,“Surf: Speeded up robust features”, in European Conference on Computer Vision,2006
[28] SZELISKI R. Video mosaics for vitural enviroments[J]. IEEE Computer Graphics and Application, 1996, 16(2): 22-30
[29]方贤勇,图像拼接技术研究:[硕士学位论文],浙江;浙江大学,2005
[30]罗三定,贺俊耀.基于SURF和KLT跟踪的图像拼接算法[J],计算机工程,2010,36(1):215-217
[31]赵振兵电气设备红外与可见光图像的配准方法研究:[硕士学位论文],河北:华北电力大学,2009
[32]张锐娟,图像配准理论及算法研究:[硕士学位论文],陕西:西安电子科技大学,2009
[33]张锐娟,张建奇,杨翠.基于SURF的图像配准方法研究[J],红外与激光工程,2009,38(1):160-165
[34]李勤,俞信.适合于生物图像的图像融合算法研究[J].光学学报, 20(4): 495-500
[35]王彦敏,基于分水岭和欧拉数原理的智能计数方法的研究与开发:[硕士学位论文],北京;北京化工大学,2006
[36] H.Digbael and C.Lantuejoul,Iterative algorithms.In Actes du second Symposimu EuorPenas Analyses Qunatitative des Mierosurtetures en Seiences des Materiux,Biologie et Medecine,Caen,4-7 Oetober 1977(1978),J-L. Chennant,Ed.,Stuttgart,85-99
[37] C.Lantuejoul, Lasquelettisation etson application aux measure topologiques polyeristallines.PhD thesis, Ecolede Mines, Paris, 1978
[38] S. Beucher and C. lantuejoul, Use of watersheds in contour detection. In Proc. international Workshop on Image Processing, Real-Time Edge and Motion Detection/Estimation, Rennes, Setember, 1979
[39] Vincent L,Soille P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations.IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583-598.
[40]杨柳青,基于分水岭变换和Contourlet变换的图像分割方法研究:[硕士学位论文],陕西;西安电子科技大学,2009
[41]侯叶,郭宝龙.基于图切割的快速运动分割方法[J].系统工程与电子技术,2009,31(12): 2998-3001
[42] Boykov Y, Kolmogorov V. An experimental comparision of min-cut/ max-flow algorithms for energy minimization in vision[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137
[43] Greig D, Porteous B, Seheult A. Exact maximum a posteriori estimation for binary images[J]. Journal of the Royal Statistical Society, Series, 1989, 1989, 51(2): 271-279
[44] L.Ford, D.Fulkerson, Flows in Networks, Princeton University Press,1962
[45] Boykov Y, Velsker O, et al., Fast Approximate Energy Minimization Via Graph Cuts, Internaional Conference on Computer Vision, Corfu, Greece, 1999: 377-384
[46] Meyer, Fernand, "Topographic distance and watershed lines," Signal Processing , Vol. 38, July 1994, pp. 113-125
[47]杨俊飞.着眼于构建和谐海洋,全面加强国家海洋战略能力的建设[C],第六届军事海洋战略与发展论坛,中国大连:中国海洋学会军事海洋学专业委员会,2009,1-5