The Image Matching Algorithm Basing on Homographic Constraints for Marine Surveying, Mapping and 3D Reconstruction

ABSTRACT Chen, Y.; Le, Y.; Xie, Z.; Qiu, Z; Zhang, C.; Cao, B., and Fang, S., 2019. The image matching algorithm basing on homographic constraints for marine surveying, mapping and 3D reconstruction. In: Hoang, A.T. and Aqeel Ashraf, M. (eds.), Research, Monitoring, and Engineering of Coastal, Port, and Marine Systems. Journal of Coastal Research, Special Issue No. 97, pp. 184–190. In the marine surveying and mapping, high-accuracy image matching is of crucial importance to improve the surveying and mapping accuracy. For the low texture area, coastal zone, island and reef, the accuracy of the mapping and 3D reconstruction would be impacted by the number of matching points and the matching accuracy, using the conventional matching algorithms basing on the imaging feature, such as scale-invariant feature transform (SIFT), speed-up robust features (SURF) and oriented brief (ORB) et al.. To overcome and reduce the problem, this paper proposes a new image matching algorithm, the homographic constraint SURF algorithm, which combines the homographic constraint condition and SURF algorithm in order to increase the number of the high-accuracy matching points and improve the accuracy of the mapping and 3D reconstruction for the marine surveying and mapping. Through experiments performance, HCSURF can extract the more number of the matching points and obtain the higher matching accuracy for island and reef images, comparing with the SIFT, SURF and ORB algorithms. In addition, the characteristics and application categories of the HCSURF are analyzed and discussed basing on the experimental results. Using the new proposed matching algorithm can improve and ensure the accuracy of the marine surveying, mapping and 3D reconstruction.

[1]  Zhiguo Li,et al.  Economics of biomass gasification: A review of the current status , 2018 .

[2]  Hanliang Fu,et al.  Research on the Phenomenon of Chinese Residents’ Spiritual Contagion for the Reuse of Recycled Water Based on SC-IAT , 2017 .

[3]  Zhenling Liu,et al.  China’s strategy for the development of renewable energies , 2017 .

[4]  Youfang Huang,et al.  A FAST AUTOMATED VISION SYSTEM FOR CONTAINER CORNER CASTING RECOGNITION , 2016 .

[5]  C. Stentoumis,et al.  On accurate dense stereo-matching using a local adaptive multi-cost approach , 2014 .

[6]  Alexandrina Rogozan,et al.  A robust cost function for stereo matching of road scenes , 2014, Pattern Recognit. Lett..

[7]  Guo Zhang,et al.  In‐Orbit Geometric Calibration And Validation Of Zy‐3 Linear Array Sensors , 2014 .

[8]  Romain Dupont,et al.  A General Dense Image Matching Framework Combining Direct and Feature-Based Costs , 2013, 2013 IEEE International Conference on Computer Vision.

[9]  Lei Peng,et al.  A New Organization and Indexing Method of Multibeam Point Cloud Data in 3D Marine GIS , 2013 .

[10]  Ce Liu,et al.  Deformable Spatial Pyramid Matching for Fast Dense Correspondences , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Christos Stentoumis,et al.  A LOCAL ADAPTIVE APPROACH FOR DENSE STEREO MATCHING IN ARCHITECTURAL SCENE RECONSTRUCTION , 2013 .

[12]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[13]  Antonio Adán,et al.  3D Reconstruction of Interior Wall Surfaces under Occlusion and Clutter , 2011, 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission.

[14]  Antonio Torralba,et al.  SIFT Flow: Dense Correspondence across Scenes and Its Applications , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  T. Brox,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation , 2022 .

[16]  V. Lepetit,et al.  DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Lu Wang,et al.  Wide-baseline image matching using Line Signatures , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[18]  Long Quan,et al.  Robust dense matching using local and global geometric constraints , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[19]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[20]  L. Mingsen,et al.  Progress and prospect of Chinese ocean satellites , 2016, National Remote Sensing Bulletin.

[21]  George Pavlidis,et al.  Multi-image 3D reconstruction data evaluation , 2014 .

[22]  姚远,et al.  Dynamic 3D Modeling of Island,Reef and Surrounding Complex Environment , 2012 .

[23]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by , 2011 .

[24]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.