Robust Underwater Image Stitching Based on Graph Matching
Image stitching is important in intelligent perception and manipulation of underwater robots. In spite of a well developed technique, it is still challenging for underwater images because of their inevitable appearance ambiguity. For the feature based underwater image stitching, robust feature correspondence is the key because most other algorithmic parts are less directly associated with the characteristics of underwater images. Structural information between feature points may be helpful for robust feature correspondence, and based on this idea the paper proposes a robust underwater image stitching method by incorporating structural cues as additional information, whose effectiveness is validated on real underwater images. Specifically, the appearance information and structural cues are integrated by a labeled weighted graph, and the underwater image correspondence is formulated by graph matching. After geometric transformation estimation, the underwater images are finally blended into a wider viewing image.
KeywordsUnderwater image Image stitching Feature correspondence Graph matching Structural information
This work is supported partly by the National Natural Science Foundation (NSFC) of China (grants 61503383, 61633009, U1613213, 61375005, 61210009, and 61773047), partly by the National Key Research and Development Plan of China (grant 2016YFC0300801), partly by the Beijing Municipal Science and Technology (grants D16110400140000 and D161100001416001), and Guangdong Science and Technology Department (grant 2016B090910001).
- 2.Huang, H., Tang, Q., Li, H., Liang, L., Li, W., Pang, Y.: Vehicle-manipulator system dynamic modeling and control for underwater autonomous manipulation. Multibody Syst. Dyn. (2017). doi: 10.1007/s11044-0169538-3
- 3.Tang, Y., Li, S., Zhang, A.: Research on optimization design of a new type of underwater vehicle for arctic expedition. In: Proceedings of the International Symposium Underwater Technology, pp. 96–100 (2009)Google Scholar
- 4.Lowe, D.: Object recognition from local scale-invariant features. In: Proceedings of IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)Google Scholar
- 5.Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Proceedigs of the European Conference on Computer vision, pp. 404–417 (2006)Google Scholar
- 7.Yang, X., Liu, Z., Qiao, H., Song, Y., Ren, S., Zheng, S.: Underwater image matching by incorporating structural constraints. Int. J. Adv. Robot. Syst. Under RevisionGoogle Scholar
- 9.Belongie, S., Malik, J.: Matching with shape contexts. In: Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries, pp. 20–26 (2000)Google Scholar
- 10.Leone, A., Distante, C., Mastrolia, A., Indiveri, G.: A fully automated approach for underwater mosaicking. In: OCEANS, pp. 1–6 (2006)Google Scholar
- 12.Ferreira, F., Veruggio, G., Caccia, M., Zereik, E., Bruzzone, G.: A real-time mosaicking algorithm using binary features for rovs. In: Proceedings of the Mediterranean Conference on Control and Automation, pp. 1267–1273 (2013)Google Scholar
- 13.Garcia-Fidalgo, E., Ortiz, A., Bonnin-Pascual, F., Company, J.: Fast image mosaicing using incremental bags of binary words. In: Proceedings of the IEEE International Conference Robotics and Automation, pp. 1174–1180 (2016)Google Scholar
- 16.Jaggi, M.: Revisiting Frank-Wolfe: projection-free sparse convex optimization. In: Proceedings of the International Conference on Machine Learning, pp. 427–435 (2013)Google Scholar