Image Matching for Space Objects Based on Grid-Based Motion Statistics
Image matching for space objects has attracted wide attention for its importance in applications. Major challenges for this task include the textureless appearance and symmetrical structure of space objects. In this paper, we propose a novel image matching method, aiming to improve the image matching quality for space objects. Our approach consists of three main components, which are grid-based motion statistic (GMS), a contrario-random sample consensus (AC-RANSAC), and constraint of three-view. First of all, GMS is utilized to generate a collection of corresponding points. Subsequently, we adopt AC-RANSAC to eliminate false matches and estimate fundamental matrix. In the end, accurate matches are obtained under the constraint of three-view. Experimental results on simulated images of space objects have quantitatively and qualitatively demonstrated the effectiveness of our approach.
KeywordsImage matching Space objects Grid-based motion statistics AC-RANSAC
This work was supported in part by the National Natural Science Foundation of China (Grant Nos. 61501009, 61771031 and 61371134), the National Key Research and Development Program of China (2016YFB0501300, 2016YFB0501302) and the Aerospace Science and Technology Innovation Fund of CASC (China Aerospace Science and Technology Corporation).
- 5.Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to sift or surf. In: 2011 International Conference on Computer Vision, pp. 2564–2571, November 2011Google Scholar
- 7.Bian, J., Lin, W.Y., Matsushita, Y., Yeung, S.K., Nguyen, T.D., Cheng, M.M.: GMS: grid-based motion statistics for fast, ultra-robust feature correspondence. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2828–2837, July 2017Google Scholar
- 9.Cong Li, Hong Rui Zhao, and Gang Fu. 3-D reconstruction of image sequence based on independent three-view. In: Advanced Materials Research, vol. 989, pp. 3844–3850. Trans Tech Publications (2014)Google Scholar
- 10.Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. In: Readings in Computer Vision, pp. 726–740. Elsevier (1987)Google Scholar