A Method of Mismatching Points Elimination of Non-collinear Multiple CCDs Remote Sensing Images Based on Clustering Algorithm
HUANG Li YOU Hongjian
(Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing 100190, China)
(Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China)
(University of Chinese Academy of Sciences, Beijing 100049, China)
Abstract:Considering the distribution characteristic of the matching points of non-collinear multiple Charge- Coupled Device (CCD) remote sensing images, a new method based on clustering to eliminate the mismatching points is proposed. First, the multi-dimensionality feature vector of matching points is obtained on the basis of the disparity curve in along-track direction. Second, all points are clustered to one cluster. Finally, the points are marked off according to the variation trend of the semi-diameter of the cluster. The experiment results running on the panchromatic image of mapping satellite 1-02 show that the method has better performance on eliminating the mismatched points and keeping the matched points.
TANG Xinming, HU Fen, WANG Mi, et al. Inner FoV stitching of spaceborne TDI CCD images based on sensor geometry and projection plane in object space[J]. Remote Sensing, 2014, 6(7): 6386-6406. doi: 10.3390/rs6076386.
[2]
SUN Tao, LONG Hui, and LIU Baocheng. Application of attitude jitter detection based on short-time asynchronous images and compensation methods for Chinese mapping satellite-1[J]. Optics Express, 2015, 23(2): 1395-1410. doi: 10.1364/OE.23.001395.
PAN Jun, HU Fen, WANG Mi, et al. An inner FOV stistching method for non-collinear TDI CCD inages[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(11): 1165-1173. doi: 10.13485/jcnki.11-2089.2014.0180.
LI Shiwei, LIU Tuanjie, and WANG Hongqi. Image mosaic for TDICCD pushbroom camera image based on image matching[J]. Remote Sensing Technology and Application, 2009, 24(3): 374-378.
[5]
ZITOVA B and FLUSSER J. Image registration methods: A survey[J]. Image and Vision Computing, 2003, 21(11): 977-1000. doi: 10.1016/S0262-8856(03)00137-9.
[6]
FISCHLER M A and BOLLES R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communication ACM, 1981, 24(6): 381-395. doi: 10.1145/ 358669.358692.
[7]
LI Bin, MING Delie, YAN Wenwen, et al. Image matching based on two-column histogram hashing and improved RANSAC[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 11(8): 783-787. doi: 10.1109/LGRS.2013.2295115.
MA Xuyan, YUAN yuan, WANG Chengyi, et al. A control point uniformization algorithm for high-resolution remote sensing image registration[J]. Remote Sensing Information, 2016, 31(3): 24-30. doi: 10.3969/j.issn.1000-3177.2016.03.004.
WU Junhan, YU Bailang, PENG Chen, et al. A metnod for fast modeling of 3D building from mobile laser scanning point clouds and remote sensing data[J]. Geomatics & Spatial Information Technology, 2016, 39(1): 25-34.
[10]
ZAHRA H and MEHDI N. Image registration based on SIFT features and adaptive RANSAC transform[C]. International Conference on Communication and Signal Processing, India, 2016: 1087-1091.
LONG Xiaoxiang, WANG Xiaoyan, and ZHONG Huimin. Analysis of image quality and processing method of space- borne focal plane view splicing TDI CCD camera[J]. Science of China: Information of Science, 2011, 41(Suppl.): 19-31.
HU F. Research on inner FOV stitching theories and algorithms for sub-images of three non-collinear TDI CCD chips[D]. [Ph.D. dissertation], Wuhan University, 2010: 63.
LU Jinbo and HE Bin. Automatic mosaic method of large field view and multi-channel remote sensing images of TDICCD cameras[J]. Chinese Journal of Space Science, 2012, 32(l): 154-160.
[14]
JAIN A K. Data clustering: 50 years beyond k-means[C]. 19th International Conference on Pattern Recognition, Tampa, USA, 2010: 651-666. doi: 10.1016/j.patrec.2009.09. 011.
ZHANG Shunlong, KU Tao, and ZHOU Hao. Accelerate K-means for multi-center clustering of big datasets[J]. Application Research of Computers, 2016, 33(2): 413-416. doi: 10.3969/j.issn.1001-3695.2016.02.021.
[16]
SINHA A and JANA P K. A novel K-Means based clustering algorithm for big data[C]. International Conference on Advances in Computing, Communications and Informatics (ICACCI), Jaipur, India, 2016: 1875-1879. doi: 10.1109/ ICACCI.2016.7732323.