Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.1.21

Automated Image Matching for Satellite Images with Different GSDs through Improved Feature Matching and Robust Estimation  

Ban, Seunghwan (Program in Smart City Engineering, Inha University)
Kim, Taejung (Department of Geoinformatic Engineering, Inha University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_1, 2022 , pp. 1257-1271 More about this Journal
Abstract
Recently, many Earth observation optical satellites have been developed, as their demands were increasing. Therefore, a rapid preprocessing of satellites became one of the most important problem for an active utilization of satellite images. Satellite image matching is a technique in which two images are transformed and represented in one specific coordinate system. This technique is used for aligning different bands or correcting of relative positions error between two satellite images. In this paper, we propose an automatic image matching method among satellite images with different ground sampling distances (GSDs). Our method is based on improved feature matching and robust estimation of transformation between satellite images. The proposed method consists of five processes: calculation of overlapping area, improved feature detection, feature matching, robust estimation of transformation, and image resampling. For feature detection, we extract overlapping areas and resample them to equalize their GSDs. For feature matching, we used Oriented FAST and rotated BRIEF (ORB) to improve matching performance. We performed image registration experiments with images KOMPSAT-3A and RapidEye. The performance verification of the proposed method was checked in qualitative and quantitative methods. The reprojection errors of image matching were in the range of 1.277 to 1.608 pixels accuracy with respect to the GSD of RapidEye images. Finally, we confirmed the possibility of satellite image matching with heterogeneous GSDs through the proposed method.
Keywords
Satellite images; Image registration; Feature; ORB; Image transformation;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Yeom, J.H., Y.K. Han, and Y.I. Kim, 2013. Analysis of shadow effect on high resolution satellite image matching in urban area, Journal of Korean Society for Geospatial Information Science, 21(2): 93-98 (in Korean with English abstract). https://doi.org/10.7319/kogsis.2013.21.2.093   DOI
2 Han, D.Y., D.S. Kim, J.B. Lee, J.H. Oh, and Y.I. Kim, 2006. Automatic image-to-image registration of middle-and-low-resolution satellite images using Scale-Invariant-Feature-Transform technique, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 24(5): 409-416 (in Korean with English abstract).
3 Park, H.J., J.H. Son, H.S. Jung, K.E. Kweon, K.D. Lee, and T. Kim, 2020. Development of the precision image processing system for CAS-500, Korean Journal of Remote Sensing, 36(5-2): 881-891 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2020.36.5.2.3   DOI
4 Sohn. J.G., E.M. Kim, Y.S. Song, and J.H. Park, 2004. Accuracy analysis of interest point operator for image matching, Proc. of Korean Society of Civil Engineers, Pyeongchang, Korea, Oct. 21-22, vol. 10, pp. 4403-4406 (in Korean).
5 Zitova, B. and J. Flusser, 2003. Image registration methods: a survey, Image and Vision Computing, 21(11): 977-1000. https://doi.org/10.1016/S0262-8856(03)00137-9   DOI
6 Shin, J.I., W.S. Yoon, H.J. Park, K.Y. Oh, and T.J. Kim, 2018. A method to improve matching success rate between KOMPSAT-3A imagery and aerial ortho-images, Korean Journal of Remote Sensing, 34(6-1): 893-903 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2018.34.6.1.5   DOI
7 Lee, K.D. and J.S. Yoon, 2019. GCP chip automatic extraction of satellite imagery using interest point in North Koran, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 37(4): 211-218 (in Korean with English abstract). https://doi.org/10.7848/ksgpc.2019.37.4.211   DOI
8 Chang, X., S. Du, Y. Li, and S. Fang, 2018. A coarse-to-fine geometric scale-invariant feature transform for large size high resolution satellite image registration, Sensors, 18(5): 1360. https://doi.org/10.3390/s18051360   DOI
9 Dubrofsky, E., 2009. Homography estimation, The University of British Columbia, Kelowna, BC, Canada.
10 Han, Y., 2013. Automatic image-to-image registration between high-resolution multisensory satellite data in urban areas, Seoul National University, Seoul, Korea (in Korean).
11 Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60(2): 91-110. https://doi.org/10.1023/B:VISI.0000029664.99615.94   DOI
12 Rublee, E., V. Rabaud, K. Konolige, and G. Bradski, 2011. ORB: An efficient alternative to SIFT or SURF, Proc. of 2011 International Conference on Computer Vision, Barcelona, Spain, Nov. 6-11, vol. 20, pp. 2564-2571. https://doi.org/10.1109/ICCV.2011.6126544   DOI
13 Jeong, J., 2015. Comparison of single-sensor stereo model and dual-sensor stereo model with high-resolution satellite imagery, Korean Journal of Remote Sensing, 31(5): 421-432 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2015.31.5.6   DOI
14 Jeon, Y.M., H.G. Ji, M.S. Seo, M.S. Pyo, and Y.S. Bae, 2019. A study on the FAST, BRIEF, ORB features of image in the field of surface detect inspection, Proc. of the Korean Society of Computer Information Conference, Gumi, Korea, Jan. 17-19, vol. 27, pp. 399-402.
15 Vijayan, V. and K. Pushpalatha, 2019. FLANN based matching with SIFT descriptors for drowsy features extraction, Proc. of International Conference on Image Information Processing, Shimla, India, Nov. 15-17, pp. 600-605. https://doi.org/10.1109/ICIIP47207.2019.8985924   DOI