Automatic Registration of Multi-source Remote Sensing Images Based on Region Growing
-
摘要: 多源遥感图像由于成像设备、所用光谱、拍摄时间等因素的不同,给配准带来极大的困难.尽管已经提出了多种匹配方法,但已有方法一般只能适用于特定的应用环境,开发出更加稳定和适用的配准算法仍然是一个极具挑战性的研究课题.提出一种基于区域生长的配准方法,首先,提取改进后的尺度不变特征,通过全局匹配确定种子点和种子区域并完成变换模型的初始化;然后,运用迭代区域生长和双向匹配策略,得到整个图像的可靠匹配点,从而实现多源遥感图像之间的配准.实验表明,该方法提取的匹配点的数量和正确率均远高于已有方法,能够对存在严重灰度差异的多源遥感图像实现高精度的配准,充分证明了该方法的鲁棒性和适用性.Abstract: Multi-source remote sensing images are usually captured by different sensors, in different spectra and/or at different times, which makes them difficult to match. Although a variety of methods have been proposed to solve this problem, most of them are only suitable for particular applications. It is still an open and challenging task to develop more stable and applicable algorithms. This paper presents a novel registration method based on region growing. It firstly utilizes the global matching to find seed points based on the updated scale-invariant features (SIFT), and then uses the seed points to start the region growing process. In the region growing phase, it estimates the transformation between the sensed image and the reference image employing the matching points in the current region, then expands the searching scope to find other matching points at farther places. This process iteratively executes until the searching region covers the whole image. Combined with bilateral matching, the proposed method can find a large number of evenly distributed matching points from only a few initial correct ones. Experiments show that this algorithm can find a greater number of matching points with higher precision than the existing methods for multi-source remote sensing images with significant gray-scale differences. Therefore, the proposed algorithm is more robust and powerful than several state-of-the-art methods.
-
Key words:
- Image registration /
- scale-invariant features (SIFT) /
- initialization /
- region growing /
- local searching
-
[1] Zitova B, Flusser J. Image registration methods: a survey. Image and Vision Computing, 2003, 21(11): 977-1000 [2] Wang Y F, Yu Q Z, Yu W X. An improved normalized cross correlation algorithm for SAR image registration. In: Proceedings of International Conference on Geoscience and Remote Sensing Symposium. Munich, Germany: IEEE, 2012. 2086-2089 [3] Kern J P, Pattichis M S. Robust multispectral image registration using mutual-information models. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(5): 1494-1505 [4] Tang Min. A novel image registration method combining morphological gradient mutual information with multiresolution optimizer. Acta Automatica Sinica, 2008, 34(3): 246-250(汤敏. 合形态学梯度互信息和多分辨率寻优的图像配准新方法. 自动化学报, 2008, 34(3): 246-250) [5] Wang A, Clausi D A. ARRSI: automatic registration of remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(5): 1483-1493 [6] Sun Da, Tang Xiang-Long, Liu Jia-Feng, Huang Jian-Hua. Density based interest point detector. Acta Automatica Sinica, 2008, 34(8): 854-860(孙达, 唐降龙, 刘家锋, 黄剑华. 基于概率密度的兴趣点检测算法. 自动化学报, 2008, 34(8): 854-860) [7] Leng Xue-Fei, Liu Jian-Ye, Xiong Zhi. A real-time image matching algorithm for navigation system based on bifurcation extraction. Acta Automatica Sinica, 2007, 33(7): 678-682(冷雪飞, 刘建业, 熊智. 基于分支特征点的导航用实时图像匹配算法. 自动化学报, 2007, 33(7): 678-682) [8] Yang Y, Gao X. Remote sensing image registration via active contour model. International Journal of Electronics Communications, 2009, 63(4): 227-234 [9] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [10] Firmenichy D, Brown M, Susstrunk S. Multispectral interest points for RGB-NIR image registration. In: Proceedings of the 18th International Conference on Image Processing. Brussels: IEEE, 2011. 181-184 [11] Fan D K, Ye Y X, Pan L, Yan S J. A remote sensing adapted image registration method based on SIFT and phase congruency. In: Proceedings of International Conference on Image Analysis and Signal Processing. Hubei, China: IEEE, 2011. 326-331 [12] Cai Guo-Rong, Li Shao-Zi, Wu Yun-Dong, Su Song-Zhi, Chen Shui-Li. A perspective invariant image matching algorithm. Acta Automatica Sinica, 2013, 39(7): 1053-1061(蔡国榕, 李绍滋, 吴云东, 苏松志, 陈水利. 一种透视不变的图像匹配算法. 自动化学报, 2013, 39(7): 1053-1061) [13] Liu Z X, An J B, Yu J. A simple and robust feature point matching algorithm based on restricted spatial order constraints for aerial image registration. IEEE Transaction on Geoscience and Remote Sensing, 2012, 50(2): 514-727 [14] Goncalves H, Luís C R, Goncalves J A. Automatic image registration through image segmentation and SIFT. IEEE Transaction on Geoscience and Remote Sensing, 2011, 49(7): 2589-2600 [15] Mikolajczyk K, Schmid C. Scale and affine invariant interest point detectors. International Journal of Computer Vision, 2004, 60(1): 63-86 [16] Li Q L, Wang G Y, Liu J G, Chen S B. Robust scale-invariant feature matching for remote sensing image registration. IEEE Geoscience and Remote Sensing Letters, 2009, 6(2): 287-291 [17] Fan B, Huo C L, Pan C H, Kong Q Q. Registration of optical and SAR satellite images by exploring the spatial relationship of the improved SIFT. IEEE Geoscience and Remote Sensing Letters, 2013, 10(4): 657-661 [18] Fishier M A, Boles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 1981, 24(6): 381-395 [19] Hasan M, Pickering M R, Jia X P. Modified SIFT for multi-modal remote sensing image registration. In: Proceedings of International Conference on Geoscience and Remote Sensing Symposium. Munich, Germany: IEEE, 2012. 2348-2351 [20] Hasan M, Jia X P, Kelly A R, Zhou J, Pickering M R. Multi-spectral remote sensing image registration via spatial relationship analysis on SIFT keypoints. In: Proceedings of International Conference on Geoscience and Remote Sensing Symposium, Honolulu, HI: IEEE, 2010. 1011-1014 [21] Yang G H, Stewart C V, Sofka M, Tsai C L. Registration of challenging image pairs: initialization, estimation, and decision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(11): 1973-1989 [22] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630 [23] Kelman A, Sofka M, Stewart C V. Keypoint descriptors for matching across multiple image modalities and non-linear intensity variations. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, Minneapolis, USA: IEEE, 2007. 1-7 [24] Wang S, You H, Fu K. BFSIFT: a novel method to find feature matches for SAR image registration. IEEE Geoscience and Remote Sensing Letters, 2012, 9(4): 649-653 [25] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision. Cambridge: Cambridge University Press, 2000. 132-150
点击查看大图
计量
- 文章访问数: 2146
- HTML全文浏览量: 78
- PDF下载量: 1086
- 被引次数: 0