An Automatic Matching Method Based on Local Phase Feature Descriptor for Multi-source Remote Sensing Images
-
摘要: 由于影像间显著的几何和辐射差异，多源遥感影像自动匹配一直是目前研究的难点问题。首先引入具有光照和对比度不变性的相位一致性模型，并对其进行扩展，构建相位一致性的特征方向信息，然后借助于梯度方向直方图的模板结构，利用其特征值和特征方向，建立一种局部特征描述符——局部相位一致性方向直方图（local histogram of orientated phase congruency，LHOPC），最后利用欧氏距离作为匹配测度进行同点名识别。对四组多源遥感影像进行试验，其结果表明，相比于尺度不变特征转换和加速鲁棒性特征算法，LHOPC能更为有效的抵抗影像间的辐射差异，提高了匹配性能。Abstract: This paper introduces the phase congruency model with illumination and contrast invariance for image matching, and extends the model to feature orientation in phase congruency. Based on the orientated gradient histogram concept, a local feature descriptor named "local histogram of orientated phase congruency (LHOPC)" is developed using the intensity and orientation of phase congruency. The Euclidean distance between LHOPC descriptors is used as similarity metric to achieve correspondences. The proposed method is evaluated with four pairs of multi-source remote sensing images. The experimental results show that LHOPC is more robust to the radiation differences between images, and performs better than the SIFT and SURF algorithms.
-
Keywords:
- remote sensing image /
- image matching /
- phase congruency /
- LHOPC
-
-
表 1 试验数据的详细信息
Table 1 Detailed Description of Test Data
试验编号 参考影像 待匹配影像 影像特点 卫星传感器分辨率/m 大小(像素)时间(年-月) 卫星传感器分辨率/m 大小(像素)时间(年-月) 试验1 SPOT4波段2(可见光)
20600×600
2002-10TM波段5(红外)
30523×523
2001-09光谱差异较大，并存在一定角度的旋转 试验2 谷歌地球(Google Earth)
约1650×650
2008-09谷歌地球(Google Earth)
约1650×650
2011-06时相差异近3年 试验3 Worldview2全色(可见光)
0.5924×931
2011-10Worldview2波段3(可见光)
2873×829
2011-10分辨率差异4倍 试验4 SPOT5波段2(可见光)
101 570×1 828
2002-10TM波段5(红外)
30596×629
2001-06时相差异15个月，分辨率差异3倍 
下载: 导出CSV
-
[1] 叶沅鑫, 单杰, 彭剑威等.利用局部自相似进行多光谱遥感影像自动配准.测绘学报, 2014, 43(3):268-275 http://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201403009.htm Ye Yuanxin, Shan Jie, Peng Jianwei, et al. Automated Multispectral Remote Sensing Image Registration Using Local Self-similarity[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(3):268-275 http://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201403009.htm
[2] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110 doi: 10.1023/B:VISI.0000029664.99615.94
[3] 叶沅鑫, 单杰, 熊金鑫, 等.一种结合SIFT和边缘信息的多源遥感影像匹配方法[J].武汉大学学报·信息科学版. 2013, 38(10):1148-1151 http://ch.whu.edu.cn/CN/abstract/abstract2771.shtml Ye Yuanxin, Shan Jie, Xiong Jinxin, et al. A Matching Method Combining SIFT and Edge Information for Multi-source Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2013, 38(10):1148-1151 http://ch.whu.edu.cn/CN/abstract/abstract2771.shtml
[4] Ye Yuanxin, Shan Jie. A Local Descriptor Based Registration Method for Multispectral Remote Sensing Images with Non-linear Intensity Differences[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 90:83-95 doi: 10.1016/j.isprsjprs.2014.01.009
[5] 凌志刚, 梁彦, 程咏梅, 等.一种稳健的多源遥感图像特征配准方法[J].电子学报, 2010, 38(12):2092-2897 http://www.cnki.com.cn/Article/CJFDTOTAL-DZXU201012031.htm Ling Zhigang, Liang Yan, Cheng Yongmei, et al. A Robust Multi-Source Remote Sensing Image Regisration Method Based on Feature Matching[J]. Acta Electronica Sinica, 2010, 38(12):2892-2897 http://www.cnki.com.cn/Article/CJFDTOTAL-DZXU201012031.htm
[6] Bay H, Ess A, Tuytelaars T, et al. Speeded-up Robust Features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3):346-359 doi: 10.1016/j.cviu.2007.09.014
[7] Rublee E, Rabaud V, Konolige K, et al. ORB:An Efficient Alternative to SIFT or SURF[C]. Proceedings of IEEE International Conference on Computer Vision, Colorado, USA, 2011
[8] Kovesi P. Image Features from Phase Congruency[J]. Journal of Computer Vision Research, 1999, 1(3):1-26
[9] Wong A, Clausi D A. ARRSI:Automatic Registration of Remote-sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(5):1483-1493 doi: 10.1109/TGRS.2007.892601
[10] 凌志刚, 梁彦, 潘泉, 等.一种鲁棒的红外与可见光多级景象匹配算法[J].航空学报, 2010, 31(6):1185-1195 http://www.cnki.com.cn/Article/CJFDTOTAL-HKXB201006013.htm Ling Zhigang, Liang Yan, Pan Quan, et al. A Robust Multi-level Scene Matching Algorithm for Infrared and Visible Light Image[J]. Acta Aeronautica et Astronautica Sinica, 2010, 31(6):1185-1195 http://www.cnki.com.cn/Article/CJFDTOTAL-HKXB201006013.htm
[11] 李明, 李德仁, 范登科, 等, 利用PC-SIFT的多源光学卫星影像自动配准方法[J].武汉大学学报·信息科学版. 2015, 40(1):1148-1151 http://ch.whu.edu.cn/CN/abstract/abstract3159.shtml Li Ming, Li Deren, Fan Dengke, et al. An Automatic PC-SIFT-Based Registration of Multi-source Images from Optical Satellites[J]. Geomatics and Information Science of Wuhan University. 2015, 40(1):1148-1151 http://ch.whu.edu.cn/CN/abstract/abstract3159.shtml
[12] Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005
[13] Morrone M C, Owens R A. Feature Detection from Local Energy[J]. Pattern Recognition Letters, 1987, 6:303-313 doi: 10.1016/0167-8655(87)90013-4
[14] Ye Yuanxin, Shen Li. HOPC:A Novel Similarity Metric Based on Geometric Structural Properties for Multi-modal Remote Sensing Image Matching[C]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, Prague, Czech, 2016
[15] Ye Yuanxin, Shan Jie, Bruzzone L, et al. Robust Registration of Multimodal Remote Sensing Images Based on Structural Similarity[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5):2941-2958 doi: 10.1109/TGRS.2017.2656380
计量
- 文章访问数:
- HTML全文浏览量:
- PDF下载量:
