An accurate UAV image matching based on essential matrix

doi:10.13474/j.cnki.11-2246.2020.0248

Abstract

Abstract: Unmanned aerial vehicle (UAV) images have been widely used for their low cost, easy access, and large amount of information. Image matching is an important research topic because the commonly used image matching methods often mismatch or eliminate a large number of matching pair. LMeds algorithm is more stricter than other robust method. The essential matrix obtained by "5-point algorithm" can be used to match point-pair coplanar scenarios. This paper uses the essential matrix, which is solved using the LMedS algorithm combined with the "5-point algorithm", as the model to culling the error. At the same time, the ORB method with the attributes of fast featuring characteristics is used to construct a precise and efficient matching method. The experimental result shows that the proposed algorithm retains a large number of uniformly distributed matching pairs. This method is fast and accurate with efficiency and can be applied in various scenarios.

Key words: UAV image, image matching, essential matrix, homography matrix, LMedS algorithm

CLC Number:

P237

GE Yipan, WANG Xiaohong. An accurate UAV image matching based on essential matrix[J]. Bulletin of Surveying and Mapping, 2020, 0(8): 55-58,75.

References

[1] 何孝莹, 岳建伟, 张栩然.基于SIFT算法的无人机影像快速匹配[J].计算机工程, 2011, 37(7):216-218,230.
[2] BAY H,TUYTELAARS T,VAN G L. SURF:speeded up robust features[C]//Proceedings of European Confer-ence on Computer Vision. Berlin:Springer, 2006:404-417.
[3] 梁焕青, 范永弘, 万惠琼, 等.一种运用AKAZ特征的无人机遥感影像拼接方法[J].测绘科学技术学报, 2016, 33(1):71-75.
[4] 覃兵, 田军, 查宇飞, 等.利用二值描述符的实时目标跟踪算法[J].西安电子科技大学学报, 2015, 42(5):168-174.
[5] RUBLEE E, RABAUD V, KONOLIGE K, et al.ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of International Conference on Computer Vision. Barcelona:IEEE, 2011:2564-2571.
[6] 何志伟, 王晓红, 邓仕雄, 等.一种喀斯特地貌无人机遥感影像的快速匹配方法[J].测绘科学, 2019, 44(7):105-110.
[7] 王晓红, 邓仕雄, 何志伟,等.结合SURF算法和单应性矩阵的无人机影像匹配[J].测绘通报, 2018(7):38-42.
[8] 李城,王仁礼,王成港,等. 改进MSAC估计F与H矩阵在匹配点中的提纯[J].测绘通报,2018(4):104-107,140.
[9] NISTER D. An efficient solution to the five-point relative pose problem[C]//Proceedings of 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, WI:IEEE, 2003:195.
[10] 高翔,张涛.视觉SLAM十四讲[M].北京:电子工业出版社,2017.
[11] HARTLEY R, ZISSERMAN A. Multiple view geometry in computer vision[M]. 2nd ed.[S.l.]:Cambridge Univercity Press, 2004.
[12] 王文斌, 刘桂华, 刘先勇, 等.本质矩阵五点算法伪解的两种剔除策略[J].光电工程, 2010, 37(8):46-52.
[13] 唐琪博, 侯守明.基于改进的ORB算法与姿态估计的跟踪注册方法研究[J].计算机应用研究, 2016, 33(12):3905-3908.
[14] MEER P, MINTZ D, ROSENFELD A, et al. Robust regression methods for computer vision:a review[J].International Journal of Computer Vision, 1991, 6(1):59-70.
[15] ZHANG M, WANG G G, CHAO H Y, et al. fast and robust algorithm for fundamental matrix estimation[C]//ICIAR 2015:Image Analysis and Recognition.[S.l.]:Springer, 2015:316-322.