Detecting Matching Blunders of Multi-Source Remote Sensing Images via Graph Theory

Detecting Matching Blunders of Multi-Source Remote Sensing Images via Graph Theory
复制标题

基于图论的多源遥感影像匹配错误检测

DOI:
10.3390/s20133712
复制
发表时间:
2020-07
期刊:
Sensors (Switzerland)
影响因子:
--
通讯作者:
Chen Jun
Chen Jun
中科院分区:
其他
文献类型:
--
作者:
Deng Cailong;Yuan Xiuxiao;Deng Lixia;Chen Jun

文献摘要

参考文献

相似文献

多源图像存在较大的辐射和几何畸变,导致匹配点少,匹配错误率高,多源图像间的全局几何关系模型不明确。因此,传统的匹配错误检测方法不能有效地工作。针对这一问题,本文提出了两种基于图论的匹配错误检测方法。该方法可以在匹配点少、匹配错误率高的情况下建立统计显著的聚类,在全局几何关系不明确的情况下,利用局部几何相似性约束检测匹配错误。第一种方法(完全图方法)利用完全图中匹配三角形所构成的簇对图像的局部几何相似性进行编码,在不考虑全局几何关系的情况下能够有效地检测匹配错误。第二种方法使用不规则三角网(TIN)图来近似一个完整的图,以减少第一种方法的计算复杂度。我们称之为基于TIN图的方法。在模拟和真实的数据(高分一号、高分一号、高分二号、全色陆地卫星、资源三号、吉林一号和无人机的近红外图像对)上的实验表明,这两种基于图的方法在识别率、误识率、剩余匹配点对数、离散度、定位精度等方面均优于经典的基于随机抽样一致性(RANSAC)的方法。值得注意的是,在大多数情况下,在模拟数据实验中,RANSAC,基于完全图的方法和基于TIN图的方法的平均错误率分别为0.50,0.26和0.14。此外,在真实的数据实验中,三种方法的平均位置精度(以像素为单位测量的RMSE)分别为2.6、1.4和1.5。此外,当匹配错误率不高于50%时,基于TIN图的方法的计算时间与基于RANSAC的方法相当,比完全基于图的方法约少2 ~ 40倍。
Large radiometric and geometric distortion in multi-source images leads to fewer matching points with high matching blunder ratios, and global geometric relationship models between multi-sensor images are inexplicit. Thus, traditional matching blunder detection methods cannot work effectively. To address this problem, we propose two matching blunder detection methods based on graph theory. The proposed methods can build statistically significant clusters in the case of few matching points with high matching blunder ratios, and use local geometric similarity constraints to detect matching blunders when the global geometric relationship is not explicit. The first method (named the complete graph-based method) uses clusters constructed by matched triangles in complete graphs to encode the local geometric similarity of images, and it can detect matching blunders effectively without considering the global geometric relationship. The second method uses the triangular irregular network (TIN) graph to approximate a complete graph to reduce to computational complexity of the first method. We name this the TIN graph-based method. Experiments show that the two graph-based methods outperform the classical random sample consensus (RANSAC)-based method in recognition rate, false rate, number of remaining matching point pairs, dispersion, positional accuracy in simulated and real data (image pairs from Gaofen1, near infrared ray of Gaofen1, Gaofen2, panchromatic Landsat, Ziyuan3, Jilin1and unmanned aerial vehicle). Notably, in most cases, the mean false rates of RANSAC, the complete graph-based method and the TIN graph-based method in simulated data experiments are 0.50, 0.26 and 0.14, respectively. In addition, the mean positional accuracy (RMSE measured in units of pixels) of the three methods is 2.6, 1.4 and 1.5 in real data experiments, respectively. Furthermore, when matching blunder ratio is no higher than 50%, the computation time of the TIN graph-based method is nearly equal to that of the RANSAC-based method, and roughly 2 to 40 times less than that of the complete graph-based method.
DOI: 10.1109/iccv.2005.198
发表时间: 2005-10
期刊: Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
影响因子: --
作者:
Jiri Matas;Ondřej Chum
通讯作者: Jiri Matas;Ondřej Chum
DOI: --
发表时间: 2014
期刊: --
影响因子: --
作者:
Zhang Yongju
通讯作者: Zhang Yongju
DOI: 10.1109/lgrs.2016.2620147
发表时间: 2016-11
影响因子: 4.8
作者:
Jiayuan Li;Qingwu Hu;M. Ai
通讯作者: Jiayuan Li;Qingwu Hu;M. Ai
DOI: 10.1007/978-3-642-15555-0_36
发表时间: 2010-09
期刊: --
影响因子: --
作者:
Minsu Cho;Jungmin Lee;Kyoung Mu Lee
通讯作者: Minsu Cho;Jungmin Lee;Kyoung Mu Lee
DOI: 10.1109/cvpr.2009.5206619
发表时间: 2009-06
期刊: 2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Olivier Duchenne;F. Bach;I. Kweon;J. Ponce
通讯作者: Olivier Duchenne;F. Bach;I. Kweon;J. Ponce