ICP image matching technology considering distorted image edge

doi:10.13474/j.cnki.11-2246.2019.0383

Abstract

Abstract: Matching technology is an important basic technology in remote sensing image processing. The difference between radiation and geometric information of images seriously interferes with similar feature matching between images. This paper proposes an algorithm of ICPDI for large difference images. Firstly, it improves the parameter setting method of the Canny operator for selecting the long edge of the image as a prominent feature of image matching. Then, it takes the distance between line features as the similarity evaluation standard for achieving the purpose of suppressing local differences by using global similar features. Finally, it adds a deformation function to the edge of the image for extending the scope of ICPDI matching technology. The accuracy and adaptability of the proposed method are verified by matching experiments between different types of remote sensing images.

Key words: image edge, effective matching features, vector deformation function, distance between vectors, iterative closest point

CLC Number:

GAO Li, JIN Fei, JIANG Zhenzhi, WANG Fan, RUI Jie. ICP image matching technology considering distorted image edge[J]. Bulletin of Surveying and Mapping, 2019, 0(12): 40-44.

References

[1] 贾迪, 朱宁丹, 杨宁华,等. 图像匹配方法研究综述[J]. 中国图象图形学报, 2019, 24(5):17-39.
[2] 胡晓彤, 任辉, 刘楠. 尺度与特征强度自适应的SURF特征点匹配算法[J]. 天津科技大学学报, 2019, 34(2):72-76.
[3] JIA X, HUANG X, ZHANG F, et al. Robust line matching for image sequences based on point correspondences and line mapping[J]. IEEE Access, 2019,7:39879-39896.
[4] 王强. 面向结构化场景的直线特征提取匹配与光束法平差研究[D]. 北京:中国矿业大学(北京),2018.
[5] 贾迪, 李玉秀, 赵明远,等. 面向像对直线特征匹配的线特征矫正与提纯方法[J]. 中国图象图形学报, 2019,24(7):1176-1187.
[6] 王竞雪, 张雪. 结合几何约束和梯度描述子的直线段匹配[J]. 测绘通报, 2018(5):29-34.
[7] WEIDONG S, HONG Z, JINGXUE W, et al. Line feature matching method based on multiple constraints for close-range images[J]. Journal of Image and Graphics, 2016(6):86-92.
[8] 智珊珊, 薛瑞. 曲线特征匹配技术研究现状及展望[J]. 无线互联科技, 2017(21):130-131.
[9] 陈璐璐. 基于描述子的曲线匹配技术研究[D]. 焦作:河南理工大学,2017.
[10] 靳秋霞,张彩霞. 基于Freeman链码的二维曲线匹配[J]. 计算机应用,2015(S1):247-251.
[11] 房然然,黄发忠,辛化梅. 二维碎片拼接的局部匹配[J]. 现代电子技术,2015(9):54-56.
[12] XIAOJIE G, JI J, XIAOAI D, et al. Spectral curve matching application analysis based on fréchet distance[J]. Geomatics and Information Science of Wuhan University, 2016,41(3):408-414.
[13] SCHEFFER C. More flexible curve matching via the partial fréchet similarity[J]. International Journal of Computational Geometry & Applications, 2016, 26(1):33-52.
[14] NING G, MENGYU M, WEI X, et al. An efficient query algorithm for trajectory similarity based on fréchet distance threshold[J]. ISPRS International Journal of Geo-Information, 2017, 6(11):326-339
[15] CHAUDHURY A, BARRON J L. Occluded leaf matching with full leaf databases using explicit occlusion modelling[C]//2018 15th Conference on Computer and Robot Vision (CRV).[S.l.]:IEEE Computer Society, 2018.
[16] 刘美池. ICP系列算法的描述与对比[J]. 科技资讯, 2019, 17(8):30-31.
[17] YANG B, ZANG Y, DONG Z, et al. An automated method to register airborne and terrestrial laser scanning point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 109:62-76.
[18] CEJNOG L W X, YAMADA F A A, VIEIRA M B. Wide angle rigid registration using a comparative tensor shape factor[J]. International Journal of Image & Graphics, 2017, 17(1):239-270.
[19] 陈小卫, 张保明, 郭海涛,等. 利用自由形状线特征的遥感影像分级匹配方法[J]. 测绘学报, 2017,46(2):78-87.
[20] CHEN Y, MEDIONI G. Object modeling by registration of multiple range images[C]//IEEE International Conference on Robotics and Automation.[S.l.]:IEEE:2002;145-155.