Air-ground image fusion technology with point cloud registration

doi:10.13474/j.cnki.11-2246.2022.0176.

Abstract

Abstract: In order to achieve the high-precision fusion of air-ground images, a fusion method based on dense matching is proposed in this paper, and the result is compared with the fusion scheme using point cloud from aerial triangulation. Firstly, the three-dimensional point cloud is obtained by aerial triangulation and dense matching to the air-ground images. Then, the coarse registration of air point cloud and ground point cloud is performed by the SAC-IA algorithm based on 3DSC features. Finally, the refined registration is performed by the improved Point-to-Plane ICP algorithm, leading to the fusion of air-ground images.Compared with the sparse point cloud from aerial triangulation, the experimental results show that the dense matching point cloud can provide more robust registration result, and its accuracy is at centimeter-level.

Key words: air-ground image fusion, dense matching, aerial triangulation, point cloud registration

CLC Number:

P208

XIE Hong, CHEN Libo, NIE Qian, WU Wei, ZHANG Pei. Air-ground image fusion technology with point cloud registration[J]. Bulletin of Surveying and Mapping, 2022, 0(6): 82-87.

References

[1] WU B,XIE L,HU H,et al.Integration of aerial oblique imagery and terrestrial imagery for optimized 3D modeling in urban areas[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018(139):119-132.
[2] NEX F,GERKE M,REMONDINO F,et al.ISPRS benchmark for multi-platform photogrammetry[C]//Proceedings of 2015 ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. Munich:ISPRS,2015:135-142.
[3] GAO X,SHEN S,ZHOU Y,et al.Ancient Chinese architecture 3D preservation by merging ground and aerial point clouds[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018(143):72-84.
[4] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[5] BAY H,ESS A,TUYTELAARS T,et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding,2008,110(3):346-359.
[6] SHAH R,DESHPANDE A,NARAYANAN P J. Multistage SFM:revisiting incremental structure from motion[C]//Proceedings of 2014 International Conference on 3D Vision. Tokyo:IEEE,2014:417-424.
[7] NODA M,TOMOKAZU T. Vehicle ego-localization by matching in-vehicle camera images to an aerial image[C]//Proceedings of 2010 Asian Conference on Computer Vision 2010 Workshops. Queenstown:Springer,2010:163-173.
[8] JENDE P,NEX F,GERKE M,et al. A fully automatic approach to register mobile mapping and airborne imagery to support the correction of platform trajectories in GNSS-denied urban areas[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2018,141:86-99.
[9] WOLFF M,COLLINS R T,LIU Y X. Regularity-driven building facade matching between aerial and street views[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Seattle:IEEE,2016:1591-1600.
[10] TIAN Y C,CHEN C,SHAH M. Cross-view image matching for geo-localization in urban environments[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:1998-2006.
[11] LIN T Y,CUI Y,BELONGIE S,et al. Learning deep representations for ground-to-aerial geolocalization[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE,2015:5007-5015.
[12] 杨璐宏,吴玮,王芮.基于空地影像联合的精细化三维重建研究[J].测绘通报,2021(S1):144-148.
[13] 赵文更,张旭,邵晴晴.融合反射强度图像的地铁隧道点云自动配准[J].测绘通报,2020(9):38-41.
[14] 马伟丽,王健,孙文潇.曲率约束的激光点云全局优化配准算法[J].遥感信息,2019,34(4):62-67.
[15] BESL P J,MCKAY N D. Method for registration of 3D shapes[C]//Proceedings of 1992 Sensor Fusion IV:Control Paradigms and Data Structures.[S.l.]:International Society for Optics and Photonics,1992.
[16] CHETVERIKOV D,SVIRKO D,STEPANOV D,et al. The trimmed iterative closest point algorithm[C]//Proceedings of 2002 IEEE International Conference on Pattern Recognition. Quebec:IEEE,2002.
[17] YU Z. Intrinsic shape signatures:a shape descriptor for 3D object recognition[C]//Proceedings of 2009 IEEE International Conference on Computer Vision Workshops. Kyoto:IEEE,2009:689-696.
[18] FROME A,HUBER D,KOLLURI R,et al. Recognizing objects in range data using regional point descriptors[C]//Proceedings of the 8th European Conference on Computer Vision. Prague:Springer,2004:224-237.
[19] RUSU R B,BLODOW N,BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//Proceedings of 2009 IEEE International Conference on Robotics&Automation. Kobe:IEEE,2009.
[20] 李仁忠,杨曼,田瑜,等.基于ISS特征点结合改进ICP的点云配准算法[J].激光与光电子学进展,2017,54(11):312-319.