Image Stitching With Manifold Optimization

被引:8
作者
Zhang, Lei [1 ]
Huang, Hua [2 ]
机构
[1] Beijing Inst Technol, Sch Comp, Beijing Key Lab Intelligent Informat Technol, Beijing 100081, Peoples R China
[2] Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China
基金
中国国家自然科学基金;
关键词
Alignment; distortion; general linear group; image stitching; manifold; ALIGNMENT; FEATURES; WARPS;
D O I
10.1109/TMM.2022.3161839
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Image stitching usually relies on spatial transformations to perform the overlap alignment and distortion mitigation. This paper presents a manifold optimization method to seek these transformations. The purpose is not to present a new formulation of image stitching, as the proposed method uses common transformations such as homography to align feature correspondences in the overlap and similarity transformations to preserve the shape. Instead, the proposed method is based on a new treatment of these transformations as elements of a prescribed matrix manifold. Its advantage lies in its more effective and efficient optimization in the manifold domain. Specifically, spatially varying homographies are computed by an efficient second-order minimization (ESM) of the geometric error of aligning feature correspondences, but with their intrinsic manifold parameterization. To mitigate the distortion, the interpolation between homography and similarity transformation is performed on a general matrix manifold. These on-manifold operations improve the stitching quality with fewer ghosting and distortion artifacts. The experiments show our manifold optimization for image stitching outperforms other methods.
引用
收藏
页码:3469 / 3482
页数:14
相关论文
共 45 条
[1]   Manifold Alignment via Global and Local Structures Preserving PCA Framework [J].
Abeo, Timothy Apasiba ;
Shen, Xiang-Jun ;
Ganaa, Ernest Domanaanmwi ;
Zhu, Qian ;
Bao, Bing-Kun ;
Zha, Zheng-Jun .
IEEE ACCESS, 2019, 7 :38123-38134
[2]   Homography-based 2D visual tracking and servoing [J].
Benhimane, S. ;
Malis, E. .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2007, 26 (07) :661-676
[3]   A Combinatorial Solution to Non-Rigid 3D Shape-to-Image Matching [J].
Bernard, Florian ;
Schmidt, Frank R. ;
Thunberg, Johan ;
Cremers, Daniel .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1436-1445
[4]   MegaParallax: Casual 360° Panoramas with Motion Parallax [J].
Bertel, Tobias ;
Campbell, Neill D. F. ;
Richardt, Christian .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2019, 25 (05) :1828-1835
[5]   Automatic panoramic image stitching using invariant features [J].
Brown, Matthew ;
Lowe, David G. .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2007, 74 (01) :59-73
[6]   Shape-Preserving Half-Projective Warps for Image Stitching [J].
Chang, Che-Han ;
Sato, Yoichi ;
Chuang, Yung-Yu .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :3254-3261
[7]   Natural Image Stitching with the Global Similarity Prior [J].
Chen, Yu-Sheng ;
Chuang, Yung-Yu .
COMPUTER VISION - ECCV 2016, PT V, 2016, 9909 :186-201
[8]   The geometric error for homographies [J].
Chum, O ;
Pajdla, T ;
Sturm, P .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2005, 97 (01) :86-102
[9]  
Gao J., 2013, EUROGRAPHICS, P45, DOI DOI 10.2312/CONF/EG2013/SHORT/045-048
[10]  
Gao JH, 2011, PROC CVPR IEEE, P49, DOI 10.1109/CVPR.2011.5995433