Image Stitching Method Based on Global and Local Features

被引：0
|
作者：
Xu X. [1 ]
Yuan S. [1 ]
Wang J. [2 ]
Dai Y. [1 ]
机构：
[1] School of Automation, Beijing Institute of Technology, Beijing
[2] Beijing JERO Instrument Limited Company, Beijing
来源：
Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology | 2022年 / 42卷 / 05期
关键词：
Deep learning; Global and local features; Homography transformation; Image stitching;
D O I：
10.15918/j.tbit1001-0645.2021.093
中图分类号：
学科分类号：
摘要：
To solve the error accumulation problem in the traditional sequential image stitching algorithm, a new image stitching method was proposed based on global and local features. Both one global image with large field of view and low resolution and some local images with small field of view and high resolution were taken simultaneously. Then, substituting deep learning for the traditional algorithm, the matching points of the two were extracted. And according to their area ratio, the matching point coordinates of the global image were scaled up at the same proportion for the purpose of projecting local images to the plane of the global image without scaling. Finally, the overlapping areas of local images after projection were fused and stitched to form a panoramic image with large field of view and high resolution. Experimental results show that deep learning can achieve feature matching quickly and accurately. Moreover, the local images are independent of each other, effectively solving the restriction of stitching sequence and the accumulation of stitching errors. Copyright ©2022 Transaction of Beijing Institute of Technology. All rights reserved.
引用
收藏
页码：502 / 510
页数：8
相关论文
共 17 条
  • [1] GADDAM V R, RIEGLER M, EG R, Et al., Tiling in interactive panoramic video: approaches and evaluation, IEEE Transactions on Multimedia, 18, 9, pp. 1819-1831, (2016)
  • [2] LIU N, WU H, LIN L., Hierarchical ensemble of background models for PTZ-based video surveillance, IEEE Trans Cybern, 45, 1, pp. 89-102, (2015)
  • [3] ANDERSON R, GALLUP D, BARRON J T, Et al., JUMP: virtual reality video, ACM Transactions on Graphics (TOG), 35, 6, pp. 198-211, (2016)
  • [4] MATZEN K, COHEN M F, EVANS B, Et al., Low-cost 360 stereo photography and video capture, Acm Transactions on Graphics, 36, 4, pp. 148-160, (2017)
  • [5] LI Jing, Research on local adaptive panoramic image stitching, (2017)
  • [6] BROWN M, LOWE D G., Automatic panoramic image stitching using invariant features, International Journal of Computer Vision, 74, 1, pp. 59-73, (2007)
  • [7] LOWE D G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [8] FISCHLER M A, BOLLES R C., Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 24, 6, pp. 381-395, (1981)
  • [9] ZHANG Xuejing, CHEN He, MA Long, Et al., Fast image registration algorithm based on sub-image features, Transactions of Beijing Institute of Technology, 35, 7, pp. 744-749, (2015)
  • [10] HU Shanqing, LI Huixing, LI Bingyi, Et al., The real-time imaging method for sliding spotlight SAR based on embedded GPU, Transactions of Beijing Institute of Technology, 40, 9, pp. 1018-1025, (2020)
12