Laser & Optoelectronics Progress, Volume. 58, Issue 8, 0810004(2021)

Improved Algorithm for High-Resolution Image Stitching Based on ORB Features

Tianci Liu1,2、*, Yansong Song2、**, Jinwang Li2, and Xin Zhao1
Author Affiliations
  • 1College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, Jilin 130022, China
  • 2Institute of Space Photo-Electronic Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China
  • show less

    The traditional image stitching method has low processing speed, is inefficient, and unable to meet the requirements for fast and accurate stitching of high-resolution images. This paper proposes an improved algorithm of high-resolution image stitching based on Oriented FAST and Rotated BRIEF (ORB) features. First, based on the ORB feature point extraction, the Hamming distance is used for fast rough matching. Then, the matching point pair is optimized based on the progressive sampling consistency (PROSAC) algorithm. Next, after removing the mismatch point pair, the image transformation matrix is solved. Finally, the weighted fusion algorithm is used to fuse the overlapping areas of the image to remove the stitching traces. Experimental results show that the proposed algorithm not only has more advantages in processing speed but also has a higher matching accuracy compared to traditional algorithms. In addition, it can realize fast and accurate stitching of high-resolution images.

    Tools

    Get Citation

    Copy Citation Text

    Tianci Liu, Yansong Song, Jinwang Li, Xin Zhao. Improved Algorithm for High-Resolution Image Stitching Based on ORB Features[J]. Laser & Optoelectronics Progress, 2021, 58(8): 0810004

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Aug. 14, 2020

    Accepted: Sep. 9, 2020

    Published Online: Apr. 12, 2021

    The Author Email: Liu Tianci (2516089598@qq.com), Song Yansong (songyansong2006@126.com)

    DOI:10.3788/LOP202158.0810004

    Topics