- 专利标题: DEEP LEARNING-BASED IMAGE STITCHING METHOD AND APPARATUS
-
申请号: US17532880申请日: 2021-11-22
-
公开(公告)号: US20220164922A1公开(公告)日: 2022-05-26
- 发明人: Gi Mun UM , Hee Kyung LEE , Dae-Young SONG , Donghyeon CHO
- 申请人: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY (IAC)
- 申请人地址: KR Daejeon; KR Daejeon
- 专利权人: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE,THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY (IAC)
- 当前专利权人: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE,THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY (IAC)
- 当前专利权人地址: KR Daejeon; KR Daejeon
- 优先权: KR10-2020-0160113 20201125,KR10-2021-0105961 20210811
- 主分类号: G06T3/40
- IPC分类号: G06T3/40 ; G06T3/00 ; G06K9/62
摘要:
A deep learning-based image stitching method and apparatus are provided. The deep learning-based image stitching method includes receiving a plurality of images including a first image and a second image stitched to the first image, extracting a feature map of the plurality of images, generating a plurality of flow maps indicating movement information of pixels of the plurality of images, based on the feature map, generating a plurality of warping images in which the pixels of the plurality of images are moved, by applying the plurality of flow maps to the plurality of images, respectively, generating a plurality of weight maps for blending the plurality of warping images, based on the feature map, and generating a stitch image in which the first image and the second image are stitched, by blending the plurality of warping images based on the plurality of weight maps.
公开/授权文献
- US11900561B2 Deep learning-based image stitching method and apparatus 公开/授权日:2024-02-13
信息查询