Invention Grant
- Patent Title: Deep learning-based image stitching method and apparatus
-
Application No.: US17532880Application Date: 2021-11-22
-
Publication No.: US11900561B2Publication Date: 2024-02-13
- Inventor: Gi Mun Um , Hee Kyung Lee , Dae-Young Song , Donghyeon Cho
- Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY (IAC)
- Applicant Address: KR Daejeon
- Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE,THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY
- Current Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE,THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY
- Current Assignee Address: KR Daejeon; KR Daejeon
- Priority: KR 20200160113 2020.11.25 KR 20210105961 2021.08.11
- Main IPC: G06T3/40
- IPC: G06T3/40 ; G06T3/00 ; G06F18/22 ; G06F18/213

Abstract:
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.
Public/Granted literature
- US20220164922A1 DEEP LEARNING-BASED IMAGE STITCHING METHOD AND APPARATUS Public/Granted day:2022-05-26
Information query