Skip to main navigation Skip to search Skip to main content

An Effective End-to-End Image Matching Network with Attentional Graph Neural Networks

  • Beihang University
  • Shandong University of Science and Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Established feature-based image matching algorithms usually use two networks to obtain the features and matching correspondences of images separately. But then the former network cannot know the results of the operations of the latter network, and backpropagation cannot be performed to optimize the parameters. For the image feature point matching problem, an end-to-end deep learning algorithm is designed. The neural network takes a pair of images as input and obtains feature keypoints, descriptors, and matching correspondences directly after a series of network layers. The advantages of the end-to-end algorithm are verified by comparing the end-to-end training strategies with independence training strategies.

Original languageEnglish
Title of host publicationICIEA 2022 - Proceedings of the 17th IEEE Conference on Industrial Electronics and Applications
EditorsWenxiang Xie, Shibin Gao, Xiaoqiong He, Xing Zhu, Jingjing Huang, Weirong Chen, Lei Ma, Haiyan Shu, Wenping Cao, Lijun Jiang, Zeliang Shu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1628-1633
Number of pages6
ISBN (Electronic)9781665409841
DOIs
StatePublished - 2022
Event17th IEEE Conference on Industrial Electronics and Applications, ICIEA 2022 - Chengdu, China
Duration: 16 Dec 202219 Dec 2022

Publication series

NameICIEA 2022 - Proceedings of the 17th IEEE Conference on Industrial Electronics and Applications

Conference

Conference17th IEEE Conference on Industrial Electronics and Applications, ICIEA 2022
Country/TerritoryChina
CityChengdu
Period16/12/2219/12/22

Keywords

  • computer vision
  • deep learning
  • feature matching
  • image matching

Fingerprint

Dive into the research topics of 'An Effective End-to-End Image Matching Network with Attentional Graph Neural Networks'. Together they form a unique fingerprint.

Cite this