Geo-localization based on CNN feature matching
Author:
Affiliation:

1. School of Computer Science and Engineering, Central South University, Changsha 410083, China;2. School of Automation, Central South University, Changsha 410083, China

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    A geo-localization method is proposed for military and civilian applications, which is used when no global navigation satellite system (GNSS) information is available. The open graphics library (OpenGL) is used to build a three-dimensional geographic model of the test area using digital elevation model (DEM) data, and the skyline can thus be extracted with the model to form a database. Then, MultiSkip DeepLab (MS-DeepLab), a fully convolutional semantic segmentation network with multiple skip structures, is proposed to extract the skyline from the query image. Finally, a matching model based on convolutional neural network (CNN) feature is adopted to calculate the similarity between the skyline features of the query image and the DEM database to realize automatic geo-localization. The experiments are conducted at a 202.6 km2 test site in north-eastern Changsha, China. 50 test points are selected to verify the effectiveness of the proposed method, and an excellent result with an average positioning error of 49.29 m is obtained.

    Reference
    Related
    Cited by
Get Citation

TANG Jin, GONG Cheng, GUO Fan, YANG Zirong, WUZhihu. Geo-localization based on CNN feature matching[J]. Optoelectronics Letters,2022,18(5):300-306

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:September 16,2021
  • Revised:October 28,2021
  • Adopted:
  • Online: June 07,2022
  • Published: