Matching Underwater Sonar Images by the Learned Descriptor Based on Style Transfer Method

TL;DR

This paper introduces a novel method combining style transfer and learned descriptors to improve underwater sonar image matching, addressing the gap between sonar and optical image matching techniques.

Contribution

It presents a new approach that uses style transfer to convert sonar images into optical styles and applies learned descriptors, enhancing matching performance.

Findings

Significantly improved sonar image matching quality

Effective style transfer preprocessing for underwater sonar images

Provides new insights into sonar image preprocessing techniques

Abstract

This paper proposes a method that combines the style transfer technique and the learned descriptor to enhance the matching performances of underwater sonar images. In the field of underwater vision, sonar is currently the most effective long-distance detection sensor, it has excellent performances in map building and target search tasks. However, the traditional image matching algorithms are all developed based on optical images. In order to solve this contradiction, the style transfer method is used to convert the sonar images into optical styles, and at the same time, the learned descriptor with excellent expressiveness for sonar images matching is introduced. Experiments show that this method significantly enhances the matching quality of sonar images. In addition, it also provides new ideas for the preprocessing of underwater sonar images by using the style transfer approach.