SSS Underwater Target Image Samples Augmentation Based on the Cross-Domain Mapping Relationship of Images of the Same Physical Object

SSS Underwater Target Image Samples Augmentation Based on the Cross-Domain Mapping Relationship of Images of the Same Physical Object

Side-scan sonar (SSS) image sample augmentation plays an important role in improving the effect of deep-learning-based underwater target detection. However, the existing sample augmentation methods for cross-domain conversion always result in weak representativeness of the augmented samples since th...

Full description

Bibliographic Details
Main Authors: Yulin Tang, Liming Wang, Shaofeng Bian, Shaohua Jin, Yuting Dong, Houpu Li, Bing Ji
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Generative adversarial network (GaN)
mapping relationship
physical target model
sample augmentation
side-scan sonar (SSS)
underwater target detection
Online Access:https://ieeexplore.ieee.org/document/10173603/

Internet

https://ieeexplore.ieee.org/document/10173603/

Similar Items