Rotated target classification of sonar images via classification after alignment

Peng Zhang; Yue Fan; Jinsong Tang; Sha Li

doi:10.1117/12.2667746

10 February 2023 Rotated target classification of sonar images via classification after alignment

Peng Zhang, Yue Fan, Jinsong Tang, Sha Li

Proceedings Volume 12552, International Conference on Geographic Information and Remote Sensing Technology (GIRST 2022); 125522P (2023) https://doi.org/10.1117/12.2667746
Event: International Conference on Geographic Information and Remote Sensing Technology (GIRST 2022), 2022, Kunming, China

Abstract

Rotated target classification is a key problem in the automatic target recognition of sonar images. We propose herein a novel rotated target classification method of sonar images featured by classification after alignment. The proposed method first aligns the orientation of the rotated targets to normal orientation, and then uses the aligned images to train and test Convolution Neural Networks (CNN) to predict target categories. On the basis of rotated target detection of Synthetic Aperture Sonar (SAS) images, the proposed method was applied to classify the detected rotated targets and compared with the widely used data augmentation method. The results demonstrate that the proposed method significantly improves the classification accuracy, accelerates both the training and inference of CNN, and decreases the number of parameters of CNN.

Citation Download Citation

Peng Zhang, Yue Fan, Jinsong Tang, and Sha Li "Rotated target classification of sonar images via classification after alignment", Proc. SPIE 12552, International Conference on Geographic Information and Remote Sensing Technology (GIRST 2022), 125522P (10 February 2023); https://doi.org/10.1117/12.2667746

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available