Bathymetry reconstruction from sidescan sonar images using neural networks

Authors

  • Julian Christopher Maypa ⋅ PH National Institute of Physics, University of the Philippines Diliman
  • Maricor N. Soriano ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

We demonstrate a method to estimate bathymetry from sidescan sonar images using machine learning. The mapping of sonar image intensity values to bathymetry maps is learned by a convolutional neural network autoencoder. This network is trained with simulated images derived from the Lambertian model, and it is tested with never-before-seen simulated images and actual sidescan sonar images. After training, the network was able to estimate bathymetry maps from actual sidescan images with an error in the sub-meter level. This degree of error is useful for the navigation of ships, construction of submarine pipelines, and management of marine protected areas.

Downloads

Issue

Article ID

SPP-2024-3E-05

Section

Complex Systems and Data Analytics

Published

2024-06-26

How to Cite

[1]
JC Maypa and MN Soriano, Bathymetry reconstruction from sidescan sonar images using neural networks, Proceedings of the Samahang Pisika ng Pilipinas 42, SPP-2024-3E-05 (2024). URL: https://proceedings.spp-online.org/article/view/SPP-2024-3E-05.