On feature extraction and region matching for forward scan sonar imaging

Murat D. Aykin, S. Negahdaripour

2012 · 31 citations · 6 references

Concepts

TL;DR

Automated processing of sonar video imagery enables valuable capabilities in turbid environments, such as detection, localization, tracking, feature mapping, and improved positioning of unmanned submarines through image registration and 3D motion estimation. This work proposes a novel technique for registering 2D forward‑look sonar images by optimizing over the sonar’s 3D motion parameters. The method achieves this by detecting landmarks with an adaptive clustering scheme and representing key features with Gaussian maps, thereby guiding the 3D motion optimization. Experiments with real data demonstrate faster computation and higher accuracy than the state‑of‑the‑art 2D transformation model, and the approach can enhance AUV navigation precision and environmental modeling.

Abstract

Automated processing of sonar video imagery enables valuable capabilities for a wide variety of underwater applications in turbid environments. Some key examples comprise the detection, localization and tracking of distinct scene targets, building feature maps, as well as improving positioning accuracy of unmanned submarines by means of image registration and 3D motion estimation to augment traditional positioning devices. This work offers a novel technique for the registration of 2D forward-look sonar images, by optimization over the sonar 3D motion parameters. It incorporates landmark detection through an adaptive clustering scheme with Gaussian map to represent key features at each frame. Improved performance is demonstrated in experiments with real data, both in terms of computation time and accuracy, relative to the state of the art, where the registration utilizes a simplified 2D image transformation model. Among many potentials, the method can improve precision in AUV navigation and environmental modeling.

References

6