Attitude-Trajectory Estimation for Forward-Looking Multibeam Sonar Based on Acoustic Image Registration

Henson, Benjamin; Zakharov, Yuriy

doi:10.1109/joe.2018.2830938

Cited by 27 publications

(15 citation statements)

References 38 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in [26], which is capable of estimating pixel displacements between two frames with subpixel accuracy. The displacement information is used to estimate the attitude and trajectory of the imaging sonar sensor.…”

Section: Image Registration Using the Simulated Imagesmentioning

confidence: 99%

Imaging sonar simulator for assessment of image registration techniques

Almanza-Medina

Henson

Zakharov

2019

Oceans 2019 MTS/Ieee Seattle

Self Cite

View full text Add to dashboard Cite

This work focuses on building a Forward-Looking sonar simulator capable of generating large volumes of ground truth data to test algorithms such as: novel image registration techniques for trajectory estimation, three-dimensional reconstruction or to be used as training data for machine learning algorithms. The simulator is capable of generating realistic data sets of images and providing ground truth data with the exact position and attitude of the sonar related to objects in a test scenario. The sonar simulator is developed using the Unity software platform. This work also shows an example application. Simulated image data sets for different sonar trajectories and seabed textures were created. These data sets are used by an attitude-trajectory estimation method and a quantitative analysis of the method is presented.

show abstract

Section: Image Registration Using the Simulated Imagesmentioning

confidence: 99%

Imaging sonar simulator for assessment of image registration techniques

Almanza-Medina

Henson

Zakharov

2019

Oceans 2019 MTS/Ieee Seattle

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Fourier-based method needs to convert the raw sonar data into a Cartesian format, introducing an interpolation error at the very beginning of the processing pipeline which is undesirable. Hence, the algorithm based on optical flow between consecutive sonar frames was proposed to register the sonar image in [12]. With the fact that neighboring pixels of sonar image show dependencies due to acoustic reverberation and dispersion, [41] only used the peripheral information in the neighborhood of a pixel to calculate the mutual information.…”

Section: Sonar Image Registrationmentioning

confidence: 99%

A Survey of Underwater Acoustic SLAM System

Jiang

Song

et al. 2019

Intelligent Robotics and Applications

View full text Add to dashboard Cite

Due to the unavailability of GPS signal, it is more urgent to develop the autonomous navigation capability for the underwater vehicles. In this paper, we summarize the development status of underwater SLAM (simultaneous localization and mapping) system. Different from the terrestrial or aerial SLAM that largely depends on the optical sensors, the underwater SLAM system mainly uses the acoustic sensors, i.e., sonars, to watch the environment. With respect to the general SLAM system, which is mainly composed of the front-end local dataassociation and the back-end global error adjustment, we briefly survey recent progress in sonar image registration and the loop closure detection. Furthermore, some heuristic problems are posed in the conclusion.

show abstract

“…Acoustic imaging techniques are not affected by these conditions and techniques for motion estimation using sonar images have been developed. For instance, Forward-Looking Sonar (FLS) images are used for underwater target tracking [26] and motion estimation approaches with deterministic [10], [25], [27], [28] or deep learning (DL) techniques [29].…”

Section: Introductionmentioning

confidence: 99%

Sonar FoV Segmentation for Motion Estimation Using DL Networks

2022

Self Cite

View full text Add to dashboard Cite

Accurate navigation of an autonomous underwater vehicle is important for its reliable operation. However, this task is challenging due to limitations of radio wave propagation and poor visibility in the aquatic environment. Underwater navigation techniques based on analysing sonar images facilitated by machine learning have shown promising results. However, previously proposed techniques are still complicated for real-time applications. This paper investigates low complexity techniques for the motion estimation based on the use of images obtained by a sonar looking down to the seafloor. The sonar can use multiple beams within a field of view (FoV). Various configurations of beams are considered according to portions of the FoV covered and two estimation approaches are investigated. In one approach, the sonar images are directly processed by a deep learning (DL) network, whereas in the other, the images are converted into (reduced size) vectors before applying them to a DL network. The vector approach shows a significantly lower computation time (about 10 times faster), which makes it suitable for realtime applications. Both the approaches show a similar estimation accuracy, about 10% of the maximum magnitude of the motion. The vector technique has been used to estimate a simulated trajectory and compare the estimate with the ground truth, which showed a good match. It has also been applied to estimate the trajectory of an imaging sonar from a real data set from a ship's hull inspection. The estimated trajectory has successfully been used to build a mosaic by merging the sonar images from the real data set.

show abstract

Attitude-Trajectory Estimation for Forward-Looking Multibeam Sonar Based on Acoustic Image Registration

Cited by 27 publications

References 38 publications

Imaging sonar simulator for assessment of image registration techniques

Imaging sonar simulator for assessment of image registration techniques

A Survey of Underwater Acoustic SLAM System

Sonar FoV Segmentation for Motion Estimation Using DL Networks

Contact Info

Product

Resources

About