Underwater-Sonar-Image-Based 3D Point Cloud Reconstruction for High Data Utilization and Object Classification Using a Neural Network

This paper proposes a sonar-based underwater object classification method for autonomous underwater vehicles (AUVs) by reconstructing an object’s three-dimensional (3D) geometry. The point cloud of underwater objects can be generated from sonar images captured while the AUV passes over the object. Then, a neural network can predict the class given the generated point cloud. By reconstructing the 3D shape of the object, the proposed method can classify the object accurately through a straightforward training process. We verified the proposed method by performing simulations and field experiments.

[1]  David P. Williams,et al.  Adaptive Multiview Target Classification in Synthetic Aperture Sonar Images Using a Partially Observable Markov Decision Process , 2012, IEEE Journal of Oceanic Engineering.

[2]  Hanumant Singh,et al.  Robotic tools for deep water archaeology: Surveying an ancient shipwreck with an autonomous underwater vehicle , 2010, J. Field Robotics.

[3]  Gaurav Pandey,et al.  Underwater Image Dehazing via Unpaired Image-to-image Translation , 2020, International Journal of Control, Automation and Systems.

[4]  Hyun Myung,et al.  Vision-based object detection and tracking for autonomous navigation of underwater robots , 2012 .

[5]  T. Maki,et al.  Tracking a Sea Turtle by an AUV with a Multibeam Imaging Sonar: Toward Robotic Observation of Marine Life , 2020 .

[6]  Son-Cheol Yu,et al.  3D Reconstruction Using Two Sonar Devices in a Monte-Carlo Approach for AUV Application , 2020 .

[7]  Scott Reed,et al.  An automatic approach to the detection and extraction of mine features in sidescan sonar , 2003 .

[8]  Son-Cheol Yu,et al.  Robust Sonar-Based Underwater Object Recognition Against Angle-of-View Variation , 2016, IEEE Sensors Journal.

[9]  Divas Karimanzira,et al.  Object Detection in Sonar Images , 2020 .

[10]  Zhijie Tang,et al.  Underwater Robot Detection System Based on Fish’s Lateral Line , 2019, Electronics.

[11]  Tamaki Ura,et al.  Development of hovering type AUV “Cyclops” and its performance evaluation using image mosaicing , 2015 .

[12]  Son-Cheol Yu,et al.  AUV-Based Underwater 3-D Point Cloud Generation Using Acoustic Lens-Based Multibeam Sonar , 2018, IEEE Journal of Oceanic Engineering.

[13]  Jinwhan Kim,et al.  A Comparison of Nonlinear Filter Algorithms for Terrain-referenced Underwater Navigation , 2018, International Journal of Control, Automation and Systems.