Method for reconstructing 3D shapes of underwater objects using ultrasound image data and an underwater robot

Technology for 3D Reconstruction of Underwater Objects Using Ultrasonic Point Cloud Grouping and Polygon Reconstruction

This technology enables an underwater robot equipped with an ultrasonic camera to generate a 3D point cloud from image data acquired while moving around an object from multiple directions. It then groups the data by movement direction and reconstructs it into a 3D polygon through 2D projection and polygon calculation.

Existing ultrasonic camera methods have limitations in reproducing seafloor objects as realistic 3D shapes because they map 3D information onto a 2D plane.

This technology proposes a method to achieve high-precision 3D modeling by grouping point clouds acquired from multiple angles, performing maximum overlapping polygon calculations, and applying post-processing noise reduction. It can be applied to seafloor exploration, shipwreck searches, and marine structure diagnostics, providing near-realistic shape information even in high-turbidity environments.

‍

‍

Key Features:

• Detecting objects located on the seafloor based on image data acquired from an ultrasonic camera
• Acquiring multiple sets of image data by moving in multiple directions relative to the object
• Analyzing the multiple sets of image data to calculate 3D point cloud data for the object
• Grouping point cloud data according to movement direction and implementing 3D polygons through polygon calculation

‍

This invention was developed with the support of the Smart Underwater Tunnel System Research Center of the Ministry of Science and ICT.