Spatial Acoustic Projection for 3D Imaging Sonar Reconstruction

Abstract

In this work we present a novel method for reconstructing 3D surfaces using a multi-beam imaging sonar. We integrate the intensities measured by the sonar from different viewpoints for fixed cell positions in a 3D grid. For each cell we integrate a feature vector that holds the mean intensity for a discretized range of viewpoints. Based on the feature vectors and independent sparse range measurements that act as ground truth information, we train convolutional neural networks that allow us to predict the signed distance and direction to the nearest surface for each cell. The predicted signed distances can be projected into a truncated signed distance field (TSDF) along the predicted directions. Utilizing the marching cubes algorithm, a polygon mesh can be rendered from the TSDF. Our method allows a dense 3D reconstruction from a limited set of viewpoints and was evaluated on three real-world datasets.

Neural Implicit Surface Reconstruction using Imaging Sonar

“…However, these methods are limited to simple geometries or require collecting a larger dataset of real elevation data. Arnold et al [32] propose training a CNN to predict the signed distance and direction to the nearest surface for each cell in a 3D grid. However, the method requires ground truth Truncated Signed Distance Field (TSDF) information which can be difficult to obtain.…”