Sonar FoV Segmentation for Motion Estimation Using DL Networks
Sonar FoV Segmentation for Motion Estimation Using DL Networks
复制标题
DOI：
10.1109/access.2022.3156271
复制
发表时间：
2022
期刊：
影响因子：
3.9
通讯作者：
José E. Almanza-Medina;B. Henson;Y. Zakharov
中科院分区：
文献类型：
--
作者：
José E. Almanza-Medina;B. Henson;Y. Zakharov
自主水下航行器的精确导航对其可靠运行至关重要。然而，由于无线电波传播的限制和水中环境能见度差，这项任务具有挑战性。在机器学习的推动下，基于分析声纳图像的水下导航技术已经显示出有希望的结果。然而，先前提出的技术对于实时应用来说仍然很复杂。本文研究了一种基于水下声纳图像的低复杂度运动估计技术。声纳可以在一个视场（FoV）内使用多个波束。根据所覆盖视场的不同，考虑了不同的波束结构，并研究了两种估计方法。在一种方法中，声纳图像由深度学习（DL）网络直接处理，而在另一种方法中，图像在应用于深度学习网络之前被转换成（缩小尺寸）向量。矢量方法的计算时间明显缩短（大约快10倍），这使得它适合于实时应用程序。两种方法都显示出相似的估计精度，约为运动最大幅度的10%。利用矢量技术对模拟弹道进行估计，并与地面真实情况进行了比较，结果吻合较好。该方法还被应用于从船体检查的真实数据集估计成像声纳的轨迹。利用估计的轨迹成功地将来自真实数据集的声纳图像合并成一个马赛克。
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 real-time 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.