Multibeam imaging sonar has become an increasingly important tool in the field of underwater object detection and description. In recent years, the scale-invariant feature transform (SIFT) algorithm has been widely adopted to obtain stable features of objects in sonar images but does not perform well on multibeam sonar images due to its sensitivity to speckle noise. In this paper, we introduce MBS-SIFT, a SIFT-like feature detector and descriptor for multibeam sonar images. This algorithm contains a feature detector followed by a local feature descriptor. A new gradient definition robust to speckle noise is presented to detect extrema in scale space, and then, interest points are filtered and located. It is also used to assign orientation and generate descriptors of interest points. Simulations and experiments demonstrate that the proposed method can capture features of underwater objects more accurately than existing approaches.

中文翻译：

---

用于多波束声纳成像的类似 SIFT 的特征检测器和描述符

多波束成像声纳已成为水下物体检测和描述领域越来越重要的工具。近年来，尺度不变特征变换（SIFT）算法被广泛用于获得声纳图像中物体的稳定特征，但由于其对散斑噪声的敏感性，在多波束声纳图像上表现不佳。在本文中，我们介绍了 MBS-SIFT，一种用于多波束声纳图像的类似 SIFT 的特征检测器和描述符。该算法包含一个特征检测器，后跟一个局部特征描述符。提出了一种新的对斑点噪声鲁棒的梯度定义来检测尺度空间中的极值，然后过滤和定位兴趣点。它还用于分配方向和生成兴趣点的描述符。