Abstract
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.
Highlights
In recent years, with the constant exploration of oceans, multibeam sonar (MBS) is being applied in many scenarios, such as underwater environment mapping [1], underwater target detection [2], and underwater terrain-aided navigation [3]
As expected, using the Laplacian of Gaussian (LoG)-Harris detector (Figures 8(a) and 8(c)), the keypoints detected are mainly in high-reflectivity areas, but many false detections occur in the background corrupt by speckle noise
We present the MBS-scale-invariant feature transform (SIFT) algorithm, which combines a keypoint detector with a feature descriptor adapted to MBS images
Summary
Received 14 August 2020; Revised 26 April 2021; Accepted 22 June 2021; Published 16 July 2021. Multibeam imaging sonar has become an increasingly important tool in the field of underwater object detection and description. 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. 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 interest points are filtered and located. Simulations and experiments demonstrate that the proposed method can capture features of underwater objects more accurately than existing approaches
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
