A Self-Supervised Denoising Strategy for Underwater Acoustic Camera Imageries
This addresses the challenge of using acoustic camera images for downstream visual algorithms in marine applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of denoising acoustic camera images in low-visibility marine environments by introducing a self-supervised deep learning strategy, which effectively filters noise without prior knowledge and enhances local feature matching performance.
In low-visibility marine environments characterized by turbidity and darkness, acoustic cameras serve as visual sensors capable of generating high-resolution 2D sonar images. However, acoustic camera images are interfered with by complex noise and are difficult to be directly ingested by downstream visual algorithms. This paper introduces a novel strategy for denoising acoustic camera images using deep learning techniques, which comprises two principal components: a self-supervised denoising framework and a fine feature-guided block. Additionally, the study explores the relationship between the level of image denoising and the improvement in feature-matching performance. Experimental results show that the proposed denoising strategy can effectively filter acoustic camera images without prior knowledge of the noise model. The denoising process is nearly end-to-end without complex parameter tuning and post-processing. It successfully removes noise while preserving fine feature details, thereby enhancing the performance of local feature matching.