🤖 AI Summary
In forward-looking sonar (FLS) near-bottom inspection under non-ideal configurations, severe intra-frame and inter-frame artifacts—as well as information loss in mosaics—arise from imaging parameter mismatches and localization errors. To address this, we propose an information-preserving sonar image mosaicking method. Our approach innovatively introduces a long-short-term sliding window (LST-SW) to dynamically correct local statistical properties, constructs a global variance map (GVM) for pixel-wise saliency modeling, and designs a statistics-aware adaptive weighting fusion strategy. Crucially, it achieves, for the first time, integrity preservation of suspicious target information without requiring precise pose knowledge or ideal imaging conditions. Real-world underwater experiments demonstrate significant artifact suppression, enhanced visibility of fine-scale targets, and improved structural fidelity of mosaics—meeting the stringent reliability requirements of expert-level manual interpretation.
📝 Abstract
Forward-Looking Sonar (FLS) has started to gain attention in the field of near-bottom close-range underwater inspection because of its high resolution and high framerate features. Although Automatic Target Recognition (ATR) algorithms have been applied tentatively for object-searching tasks, human supervision is still indispensable, especially when involving critical areas. A clear FLS mosaic containing all suspicious information is in demand to help experts deal with tremendous perception data. However, previous work only considered that FLS is working in an ideal system configuration, which assumes an appropriate sonar imaging setup and the availability of accurate positioning data. Without those promises, the intra-frame and inter-frame artifacts will appear and degrade the quality of the final mosaic by making the information of interest invisible. In this paper, we propose a novel blending method for FLS mosaicing which can preserve interested information. A Long-Short Time Sliding Window (LST-SW) is designed to rectify the local statistics of raw sonar images. The statistics are then utilized to construct a Global Variance Map (GVM). The GVM helps to emphasize the useful information contained in images in the blending phase by classifying the informative and featureless pixels, thereby enhancing the quality of final mosaic. The method is verified using data collected in the real environment. The results show that our method can preserve more details in FLS mosaics for human inspection purposes in practice.
