Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar

2025-11-17

AI Summary

This work addresses the challenge of real-time underwater sonar imaging under dual constraints: extremely low upstream bandwidth (<0.0118 bpp) and severe acoustic artifacts—such as speckle, reverberation, and motion blur—affecting 98% of frames. We propose SCOPE, a self-supervised framework jointly optimizing compression and artifact correction. Its core innovations include: (i) the first integration of frequency-encoded latent-space learning with frequency-aware multi-scale segmentation, enabling end-to-end joint optimization without clean ground-truth labels or synthetic data, using only low-pass proxies; and (ii) adaptive codebook compression (ACC) coupled with embedded GPU-accelerated encoding and server-side multi-layer decoding to ensure real-time performance. Experiments demonstrate an SSIM of 0.77—40% higher than state-of-the-art—and over 80% bandwidth reduction, while significantly improving downstream object detection accuracy.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Real-time imaging sonar has become an important tool for underwater monitoring in environments where optical sensing is unreliable. Its broader use is constrained by two coupled challenges: highly limited uplink bandwidth and severe sonar-specific artifacts (speckle, motion blur, reverberation, acoustic shadows) that affect up to 98% of frames. We present SCOPE, a self-supervised framework that jointly performs compression and artifact correction without clean-noise pairs or synthetic assumptions. SCOPE combines (i) Adaptive Codebook Compression (ACC), which learns frequency-encoded latent representations tailored to sonar, with (ii) Frequency-Aware Multiscale Segmentation (FAMS), which decomposes frames into low-frequency structure and sparse high-frequency dynamics while suppressing rapidly fluctuating artifacts. A hedging training strategy further guides frequency-aware learning using low-pass proxy pairs generated without labels. Evaluated on months of in-situ ARIS sonar data, SCOPE achieves a structural similarity index (SSIM) of 0.77, representing a 40% improvement over prior self-supervised denoising baselines, at bitrates down to <= 0.0118 bpp. It reduces uplink bandwidth by more than 80% while improving downstream detection. The system runs in real time, with 3.1 ms encoding on an embedded GPU and 97 ms full multi-layer decoding on the server end. SCOPE has been deployed for months in three Pacific Northwest rivers to support real-time salmon enumeration and environmental monitoring in the wild. Results demonstrate that learning frequency-structured latents enables practical, low-bitrate sonar streaming with preserved signal details under real-world deployment conditions.

Problem

• Addresses limited uplink bandwidth for real-time underwater sonar streaming
• Corrects severe sonar artifacts like speckle and shadows without clean data
• Enables real-time compression and enhancement for underwater monitoring applications

Innovation

• Self-supervised framework for compression and artifact correction
• Adaptive Codebook Compression learns frequency-encoded latent representations
• Frequency-Aware Multiscale Segmentation separates structure from dynamics