Underwater Object Detection

Overview

Underwater object detection studies how to locate and classify fish, debris, divers, and other targets in images affected by color loss, blur, backscatter, clutter, or sonar noise. Common approaches adapt YOLO-style detectors with multi-scale feature pyramids, attention, and physics-aware image restoration; sonar work also explores spiking networks, 3D detection, and fusion with cameras. Evaluation spans optical datasets such as RUOD, DUO, and URPC and sonar datasets such as UATD, with newer benchmarks examining domain differences, annotation quality, and cross-modal robustness. A central challenge is balancing accuracy, small-target sensitivity, and real-time efficiency while ensuring models generalize across changing water, seabed, sensors, and acquisition conditions.

Latest papers

31 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Feb 23, 2026

FinSight-Net:A Physics-Aware Decoupled Network with Frequency-Domain Compensation for Underwater Fish Detection in Smart Aquaculture

Underwater fish detection (UFD) is a core capability for smart aquaculture and marine ecological monitoring. While recent detectors improve accuracy by stacking feature extractors or introducing heavy attention modules, they often incur substantial computational overhead and, more importantly, neglect the physics that fundamentally limits UFD: wavelength-dependent absorption and turbidity-induced scattering significantly degrade contrast, blur fine structures, and introduce backscattering noise, leading to unreliable localization and recognition. To address these challenges, we propose FinSight-Net, an efficient and physics-aware detection framework tailored for complex aquaculture environments. FinSight-Net introduces a Multi-Scale Decoupled Dual-Stream Processing (MS-DDSP) bottleneck that explicitly targets frequency-specific information loss via heterogeneous convolutional branches, suppressing backscattering artifacts while compensating distorted biological cues through scale-aware and channel-weighted pathways. We further design an Efficient Path Aggregation FPN (EPA-FPN) as a detail-filling mechanism: it restores high-frequency spatial information typically attenuated in deep layers by establishing long-range skip connections and pruning redundant fusion routes, enabling robust detection of non-rigid fish targets under severe blur and turbidity. Extensive experiments on DeepFish, AquaFishSet, and our challenging UW-BlurredFish benchmark demonstrate that FinSight-Net achieves state-of-the-art performance. In particular, on UW-BlurredFish, FinSight-Net reaches 92.8% mAP, outperforming YOLOv11s by 4.8% while reducing parameters by 29.0%, providing a strong and lightweight solution for real-time automated monitoring in smart aquaculture.