RT-DETR
RT-DETR on World Data Ocean: a running collection of 3 stories we have gathered and hand-picked because they are worth your time. Every post here touches on rt-detr in some way — the news, the analysis, the deep dives, and the occasional surprise find. A Global Hub for Ocean Intelligence 4 World Data Ocean is a centralized digital platform where researchers, scientists, and ocean enthusiasts converge to explore, analyze, and… New stories are added to this page as we find them, so check back if you want to keep up with what is happening around rt-detr, or subscribe to the RSS feed to get them as soon as they are published. Browse the collection below, or head back to the homepage to see everything World Data Ocean is covering right now.
Reliability-aware query restoration for embedded real-time object detection in degraded underwater vision systems
Real-time object detection in underwater vision systems faces significant challenges due to degraded visibility. Addressing this, our research introduces DQR-RTDETR, a novel framework that restores query reliability within RT-DETR detectors, demonstrably improving performance in turbid conditions. Empirical validation on the SeaClear dataset reveals a substantial increase in mean average precision (mAP@0.5:0.95) from 0.6998 to 0.7444, alongside improved localization. This compact intervention, adding only 0.05 million parameters, enables efficient edge deployment, achieving 18.7 FPS on an NVIDIA Jetson Orin NX
Lightweight Edge–Frequency Driven Real-Time Detection Transformer for side-scan sonar target detection
Side-scan sonar (SSS) remains the dominant imaging technology for underwater target detection, yet inherent image distortions and noise significantly impede high-precision recognition. Addressing this challenge, we introduce the Lightweight Edge–Frequency Driven Real-Time Detection Transformer (LEF-RT-DETR) framework, designed to enhance both accuracy and real-time performance. Through innovations like the Gaussian-Edge Enhancement Module and Multi-Scale Frequency-Spatial Denoising Block, LEF-RT-DETR demonstrably improves target feature perception and noise reduction. Experimental results show a 4.3% improvement in Average Precision compared to RT-DETR, alongside a substantial reduction in computational cost—a
Improved Transformer-based detection of underwater plastic debris in complex environments
Accurate detection of underwater plastic debris presents a significant challenge due to image degradation, small debris size, and complex backgrounds. This study introduces an improved RF-DETR detector, leveraging frequency-aware feature reweighting and adaptive query strategies to enhance the representation of challenging features. Evaluations on the TrashCan and DeepTrash datasets demonstrate superior performance compared to established baselines, achieving notable precision and mAP scores.