We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Improved Transformer-based detection of underwater plastic debris in complex environments
Summary
Researchers built an improved AI system that can spot plastic trash underwater more accurately, even in murky, cluttered footage where debris is small or hard to see. This matters because better detection tools could help track and clean up ocean plastic before it breaks down into microplastics — the tiny particles increasingly found in seafood, drinking water, and even human blood and organs. While this study focused on detection technology rather than health outcomes directly, improving our ability to find and remove plastic waste is an important step toward reducing microplastic pollution that can ultimately end up in our food chain and bodies.
Introduction Underwater plastic debris detection remains challenging in visually cluttered environments because underwater images are often severely degraded, debris instances are small, and backgrounds are complex. To address these challenges, this study develops an improved RF-DETR detector for underwater plastic debris detection. Methods The proposed architecture integrates an underwater frequency-aware feature reweighting module, a multi-scale frequency-aware attention module, and a query adaptive reweighting module with bounded learnable scales. These modules are designed to enhance the representation of weak-texture and low-contrast features while improving query-level localization and classification. The model was evaluated on the TrashCan dataset and further assessed through a transfer experiment on the DeepTrash dataset. Results On the TrashCan dataset, the proposed detector achieved 93.11% precision, an F1-score of 86.63%, an mAP@50 of 91.84%, and an mAP@50:95 of 69.92%. In the DeepTrash transfer experiment, the TrashCan-trained checkpoint was adapted to the one-class plastic target dataset and achieved 91.67% precision, 79.00% recall, an F1-score of 84.86%, an mAP@50 of 86.23%, and an mAP@50:95 of 55.06%. Compared with representative baselines, including YOLOv11n, YOLO26n, YOLO26s, and RT-DETR, the improved RF-DETR achieved the strongest overall performance in the reported TrashCan evaluation and DeepTrash transfer experiment. Ablation results further showed that the three proposed modules performed best when used in combination. Discussion The results demonstrate that the proposed frequency-aware feature enhancement and adaptive query reweighting strategies improve the detection of small and low-contrast underwater debris. The transfer results also indicate promising cross-dataset generalization. Overall, the proposed method provides a favorable trade-off between detection performance and model complexity on the evaluated datasets.