We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Research on marine litter detection based on CNN-Transformer heterogeneous parallelism
AI summary Read the abstract
Researchers developed YOLO-Trans, a CNN-Transformer hybrid model for detecting marine debris in ocean imagery, outperforming standard detection models on a multi-scenario dataset of small and deformed targets. Accurate automated marine litter detection is critical for monitoring and quantifying plastic pollution at sea, enabling more effective large-scale cleanup and pollution tracking.
Aiming at strong background interference and low detection accuracy of small/deformed targets in marine debris detection, this paper develops a high-precision lightweight intelligent detection and recognition system. A multi-scenario dataset is built and data augmentation is used to tackle sample scarcity and domain shift; a CNN-Transformer heterogeneous parallel model YOLO-Trans is designed on the YOLOv8 baseline for local-to-global feature extraction and accurate detection of small/deformed targets, and a visual detection system is developed with PyQt5. Experiments show the model surpasses the original YOLOv8s in all metrics on the self-built dataset, and ablation experiments validate the improved modules’ effectiveness, offering technical support for large-scale intelligent marine debris monitoring.
More Papers Like This
Swin Transformer-Based Framework for Floating Marine Debris Detection and Classification
AI summary Read the abstract
An optimized Swin Transformer deep learning model achieved 98.5% accuracy in classifying floating marine debris in rivers, shorelines, and harbors, outperforming conventional CNNs. Automated, scalable debris detection supports real-time environmental monitoring and more effective cleanup of plastic pollution accumulation zones.
Deep Learning-Based Underwater Trash Detection System UsingYOLOv8
AI summary Read the abstract
Researchers trained a YOLOv8 deep learning model on underwater debris imagery to enable real-time detection and classification of submerged plastic trash, demonstrating substantially faster and more scalable performance than traditional manual survey or sonar-based methods.
Synergistic integration of vision transformers and advanced segmentation algorithms for panoptic mapping of marine litter
AI summary Read the abstract
A panoptic segmentation approach combining vision transformers with instance and semantic segmentation accurately classifies and localizes marine litter objects in challenging underwater and surface imagery. Improved automated detection of marine debris is essential for quantifying plastic pollution distribution and informing targeted cleanup and regulatory interventions.
State of the art applications of deep learning within tracking and detecting marine debris: A survey
AI summary Read the abstract
This survey analyzed 28 recent deep learning studies applied to marine debris detection and tracking, finding that YOLO-based models significantly outperform other object detection methods. Testing on a small curated dataset revealed low accuracy and high false positive rates, underscoring the urgent need for a comprehensive annotated database of underwater plastic debris.
Transformer Assisted U-Net for Marine Litter Detection on Sentinel-2 Imagery
AI summary Read the abstract
This study presented a deep learning scheme for detecting marine litter in Sentinel-2 satellite imagery using a Deep UNet architecture enhanced with self- and cross-attention transformer mechanisms in the decoder, incorporating all Sentinel-2 bands alongside NDVI and FDI indices. The model was trained on the FloatingObjects benchmark dataset and compared against state-of-the-art approaches for marine debris segmentation from space.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.