We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Plastic water bottle detection model using computer vision in aquatic environments
AI summary Read the abstract
YOLOv8 computer vision system for automated plastic bottle counting in rivers, achieving >0.947 recall
Watershed macrotrash contamination is difficult to measure and requires tedious and labor-intensive processes. This work proposes an automated approach to waste counting, focusing on using computer vision, deep learning, and object tracking algorithms to acquire accurate counts of plastic bottles as they advect down rivers and streams. By using a combination of several publicly available labeled trash and plastic bottle image datasets, the model was trained to achieve high performance with the YOLOv8 object detection model. This was paired with the Norfair object tracking library and a novel post-processing algorithm to filter out false positives. The model performed extremely accurately over the test scenarios with just one false positive and recalls in excess of 0.947.
More Papers Like This
Construction of a Real-Time Detection for Floating Plastics in a Stream Using Video Cameras and Deep Learning
AI summary Read the abstract
This study developed a real-time YOLOv8-nano deep learning model to detect and classify four types of floating plastic debris in streams using field video data, achieving an F1-score of 0.982 in validation and 0.980 in testing. While object classification performance was high, tracking and counting at a monitoring line was limited (6 of 32 observed debris items detected), indicating the need for improved tracking methodology for practical river monitoring applications.
Real-time detection of macroplastic pollution in inland waters: development of a lightweight image recognition system
AI summary Read the abstract
This study developed a lightweight YOLOv8-based real-time detection system for macroplastic pollution in inland waters, optimized for deployment on fixed camera systems and UAVs. Pre-processing techniques including image tiling and blurring improved recall and mAP, and the system supports both decentralized on-site and centralized processing configurations.
RiSIM: River surface image monitoring software for quantifying floating macroplastic transport
AI summary Read the abstract
Researchers developed RiSIM, an image-based river monitoring software using deep learning for detecting, classifying, and tracking floating macroplastics, achieving strong agreement with ground truth measurements (r = 0.91 for quantity) and demonstrating that plastic transport rates increase significantly during flood events.
A Machine Learning Approach To Microplastic Detection And Quantification In Aquatic Environments
AI summary Read the abstract
This study developed a machine learning approach for detecting and quantifying microplastics in aquatic environments, demonstrating that automated image analysis can improve throughput and accuracy compared to manual microscopic counting for environmental monitoring applications.
YOLOv8-Based Microplastic Detection and Quantification in River Water Microscopic Images
AI summary Read the abstract
Researchers trained a YOLOv8 deep learning model on 300 microscopic images of river water from three Indonesian sites, achieving 0.786 precision and 0.731 mAP@0.5 for detecting microplastics, with higher image resolution improving accuracy and FTIR laboratory validation confirming compositional agreement with model detections.
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.