We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
WaveFilter: Advanced Imaging for Marine Microplastic Monitoring
Summary
This paper describes WaveFilter, a deep-learning system based on the YOLOv5 model trained to automatically detect microplastics in images of aquatic environments, achieving about 80% precision in identifying plastic particles even against complex backgrounds. The model is compact enough for real-time deployment, offering a faster and more scalable alternative to tedious manual counting methods. Automated detection tools like this could make large-scale marine microplastic monitoring more practical and consistent.
YOLOv5 has proven to be an efficient deep learning model for the detection of microplastics in aquatic environments. It is compact, with a total number of 214 layers and 7,022,326 parameters, while its model size is approximately 14.4 MB. Extensive performance analysis was done that states that the model has a precision of 79.8% and a recall of 67.1%, hence proving efficiency in the detection of instances of microplastics. The performance metrics are that the model offers a mAP of 72.1% at IoU=0.5 and averaged mAP of 34.1% averaged across different IoU values. These also validate the strength of YOLOv5 to detect microplastic with complex backgrounds which could be applied to real-time, automated, computer vision-based frameworks for the detection of marine plastic pollution. These promising results from the study have opened further vistas for development in environment monitoring and conservation.
Sign in to start a discussion.
More Papers Like This
Implementation of YOLOv5 for Detection and Classification of Microplastics and Microorganisms in Marine Environment
Researchers trained a YOLOv5 deep learning model on marine environment images and demonstrated it can accurately detect and classify both microplastics and microorganisms in real time, offering a memory-efficient tool for automated environmental monitoring.
TECI-YOLO: An Efficient, Lightweight Model for Detecting Small Floating Objects on Water Surfaces
Despite its title referencing floating object detection on water, this paper studies a machine learning model (TECI-YOLO) for detecting small objects on water surfaces using computer vision — not microplastic pollution. It examines improvements in detection accuracy and computational efficiency for real-time marine monitoring and is not directly relevant to microplastics research.
An Image Analysis of Coastal Debris Detection -Detection of microplastics using deep learning-
Researchers developed a deep learning-based coastal debris detection system using YOLOv7 and the SAHI vision library to identify microplastics in image data collected from shorelines. The system demonstrated effective detection performance and offers a scalable approach for automated monitoring of microplastic litter in coastal environments.
YOLOv7-Based Microplastic Detection: Crafting a Custom Dataset for Environmental Analysis
Researchers used three versions of the YOLO object detection model to detect and count microplastics from a custom-built dataset. YOLOv8 achieved the highest overall accuracy at 81.4%, followed by YOLOv7 at 80.7% and YOLOv9 at 77.2%, though YOLOv7 performed best with real-time test data. The study demonstrates the potential of AI-based detection systems for automating microplastic identification in environmental samples.
Detection of Floating Objects on Water Surface Using YOLOv5s in an Edge Computing Environment
This paper is not directly about microplastic pollution. It presents an improved computer vision system (YOLOv5s) for detecting floating objects on water surfaces using edge computing. While such technology could potentially be applied to detect plastic debris in rivers, the study itself focuses on the object detection algorithm rather than microplastics specifically.