0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Marine & Wildlife Sign in to save

Implementation of YOLOv5 for Detection and Classification of Microplastics and Microorganisms in Marine Environment

2023 7 citations ? Citation count from OpenAlex, updated daily. May differ slightly from the publisher's own count.
Iurii E. Shishkin, A.N. Grekov

Summary

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.

The authors of the work proposed a method for detecting and classifying microplastics and microorganisms in the marine environment using the YOLOv5 deep learning model. The model is trained on a dataset of 300 images collected from the marine environment, which includes microplastics and microorganisms. The images were marked using Label-Studio and the marked data was used to train the YOLOv5 model. The model was then tested on 60 control images to validate its accuracy. The results of the experiment showed that the YOLOv5 model is capable of accurately detecting and classifying microplastics and microorganisms in the marine environment. The YOLOv5 model has the advantage of having a small memory requirement, ability to work in real time, and better background area distinction compared to other models.

Share this paper