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. Policy & Risk Sign in to save

An Image Analysis of Coastal Debris Detection -Detection of microplastics using deep learning-

Proceedings of International Conference on Artificial Life and Robotics 2024 Score: 35 ? 0–100 AI score estimating relevance to the microplastics field. Papers below 30 are filtered from public browse.
Yuto Okawachi, Shintaro Ogawa, Takamasa Hayashi, Chi Jie Tan, Janthori Titan, Eiji Hayashi, Eiji Hayashi, Ayumu Tominaga, Satoko Seino

Summary

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.

To address the issue of litter drifting ashore, this study developed a deep learning-based microplastic detection system.The system employed yolov7 [1] as its deep learning network, complemented by SAHI (Slicing Aided Hyper Inference) [2] as an additional vision library.yolov7 is renowned for its efficacy in real-time object detection.Our experimental framework involved four tests, utilizing two variations of yolov7 -the standard model and yolov7-e6e -in conjunction with SAHI.The effectiveness of each test was quantified using metrics such as Intersection over Union (IoU), Precision, Recall, F-measure, and Detection Time in seconds.For our dataset, we gathered images from actual cleanup locations, such as Hokuto Mizukumi Park.The model's discriminator underwent 700 training iterations, with a learning rate set at 0.001.Experimental results showed that it detects fairly small microplastics.

Sign in to start a discussion.

More Papers Like This

Article Tier 2

Development of Drifting Debris Detection System using Deep Learning on Coastal Cleanup

Researchers developed a deep learning-based system to detect litter on beaches using images and automated object recognition. Efficient litter detection tools could help coastal cleanup programs identify and remove plastic debris before it breaks down into microplastics.

Article Tier 2

Computer vision segmentation model—deep learning for categorizing microplastic debris

Researchers developed a deep learning computer vision model for automatically categorizing beached microplastic debris from images. The segmentation model was trained to identify and classify different types of microplastic particles, reducing the need for time-consuming manual counting and laboratory analysis. The study suggests that automated image-based detection could enable more scalable and consistent monitoring of microplastic pollution along coastlines.

Article Tier 2

Detection and assessment of marine litter in an uninhabited island, Arabian Gulf: A case study with conventional and machine learning approaches

Researchers surveyed marine litter on a remote Arabian Gulf island after a large cleanup, then trained a YOLO-v5 deep learning model on 10,400 beach images to automatically detect debris, achieving 90% detection accuracy and demonstrating that windward shores accumulate significantly more litter from neighboring countries.

Article Tier 2

Deep-Feature-Based Approach to Marine Debris Classification

This study applied deep learning to classify marine debris from images, demonstrating that feature-based neural network approaches can effectively distinguish plastic types and other debris categories to support automated ocean monitoring.

Article Tier 2

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.

Share this paper