We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Papers
61,005 resultsShowing papers similar to High-resolution, non-invasive animal tracking and reconstruction of local environment in aquatic ecosystems
ClearMoveR: an R package for easy processing and analysis of animal video-tracking data
This paper introduces MoveR, an R software package for analyzing animal video-tracking data to study movement and behavior. The tool is not related to microplastic research but could be applied to study how animals respond behaviorally to plastic pollution exposure.
MoveR: An R package for easy processing and analysis of animal video-tracking data
Researchers developed MoveR, an open-source R package that provides flexible tools for importing, filtering, visualizing, and analyzing animal movement data from common video-tracking systems. The package addresses challenges posed by the complexity and noisiness of high-resolution tracking datasets by offering functions for polishing data, removing artifacts, subsetting paths, and computing movement and behavior metrics.
An Open-Source Computer Vision-Based Method for Microplastic Settling Velocity Calculation
Researchers developed an open-source computer vision method to measure microplastic settling velocities from video recordings, enabling low-cost quantification of how particles of different sizes and densities sink in water columns with implications for predicting MP fate in aquatic environments.
An Open-Source Computer-Vision-Based Method for Spherical Microplastic Settling Velocity Calculation
Researchers developed an open-source computer vision method to measure the settling velocity of spherical microplastics, replacing subjective manual methods with automated image analysis. The tool provides a standardized, accessible approach for predicting microplastic transport and fate in aquatic environments.
A field deployable imaging system for detecting microplastics in the aquatic environment
Researchers built a portable imaging system for detecting microplastics in water that can be deployed directly in the field rather than requiring laboratory analysis. The system uses a de-scattering algorithm to produce clear images even in turbid water conditions and can identify particles as small as 50 micrometers. This low-cost tool could make routine microplastic monitoring of rivers, lakes, and coastal waters much more practical and accessible.
The SWIMMER: a System for underWater Imaging and Monitoring for Marine Environment Research
Researchers developed SWIMMER (System for underWater Imaging and Monitoring for Marine Environment Research), an open-source low-cost robotic platform designed for non-invasive stereo imaging of basking sharks to study their poorly understood gill-raker filtration system — which processes two million liters of water per hour — as a potential model for microplastic filtration technologies. Field trials successfully captured video of 9 individual sharks across 6 encounters, demonstrating the platform's capability for marine environmental monitoring.
A portable AI-powered rotifer-tracking system for in-situ water quality assessment
Researchers built a portable, low-cost AI-powered microscope using a Raspberry Pi and 3D-printed components to track rotifers (freshwater organisms) as biological indicators of water quality in the field. The system automated rotifer tracking and analysis, enabling real-time water quality assessment without lab infrastructure.
Estimating precision and accuracy of automated video post-processing: A step towards implementation of AI/ML for optics-based fish sampling
Researchers developed automated computer vision models for identifying commercially important Gulf of Mexico fish species from video surveys, assessing precision and accuracy as a step toward replacing manual review with AI-based processing.
Identification and velocity measurement of microplastics based on machine learning
Researchers developed a machine learning framework to simultaneously track multiple microplastics in water and measure their terminal settling velocities, capturing particle interaction dynamics that conventional single-particle tracking methods miss.
Marine Litter Tracking System: A Case Study with Open-Source Technology and a Citizen Science-Based Approach
Researchers deployed GPS-tracked drifter devices in the Arno River using open-source hardware and citizen science approaches to track how plastic litter moves through river systems toward the ocean, providing empirical data on plastic transport dynamics that can improve models of river-to-ocean plastic flux.
Improving YOLOv11 for marine water quality monitoring and pollution source identification
Researchers improved the YOLOv11 computer vision model to better detect and identify marine pollution sources, including oil spills, debris, and turbid water, in complex underwater environments. The enhanced model achieved higher detection accuracy and faster processing speeds compared to the standard version. The study demonstrates that advanced AI-based monitoring tools can meaningfully improve our ability to track and respond to marine pollution in real time.
Optical System for In-situ Detection of Microplastics
Researchers developed a portable optical system capable of detecting, identifying, continuously monitoring, and quantifying microplastics in situ at natural water bodies. The system uses optical techniques to observe the temporal behavior of microplastic concentrations at fixed locations, enabling real-time environmental monitoring without sample collection and laboratory processing.
Real-Time Quantification of Microplastics in Aquatic Systems via Fluorescence Microscopy
Researchers developed a real-time fluorescence microscopy method capable of quantifying microplastics in aquatic systems with high precision, providing a faster and more accessible tool for monitoring microplastic contamination in drinking water reservoirs.
A Machine Learning Approach To Microplastic Detection And Quantification In Aquatic Environments
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.
Application of Pattern Recognition and Computer Vision Tools to Improve the Morphological Analysis of Microplastic Items in Biological Samples
Researchers developed and validated an open-source image analysis procedure for measuring morphological characteristics of microplastic items identified in fish organ samples, using manually set edge points in digital microscope images and comparison against commercial MotiConnect software. The proposed workflow enabled accurate calculation of shape descriptors such as length, width, and item area, offering a cost-effective alternative for routine laboratory microplastic morphological analysis.
Rapid development of fast and flexible environmental models: the Mobius framework v1.0
This paper describes Mobius, an open-source framework for building environmental models that allows researchers without advanced programming skills to create complex water quality and ecological models. Better modeling tools can help scientists predict how microplastics and other pollutants spread through watersheds.
Real-Time Detection of Microplastics Using an AI Camera
Researchers developed a camera-based system using artificial intelligence to detect and measure microplastics in real time as they move through water. The system was tested with three different camera setups and could identify particles, measure their size, and track their speed. This technology could provide a faster and more practical alternative to the labor-intensive laboratory methods currently used to monitor microplastic pollution.
PlanktonScope: Affordable modular imaging platform for citizen oceanography
Researchers built an affordable, modular imaging platform called the PlanktonScope that enables citizen scientists and researchers to image and monitor marine plankton communities at low cost. Such tools could be adapted for identifying and counting microplastic particles in water samples, expanding the scale of environmental monitoring.
Identification of Microplastics in Aquatic Environments Using Oxidative Treatment and Automated Image Analysis
Researchers developed a cost-effective and replicable method for detecting microplastics in freshwater environments using oxidative treatment to digest organic matter from water samples, enabling cleaner isolation and more accurate identification of MP particles without requiring expensive instrumentation.
Automatic Detection of Microplastics in the Aqueous Environment
Researchers developed a deep-learning system for real-time detection and counting of microplastics in freshwater, achieving high accuracy for particles 1 mm and larger.
Message in a bottle: Open source technology to track the movement of plastic pollution
Researchers tracked individual 500 ml PET plastic bottles released into the Ganges River system using open-source GPS and satellite technology to study how plastic debris moves through river systems before reaching the ocean. The study demonstrated the feasibility of using animal-tracking technology to follow plastic items through complex riparian environments, providing new insights into inland plastic transport pathways.
Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection
Researchers developed a robust and fair underwater target detection system for automated underwater vehicles (AUVs) to support marine biodiversity data collection, addressing unique challenges of subsea imaging compared to above-ground remote sensing.
Enhancing Marine Debris Acoustic Monitoring by Optical Flow-Based Motion Vector Analysis
An optical flow-based motion vector analysis approach was developed to enhance acoustic monitoring of marine plastic debris in coastal environments. The method improved detection accuracy of debris movement underwater, offering a cost-effective tool for continuous autonomous marine debris surveillance.
A Handy Open-Source Application Based on Computer Vision and Machine Learning Algorithms to Count and Classify Microplastics
An open-source computer vision application was developed to automatically count and classify microplastics in microscopy images, achieving accuracy comparable to manual counting while processing samples orders of magnitude faster, offering the scientific community a free tool to reduce the bottleneck of tedious visual microplastic enumeration.