We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Papers
20 resultsShowing papers similar to Object Detection of Macroplastic Waste Using Unmanned Aerial Vehicles in Urban Canal
ClearMini Uav-based Litter Detection on River Banks
Researchers developed a drone-based litter detection system combining high-resolution mapping, deep learning object detection, and vision-based localization that locates riverbank litter with decimeter-level accuracy, enabling automated monitoring of plastic pollution in urban waterway areas.
Quantifying Marine Macro Litter Abundance on a Sandy Beach Using Unmanned Aerial Systems and Object-Oriented Machine Learning Methods
Researchers developed an object-oriented machine learning classification strategy using unmanned aerial system imagery to automatically identify and quantify marine macro litter on sandy beaches, comparing three automated methods against manual counts. The UAS-based approach demonstrated capacity for scalable, cost-effective beach litter monitoring to support coastal pollution surveillance programs.
UAV Approach for Detecting Plastic Marine Debris on the Beach: A Case Study in the Po River Delta (Italy)
UAV imaging was used to detect and map anthropogenic marine debris on beaches in the Po River Delta, Italy, testing different image processing strategies and demonstrating that centimeter-scale spatial resolution UAV surveys can efficiently locate macroplastics before they degrade into harder-to-remove microplastics.
A Deep Learning Model for Automatic Plastic Mapping Using Unmanned Aerial Vehicle (UAV) Data
Researchers applied a deep learning semantic segmentation model (ResUNet50 based on U-Net architecture) to UAV orthophotos to automatically map floating plastic debris, achieving F1-scores of 0.86-0.92 for specific plastic types including oriented polystyrene, nylon, and PET. Classification accuracy decreased with lower spatial resolution, with 4 mm resolution providing optimal performance for distinguishing plastic types.
Plastic Waste on Water Surfaces Detection Using Convolutional Neural Networks
Researchers evaluated state-of-the-art convolutional neural network architectures for automatically detecting plastic waste on water surfaces, training models on a dataset representing four categories of plastic litter including plastic bags. The study benchmarked multiple CNN object detection models following extensive dataset preprocessing to determine the most effective approach for automated plastic pollution identification.
Designing Unmanned Aerial Survey Monitoring Program to Assess Floating Litter Contamination
Researchers tested drone-based aerial surveys with high-resolution cameras as a cost-effective method for monitoring floating litter contamination in coastal waters, comparing manual counting, automated detection, and modeling approaches to optimize survey design.
Use of UAVs and Deep Learning for Beach Litter Monitoring
Researchers developed an autonomous beach litter monitoring pipeline using UAV drone surveys combined with a YOLOv5 deep learning object detection algorithm trained on footage from Malta, Gozo, and the Red Sea coast. The system achieved a mean average precision (mAP50-95) of 0.252 across all litter classes and incorporated geolocation and digital elevation model data to support future autonomous retrieval robots.
A Proposed Technology Solution for Preventing Marine Littering Based on Uavs and Iot Cloud-based Data Analytics
This paper proposes a technological solution using unmanned aerial vehicles and automated collection systems to prevent marine littering at coastal hotspots. The approach aims to intercept plastic waste before it enters the ocean and breaks down into microplastics.
Aerial Remote Sensing of Aquatic Microplastic Pollution: The State of the Science and How to Move It Forward
A systematic literature review of aerial remote sensing for aquatic microplastic detection identified three main approaches — spectral characteristics, floating debris imaging, and AI-based analysis — all still largely experimental rather than operational.
Automatic detection and quantification of floating marine macro-litter in aerial images: Introducing a novel deep learning approach connected to a web application in R
Researchers developed a convolutional neural network-based algorithm to automatically detect and quantify floating marine macro-litter in aerial images, training it on 3,723 images and integrating it into a web application for practical monitoring use.
Advancing floating macroplastic detection from space using hyperspectral imagery
Researchers evaluated the use of hyperspectral satellite and airborne imagery to detect floating plastic debris in rivers and oceans, addressing major challenges related to plastic spectral properties in field conditions. Remote sensing tools for plastic detection are important for large-scale monitoring of the macro-scale plastic that eventually becomes microplastics.
Mapping Waste Piles in an Urban Environment Using Ground Surveys, Manual Digitization of Drone Imagery, and Object Based Image Classification Approach
This study used drone imagery and image classification to map illegal waste dumps in a densely populated Malawian neighborhood. Better waste monitoring tools like drone-based detection are important for identifying sites where plastic waste accumulates and fragments into microplastics.
An automated solid waste detection using the optimized YOLO model for riverine management
Researchers developed an optimized YOLO-based deep learning model for automated detection of solid waste in rivers, achieving high accuracy in identifying floating debris to support autonomous robotic riverine cleanup systems.
Using a UAV Thermal Infrared Camera for Monitoring Floating Marine Plastic Litter
Researchers evaluated thermal infrared (TIR) cameras mounted on UAVs as a novel tool for detecting floating plastic litter on water surfaces, demonstrating that TIR imaging can complement visible and near-infrared sensing by detecting plastics based on temperature differences rather than optical reflectance.
Use of an uncrewed surface vehicle and near infrared hyperspectral imaging for sampling and analysis of aquatic microplastics
Researchers combined an uncrewed surface vehicle with near-infrared hyperspectral imaging to sample and analyze aquatic microplastics larger than 300 micrometers. The approach demonstrated improved scalability and repeatability compared to traditional trawling methods, offering a more efficient way to monitor microplastic contamination in coastal waters.
Implementing Edge Based Object Detection For Microplastic Debris
This study developed an edge-based object detection algorithm for identifying microplastic debris in images. Automated detection methods are important for scaling up microplastic monitoring, particularly in field settings where manual visual inspection of thousands of particles is impractical.
Enhancing marine debris identification with convolutional neural networks
A deep learning model was developed to identify and classify marine debris components captured by underwater remotely operated vehicle imagery, addressing the challenge of widely distributed ocean waste including microplastics. The convolutional neural network demonstrated improved accuracy for debris detection and classification compared to conventional image analysis methods.
Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images
Researchers applied machine learning to aerial multispectral images for automated detection of plastic litter in natural areas, demonstrating that combining spectral data with classification algorithms can effectively identify and monitor plastic waste pollution.
Aquatic Trash Detection and Classification: a Machine Learning and Deep Learning Perspective
This review examines machine learning and deep learning approaches for detecting and classifying aquatic trash in waterways, evaluating how computer vision algorithms trained on underwater and surface imagery can automate pollution monitoring for faster, more scalable ocean cleanup.
Quantification of floating riverine macro-debris transport using an image processing approach
A new image-based algorithm was developed to measure how much floating debris is moving across a river surface, using color detection and template matching. This tool could help track macro-debris transport in rivers, which is the primary pathway for plastic litter reaching the ocean.