We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Automated Detection and Mapping of Waste in Different Environments and Seasons Using UAV Imagery and AI
AI summary Read the abstract
Researchers tested drone cameras and artificial intelligence to spot waste, like plastic bags, bottles, construction debris and rubber, in two riverside areas in Romania. Using computer filtering to avoid counting the same item twice cut the detected waste count from 521 to 194 items. Only spring data has been analyzed so far, so results across seasons and locations are not yet known.
This presentation describes a workflow for automated detection and mapping of waste in different environments using UAV imagery and artificial intelligence. The study focuses on two sites in western Călărași County, Romania, near the Argeș River and the localities of Budești and Șoldanu. RGB UAV imagery acquired during the spring 2026 campaign is processed using semantic segmentation with a DeepLabV3+ model and a ResNet-152 encoder. The model considers four waste categories: plastic bags, plastic bottles, construction debris, and rubber. Predictions are converted into spatial summaries, including object counts and approximate mapped area, using image geolocation and ground sampling distance estimates. Preliminary post-processing tests examine confidence thresholds and overlap-controlled frame selection to reduce repeated counting. At a confidence threshold of 0.5, overlap control reduced the reported object count from 521 to 194 and summed mapped area from 37.02 m² to 12.59 m². Seasonal robustness and generalisation across sites remain to be evaluated, as only the spring campaign has been completed at this stage. The work is associated with the ACCELERATE project (101182930), funded by the European Union under Horizon Europe Marie Skłodowska-Curie Actions Staff Exchanges.
More Papers Like This
Automated Detection and Mapping of Waste in Different Environments and Seasons Using UAV Imagery and AI
AI summary Read the abstract
Researchers used drone cameras and artificial intelligence to spot illegal waste dumps, including plastic litter, across rural and semi-rural areas in Romania. The system identified over 3,000 waste items with 91% accuracy, finding that trash often piles up near roads and intersections, suggesting people dump it from vehicles.
Real-Time River Plastic and Debris Detection System using Computer Vision
AI summary Read the abstract
Researchers designed a computer system that uses camera footage and artificial intelligence to automatically spot floating plastic bottles, bags and other debris in rivers. The system counts items and tracks pollution patterns over time, offering a way to monitor river waste without manual inspection.
Ocean and River Plastic Waste Detection Using Computer Vision
AI summary Read the abstract
Millions of tons of plastic pour into our oceans every year, much of it carried by rivers—but tracking where it comes from has always relied on slow, manual surveys. This study built an AI camera system that automatically spots and counts floating plastic waste from drone and shoreline footage with over 91% accuracy, offering a faster way to find pollution hotspots. Better tracking matters because plastic waste that lingers in waterways breaks down into microplastics, which end up in the fish and water we consume, making tools like this useful for guiding cleanup efforts before pollution reaches our food and water supply.
Leveraging Artificial Intelligence for Plastic Waste Management in Coastal Waters: A Drone-Based Approach for Identification and Hotspot Detection
AI summary Read the abstract
A machine learning model trained on drone footage achieved 89.4% accuracy in classifying plastic debris types in coastal waters and identifying hotspot areas for targeted cleanup operations. The AI-driven approach offers faster and more scalable monitoring than traditional methods, though detection of small microplastics and environmental variability remain challenges.
Multi-Scale Hierarchical Attention Ensemble Network for Fine-Grained Riverine Waste Segmentation Using UAV Multispectral Imagery
AI summary Read the abstract
Researchers used a drone with a special five-band camera to fly over a river in Indonesia and trained an AI system to automatically spot and map plastic waste floating in the water, even distinguishing it from natural debris like leaves and branches. This matters because rivers are a major pathway for plastic to reach oceans and break down into microplastics, which can end up in our food and water; better, faster detection tools like this could help communities target cleanup efforts before waste spreads further. The study is an early proof-of-concept from one river during one season, so more testing is needed before it can be used widely.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.