We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Multi-Task UAV Dataset for Floating Plastic Waste Detection in the Kashmir Region (AquaPlasticWaste 2026)
Summary
Researchers created a massive collection of drone photos (5,000 images) showing plastic trash floating on Dal Lake, a freshwater lake in Kashmir that many communities depend on, and carefully labeled every piece of litter to train AI models to spot it automatically. This matters because polluted lakes can break down into microplastics that contaminate drinking water and the food chain, and better detection tools could help conservationists find and clean up trash faster before it degrades further. While this study doesn't test health effects directly, it provides a key building block, reliable AI monitoring, for protecting water sources that people rely on.
AquaPlasticWaste 2026 — Multi-Task UAV Dataset for Floating Plastic Waste Detection in the Kashmir Region — is a 5,000-image UAV aerial imagery dataset for automated plastic waste monitoring on Dal Lake, an ecologically important Himalayan freshwater lake in Srinagar, Kashmir, India, facing severe pollution pressure. Images were captured with a consumer-grade quadrotor UAV flown at a consistent altitude across open water, shoreline, houseboat clusters, and floating garden zones, under varied lighting conditions. It is the first multi-task, polygon-annotated UAV dataset targeting plastic pollution on a Himalayan lake surface. All images carry polygon-based instance segmentation masks, rather than bounding boxes, to capture the irregular shapes of floating litter (e.g., flattened bags, torn wrappers). Masks were created in CVAT and verified through a primary annotator, a second cross-checking annotator, a third adjudicator, and a final quality-control pass. Two labeling schemes are provided from the same masks: binary (plastic vs. non-plastic) and seven-class (background, bottle, cap, foam, polythene, shoe, wrapper). Annotations are exported in both COCO JSON and YOLO polygon/segmentation formats for direct use in standard detection and segmentation frameworks. Of the 5,000 images, 4,692 (93.8%) contain plastic and 308 (6.2%) are plastic-free, with 30,166 polygon instances annotated in total. Wrapper is the most common class (35.4% of instances, present in 63.2% of images); shoe is rarest (1.1% of instances, 4.8% of images). Mean plastic pixel coverage is 1.40% per image (median 0.55%, max 33.31%), and median instance size is 1,448 pixels, well below typical benchmark object sizes (e.g., MS-COCO) — a genuine small-object challenge. Imbalance is reported at three levels for different loss-function needs: 31.9:1 by instance count (wrapper vs. shoe), 44.8:1 by pixel area among foreground classes (polythene vs. cap), and 70.4:1 between plastic and background pixels overall. A single annotation source supports four downstream tasks: image classification, litter-density regression, instance segmentation, and semantic segmentation, enabling multi-task and cross-task benchmarking without repeated labeling effort. Existing waste-detection datasets such as TrashNet, TACO, UAVVaste, and TrashCan are ground-level, underwater, or single-task; none target a freshwater lake surface from the air. AquaPlasticWaste 2026 fills this gap, offering a realistic, class-imbalanced, small-object benchmark relevant to environmental monitoring, lake-conservation planning, and edge-deployable UAV vision systems.