New dataset targets municipal waste detection in urban areas

Researchers have introduced the Maltese Domestic Waste Dataset (MDWD), a new street-level benchmark designed for municipal solid waste detection in dense urban environments. The dataset contains nearly 3,700 images with over 11,000 annotated instances across five waste categories, addressing a gap in existing resources that often focus on individual litter or aerial imagery. A benchmark evaluation using various YOLO models and RF-DETR-M showed that RF-DETR-M achieved high performance, indicating the dataset's utility for training both compact and transformer-based detectors. AI

IMPACT This dataset could advance research in automated waste management and urban monitoring systems.

RANK_REASON The item describes a new academic dataset and benchmark for a specific computer vision task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• computer vision
• Hugging Face
• Malta
• Maltese Domestic Waste Dataset
• MDWD
• RF-DETR-M
• YOLO

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →