The goal of our research is to advance the state of the art in river plastic litter detection. RivPLitter is a large-scale, high-resolution dataset specifically curated to facilitate the development and evaluation of object detection models in complex river environments.
This dataset is made available (upon request) for the academic community to support research in environmental monitoring and plastic pollution mitigation.
The dataset includes 88,860 images with high-resolution 4K imagery, covering various environmental conditions and object classes including plastic, debris, bottles, and bags.