Groningen Dataset for Floating Litter Detection

Dataset

This dataset contains the data used for the publication:

Jia, T., de Vries, R., Kapelan, Z., van Emmerik, T. H., & Taormina, R. (2024). Detecting floating litter in freshwater bodies with semi-supervised deep learning. Water Research, 266, 122405. https://doi.org/10.1016/j.watres.2024.122405

The Groningen dataset is for detecting floating litter with computer vision. We conducted several experiments in a canal in Groningen, the Netherlands, in 2023. We captured data employing a security cameras (Obscape HQ time-lapse), mounted on a bridge at a height of 4m. We recorded images with a time-lapse recording (1 image/6 sec). The image resolution is 2592*1944. This dataset consists of 63 RGB images. We manually labeled the litter items in these images with bounding boxes, resulting in a total number of 383 annotations.

The 63 images are stored in the images.zip file, the annotations are stored in the labels_txt.zip file, and the class of the annotation (i.e., litter) is stored in the classes.txt file. 

Cite this dataset

If you use this dataset for a publication, please cite the paper. Here is a BibTeX entry:

@article{jia2024detecting,
  title={Detecting floating litter in freshwater bodies with semi-supervised deep learning},
  author={Jia, Tianlong and de Vries, Rinze and Kapelan, Zoran and van Emmerik, Tim HM and Taormina, Riccardo},
  journal={Water Research},
  volume={266},
  pages={122405},
  year={2024},
  publisher={Elsevier}
}