Published April 5, 2023 | Version 1.0
Dataset Open

Pest Sticky Traps: a dataset for Whitefly Pest Population Density Estimation in Chromotropic Sticky Traps

  • 1. Institute of Information Science and Technologies, National Research Council, Pisa, Italy
  • 2. Department of Agriculture, Food and Environment of the University of Pisa, Italy
  • 3. Department of Computer Science of the University of Pisa, Italy

Contributors

Contact person:

Data collector:

  • 1. Institute of Information Science and Technologies, National Research Council, Pisa, Italy
  • 2. Department of Agriculture, Food and Environment of the University of Pisa, Italy

Description

The dataset

The Pest Sticky Traps (PST) dataset is a collection of yellow chromotropic sticky trap pictures specifically designed for training/testing deep learning models to automatically count insects and estimate pest populations.

Images were manually annotated by some experts of the Department of Agriculture, Food and Environment of the University of Pisa (Italy) by putting a dot over the centroids of each identified insect. Specifically, we labeled insects as belonging to the category “whitefly” considering two different species, i.e., the sweet potato whitefly (Bemisia tabaci) (Gennadius) and the greenhouse whitefly (Trialeurodes vaporariorum) (Westwood).

The dataset comprises two subsets:
- a subset we suggest using for the training/validation phases (contained in the `train/` folder)
- a subset we suggest using for the test phase (contained in the `test/` folder)

Annotations of the two subsets are contained in `train/annotations.csv` and `test/annotations.csv`, respectively. They have the following columns:
- *imageName* - filename of the image containing the whiteflies,
- *X,Y* - 2D coordinates of the whitefly in the image space,
- *class* - class index of the insect (always 0 in this dataset).

 

Citing our work

If you found this dataset useful, please cite the following paper

@inproceedings{CIAMPI2023102384,
title = {A deep learning-based pipeline for whitefly pest abundance estimation on chromotropic sticky traps},
   journal = {Ecological Informatics},
volume = {78},
pages = {102384},
year = {2023},
issn = {1574-9541},     doi = {10.1016/j.ecoinf.2023.102384},   url = {https://www.sciencedirect.com/science/article/pii/S1574954123004132},   year = 2023,     author = {Luca Ciampi and Valeria Zeni and Luca Incrocci and Angelo Canale and Giovanni Benelli and Fabrizio Falchi and Giuseppe Amato and Stefano Chessa}, }

and this Zenodo Dataset

@dataset{ciampi_2023_7801239,
    author = {Luca Ciampi and Valeria Zeni and Luca Incrocci and Angelo Canale and Giovanni Benelli and Fabrizio Falchi and Giuseppe Amato and Stefano Chessa},
    title = {Pest Sticky Traps: a dataset for Whitefly Pest Population Density Estimation in Chromotropic Sticky Traps}},
    month = apr,
    year = 2023,
    publisher = {Zenodo},
    version = {1.0.0},
    doi = {10.5281/zenodo.7801239},
    url = {https://doi.org/10.5281/zenodo.6560823}
}

 

Contact Information

If you would like further information about the dataset or if you experience any issues downloading files, please contact us at luca.ciampi@isti.cnr.it

 

 

Files

pest-sticky-traps.zip

Files (144.0 MB)

Name Size Download all
md5:43e6f6e7e2ac6c415983de4d47af8f52
144.0 MB Preview Download

Additional details

Funding

European Commission
AI4Media – A European Excellence Centre for Media, Society and Democracy 951911