TACO is a growing image dataset of waste in the wild. It contains images of litter taken under diverse environments: woods, roads and beaches. These images are manually labeled and segmented according to a hierarchical taxonomy to train and evaluate object detection algorithms. Currently, images are hosted on Flickr and we are developing a server to collect more images and annotations @ tacodataset.org

If you use this dataset and API in a publication, please cite us:  

@misc{Taco19,
  author       = {Pedro F. Proença and Pedro Simões},
  title        = {TACO: Trash Annotations in Context Dataset},
  year         = 2019,
  doi          = {10.5281/zenodo.3242156},
  url          = {http://tacodataset.org}
}

For convenience, annotations are provided in COCO format. TACO is still relatively small, but it is growing. Stay tuned!

To download the dataset images simply issue

python3 download.py

Our API contains a notebook demo.pynb to inspect the dataset and visualize annotations. To use demo.pynb, you require:

• jupyter
• seaborn
• python cocoapi

The implementation of Mask-RCNN by Matterport is included in /detector with a few modifications. Requirements are the same. For usage instructions, check detector/detector.py.

n.b. Most of the original classes of TACO have very few annotations, therefore these must be either left out or merged together. Depending on the problem, detector/taco_config contains several class maps to target classes, which maintain the most dominant classes, e.g., Can, Bottles and Plastic bags