ALTO

A Large-Scale Dataset for UAV Visual Place Recognition and Localization

Background and Major Contributions

We present the ALTO dataset, a vision-focused dataset for developing and benchmarking Visual Place Recognition and Localization methods for Unmanned Aerial Vehicles. The dataset comprises two long (approximately 150km and 260km) trajectories flown by helicopter over Ohio and Pennsylvania. It includes high-precision GPS ground truth location data, high-precision IMU readings, laser altimeter readings, and RGB downward-facing camera imagery. In addition, we provide reference imagery over the flight paths, which makes this dataset suitable for VPR bench-marking and other tasks common in Localization, such as image registration and visual odometry. To the author’s knowledge, this is the largest real-world aerial-vehicle dataset. Our dataset is available at ALTO.

Datasets of UAV datasets from Pittsburgh to Ohio.

Publications

BibTeX:

@article{cisneros2022alto,
  title={ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and Localization},
  author={Cisneros, Ivan and Yin, Peng and Zhang, Ji and Choset, Howie and Scherer, Sebastian},
  journal={arXiv preprint arXiv:2207.12317},
  year={2022},
  url={https://github.com/MetaSLAM/ALTO}
}

Contact

  • Peng Yin: (hitmaxtom [at] gmail [dot] com)