Skip to main content

Jakarto datasets containing realworld 3d data from lidar sensors.

Project description

Jakarto datasets for 3d detection challenge of urban assets

Build Status Code coverage License PyPI version GitHub stars

We built that python API to share some real-world 3d lidar datasets of urban assets. We hope to help some of you to develop and test algorithms about 3d lidar processing.

jakarto car detection

Those datasets have been gathered with the Jakarto truck. jakarto truck

Installation

This API requires python 3.6+.

pip install jakarto-datasets

Usage

from jakarto_datasets.datasets.storm_drains import StormDrainsDataset

# Load dataset
storm_drains_2019 = StormDrainsDataset()

for data in storm_drains_2019.training_set:
    coordinates = data.get_coordinates_data()
    lidar_data = data.get_lidar_data()

    label = data.get_label_lidar_data()

    print(data)
    print(coordinates.shape)
    print(lidar_data.shape)
    print(label.shape)

    print(lidar_data['intensity'])

Datasets

datasets year 3d lidar label raster mask len(training_set) len(testing_set) examples description
storm drains 2019 :heavy_check_mark: :heavy_check_mark: :heavy_check_mark: :heavy_check_mark: 223 150 see examples see details

Benchmarks

We will be more than happy to share your experiments.

datasets title authors links description
storm drains 2019 balanced random forest Jakarto team link Use a deadly simple balanced random forest to classify each point from lidar data. Although it doesn't use spatial information, it allowed Jakarto to detect ~25% of storm drains. Those storm drains will be added to the Jakarto storm drains 2020 dataset.
... ... ... ...

Citation

If you find this work useful and wish to refer to, please consider the following BibTeX entry:

@MISC{jakarto_datasets,
    author = {Loic Messal and Cedric Pelletier and {Jakarto Cartographie 3d team}},
    title = {Jakarto datasets},
    year = {2019},
    howpublished={\url{https://github.com/jakarto3d/jakarto_datasets}}
}

A github star may also help.

Contact

If you want to email us, please send an email to contact@jakarto.com.

License

This project is licensed under the terms of the MIT license. (see LICENSE.txt file for details).

Project details


Release history Release notifications

This version

0.1.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for jakarto-datasets, version 0.1.0
Filename, size File type Python version Upload date Hashes
Filename, size jakarto_datasets-0.1.0-py3-none-any.whl (9.7 kB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size jakarto_datasets-0.1.0.tar.gz (7.0 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page