Skip to content

Agricultural Dataset with Static and Moving Obstacles

Notifications You must be signed in to change notification settings

mikkelkh/FieldSAFE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FieldSAFE - Dataset for Obstacle Detection in Agriculture

Watch the video

This repository contains the necessary software for utilizing the FieldSAFE dataset. Software and example usage scripts are available in the folder "ros". Further, ground truth GPS annotations for all static and dynamic obstacles are contained in the folder "ground_truth".

For more information, visit the FieldSAFE website: https://vision.eng.au.dk/fieldsafe/

Citation

If you use this dataset in your research or elsewhere, please cite/reference the following paper:

FieldSAFE: Dataset for Obstacle Detection in Agriculture

@article{kragh2017fieldsafe,
  title={FieldSAFE: Dataset for Obstacle Detection in Agriculture},
  author={Kragh, Mikkel Fly and Christiansen, Peter and Laursen, Morten Stigaard and Larsen, Morten and Steen, Kim Arild and Green, Ole and Karstoft, Henrik and J{\o}rgensen, Rasmus Nyholm},
  journal={arXiv preprint arXiv:1709.03526},
  year={2017}
}

Installation Instructions

The FieldSAFE dataset and software has been tested with Ubuntu 16.04 and ROS Kinetic, but may work with other Linux distributions and newer ROS distributions. Below, installations instructions for all necessary dependencies are given.

  • Install ROS Kinetic on Ubuntu 16.04 (Desktop-Full Install)

    https://wiki.ros.org/kinetic/Installation/Ubuntu

  • Install the following additional packages:

    sudo apt-get install ros-kinetic-robot-localization 
    sudo apt-get install ros-kinetic-geographic-msgs
    sudo apt-get install libpcap-dev
  • Clone and build this repository

    git clone https://github.com/mikkelkh/FieldSAFE
    cd FieldSAFE
    git submodule update --init --recursive
    cd ros
    catkin_make
  • Environment Setup

    source devel/setup.bash
  • Download a 1 minute example bag with sensor data:

    2016-10-25-11-41-21_example.bag

  • Run the original demo

    roslaunch demo demo.launch file:=/path/to/2016-10-25-11-41-21_example.bag

    or this updated demo by @tambetm including visualization of ground truth obstacles:

    roslaunch demo demo_markers.launch file:=/path/to/2016-10-25-11-41-21_example.bag
  • Download more data from:

    https://vision.eng.au.dk/fieldsafe/

About

Agricultural Dataset with Static and Moving Obstacles

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published