## Article Abstract ------------ We provide a novel challenging dataset that offers a new landscape of testing material for mobile robotics, autonomous driving research, and heavy machine operation. In contrast to common urban structures, we explore an unregulated natural environment to exemplify sub-urban and forest environment. The sequences provide two-natured data where each place is visited in summer and winter conditions. The vehicle used for recording is equipped with a sensor rig that constitutes four RGB cameras, an Inertial Measurement Unit, and a Global Navigation Satellite System receiver. The sensors are synchronized based on non-drifting timestamps. The dataset provides trajectories of varying complexity both for the state of the art visual odometry approaches and visual simultaneous localization and mapping algorithms. ## Suggested Citation ------------ @article{ali_durmush_suominen_yli-hietanen_peltonen_collin_gotchev_2020, title= {FinnForest dataset: A forest landscape for visual SLAM}, volume= {132}, DOI={10.1016/j.robot.2020.103610}, journal= {Robotics and Autonomous Systems}, author= {Ali, Ihtisham and Durmush, Ahmed and Suominen, Olli and Yli-Hietanen, Jari and Peltonen, Sari and Collin, Jussi and Gotchev, Atanas}, year= {2020}, pages= {103610} ## Introductory Video ------------ [](https://youtu.be/bGyEf3zUj-w "Introduction video") ## Dataset Directory ------------  ## Guiding Points ------------ - To start using directly, you can download individual sequences from the RectifiedData in the form of Images or Rosbags e.g. *rectifiedImageFormat* > *dataset_40Hz* > *'desiredSequence'.zip* - The ground truth of the trajectories and calibration information of the cameras is provided in *AllGroundTruths\_and\_Calibration.zip* - The development and evaluation toolkits are packed in *toolkit.zip* - To process from scratch you can download the raw version of data (*RAWData\_40Hz*) which can be processed with the calibration information from *AllGroundTruths\_and\_Calibration.zip* using the development toolkit in *toolkit.zip*. You are encouraged to use other methods to process the data in case better results can be achieved - To start downloading, switch to the **Data tab** above the dataset title. **Note:** We recommend downloading the compressed files separately using a fixed ethernet connection instead of a wireless internet connection. If you face any issue downloading data or if you have any queries, feel free to contact at <ihtisham.ali@tuni.fi>.

2020