Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Dec 3:40:107667.
doi: 10.1016/j.dib.2021.107667. eCollection 2022 Feb.

Brno urban dataset: Winter extension

Adam Ligocki  1 , Ales Jelinek  1 , Ludek Zalud  1
Affiliations

Brno urban dataset: Winter extension

Adam Ligocki et al. Data Brief. .

Abstract

This paper presents our latest extension of the Brno Urban Dataset (BUD), the Winter Extension (WE). The dataset contains data from commonly used sensors in the automotive industry, like four RGB and single IR cameras, three 3D LiDARs, differential RTK GNSS receiver with heading estimation, the IMU and FMCW radar. Data from all sensors are precisely timestamped for future offline interpretation and data fusion. The most significant gain of the dataset is the focus on the winter conditions in snow-covered environments. Only a few public datasets deal with these kinds of conditions. We recorded the dataset during February 2021 in Brno, Czechia, when fresh snow covers the entire city and the surrounding countryside. The dataset contains situations from the city center, suburbs, highways as well as the countryside. Overall, the new extension adds three hours of real-life traffic situations from the mid-size city to the existing 10 h of original records. Additionally, we provide the precalculated YOLO neural network object detection annotations for all five cameras for the entire old data and the new ones. The dataset is suitable for developing mapping and navigation algorithms as well as the collision and object detection pipelines. The entire dataset is available as open-source under the MIT license.

Keywords: 3D LiDAR; IMU; IR camera; Multimodal dataset; Navigation data; Neural networks; RGB camera; RTK GNSS.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no known competing financial interests or personal relationships which have or could be perceived to have influenced the work reported in this article.

Figures

Fig 1
Fig. 1
(left) The Atlas sensory framework installed on the roof of the testing car. Data were recorded in the early February of 2021; (right) Detail sensory framework overview. Four RGB cameras (blue), two side Velodyne scanners and single Livox sensor (all gray), GNSS RTK receiver (yellow) with pair of differential antennas (white), Xsens IMU (orange) in the center, and the FMCW radar (red) in the front of the framework.
Fig 2
Fig. 2
Sensors used overview: RGB cameras (top two rows), IR camera (third row), and LiDARs (bottom line - left Velodyne, forward-looking Livox, and right Velodyne scanners).
Fig 3
Fig. 3
Example of neural network precalculated labels for RGB and IR camera data. In total, we provide annotations of approximately 52 h of RGB video (13 h for four cameras) at ten fps and about 13 h of annotated IR video. In total, it makes about 3.2.
Fig 4
Fig. 4
Overview of the most common annotated objects in the RGB and IR domain.
Fig 5
Fig. 5
Visualized trajectories traversed during the BUD Winter Extension recording in Brno, Czech Republic.
See this image and copyright information in PMC

References

    1. Ligocki A., Jelinek A., Zalud L. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) IEEE; 2020. Brno urban dataset-the new data for self-driving agents and mapping tasks; pp. 3284–3290.
    1. Rehder J., Nikolic J., Schneider T., Hinzmann T., Siegwart R. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) IEEE; 2016. Extending kalibr: calibrating the extrinsics of multiple imus and of individual axes; pp. 4304–4311.
    1. Geiger A., Moosmann F., Car O., Schuster B. Proceedings of the IEEE International Conference on Robotics and Automation. IEEE; 2012. Automatic camera and range sensor calibration using a single shot; pp. 3936–3943.
    1. Zalud L., Kocmanova P. Proceedings of the IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) IEEE; 2013. Fusion of the thermal imaging and ccd camera based data for stereo vision visual telepresence; pp. 1–6.
    1. Gao X., Xing G., Roy S., Liu H. Proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers. IEEE; 2019. Experiments with mmwave automotive radar test-bed; pp. 1–6.

LinkOut - more resources