You're currently viewing an old version of this dataset. To see the current version, click here.

i.c.sens Stereo Image Vehicle Dataset

The i.c.sens Stereo Image Vehicle Dataset is a dataset for vehicle detection, pose estimation, and reconstruction. It consists of street-level stereo images and delivers reference information for the 3D pose and shape of vehicles being visible in the scene. For the acquisition of the data, a vehicle was equipped with a synchronised and calibrated stereo camera rig and stereoscopic image sequences were recorded in urban environments in the city of Hanover for the generation of the data set. Vehicle CAD models are manually fitted to the observations and are provided as reference data.

Examples of the reference CAD models can be seen in the subsequent figure: Reference CAD Models

Details on the data and its usage can be found in the provided documentation file.

Related Publications:

  • Coenen, M. and Rottensteiner, F., 2019: Probabilistic Vehicle Reconstruction Using a Multi-Task CNN. In: IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 822-831. https://ieeexplore.ieee.org/document/9022056

  • Schön, S., Brenner, C., Alkhatib, H., Coenen, M., Dbouk, H., Garcia-Fernandez, N., Fischer, C., Heipke, C., Lohmann, K., Neumann, I., Nguyen, U., Paffenholz, J.-A., Peters, T., Rottensteiner, F., Schachtschneider, J., Sester, M., Sun, L., Vogel, S., Voges, R. and Wagner, B., 2018: Integrity and Collaboration in Dynamic Sensor Networks. Sensors 18(7), pp. 2400-2421. https://www.mdpi.com/1424-8220/18/7/2400

Data and Resources

Cite this as

Max Coenen (2020). Dataset: i.c.sens Stereo Image Vehicle Dataset. https://doi.org/10.25835/0078519

DOI retrieved: July 14, 2020

Additional Info

Field Value
Imported on October 14, 2021
Last update October 14, 2021
License CC-BY-NC-3.0
Source https://data.uni-hannover.de/dataset/icsens-stereo-image-vehicle-dataset
Author Max Coenen
Author Email Max Coenen
Source Creation 15 June, 2020, 15:21 PM (UTC+0000)
Source Modified 14 September, 2020, 11:17 AM (UTC+0000)