Corpus ID: 214794888

Extraction and Assessment of Naturalistic Human Driving Trajectories from Infrastructure Camera and Radar Sensors

@article{Notz2020ExtractionAA,
  title={Extraction and Assessment of Naturalistic Human Driving Trajectories from Infrastructure Camera and Radar Sensors},
  author={Dominik Notz and Felix Becker and Thomas K{\"u}hbeck and Daniel Watzenig},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.01288}
}
  • Dominik Notz, Felix Becker, +1 author Daniel Watzenig
  • Published 2020
  • Engineering, Computer Science
  • ArXiv
  • Collecting realistic driving trajectories is crucial for training machine learning models that imitate human driving behavior. Most of today's autonomous driving datasets contain only a few trajectories per location and are recorded with test vehicles that are cautiously driven by trained drivers. In particular in interactive scenarios such as highway merges, the test driver's behavior significantly influences other vehicles. This influence prevents recording the whole traffic space of human… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    nuScenes: A multimodal dataset for autonomous driving

    VIEW 3 EXCERPTS

    Learning Traffic Behaviors by Extracting Vehicle Trajectories from Online Video Streams

    VIEW 1 EXCERPT

    A Survey of Vision-Based Traffic Monitoring of Road Intersections

    VIEW 2 EXCERPTS

    The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems

    VIEW 2 EXCERPTS

    Argoverse: 3D Tracking and Forecasting With Rich Maps

    VIEW 3 EXCERPTS

    Methods for Improving the Accuracy of the Virtual Assessment of Autonomous Driving

    VIEW 3 EXCERPTS

    Learning From Demonstration in the Wild

    VIEW 2 EXCERPTS

    Extending IOU Based Multi-Object Tracking by Visual Information

    VIEW 1 EXCERPT