An Evaluation Framework for Stereo-Based Driver Assistance

@inproceedings{Schneider2011AnEF,
  title={An Evaluation Framework for Stereo-Based Driver Assistance},
  author={Nicolai Schneider and Stefan K. Gehrig and David Pfeiffer and Konstantinos A. Banitsas},
  booktitle={Theoretical Foundations of Computer Vision},
  year={2011}
}
The accuracy of stereo algorithms or optical flow methods is commonly assessed by comparing the results against the Middlebury database. However, equivalent data for automotive or robotics applications rarely exist as they are difficult to obtain. As our main contribution, we introduce an evaluation framework tailored for stereo-based driver assistance able to deliver excellent performance measures while circumventing manual label effort. Within this framework one can combine several ways of… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-3 OF 3 CITATIONS

Testing of Advanced Driver Assistance Towards Automated Driving: A Survey and Taxonomy on Existing Approaches and Open Questions

VIEW 2 EXCERPTS
CITES BACKGROUND

Making Bertha See

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 42 REFERENCES

Efficient representation of traffic scenes by means of dynamic stixels

VIEW 10 EXCERPTS

Evaluation of stereo-based scene analysis under real-world conditions

  • N. Schneider
  • Master’s thesis, Brunel University
  • 2011
VIEW 1 EXCERPT

A constricted bundle adjustment parameterization for relative scale estimation in visual odometry

VIEW 1 EXCERPT

Ground truth evaluation of the Stixel representation using laser scanners

VIEW 3 EXCERPTS

Vehicle Tracking and Motion Estimation Based on Stereo Vision Sequences

  • A. Barth
  • PhD thesis, Friedrich-Wilhelms-Universitaet zu Bonn
  • 2010
VIEW 1 EXCERPT

Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme

VIEW 1 EXCERPT