New features and insights for pedestrian detection

@article{Walk2010NewFA,
  title={New features and insights for pedestrian detection},
  author={Stefan Walk and Nikodem Majer and Konrad Schindler and Bernt Schiele},
  journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  year={2010},
  pages={1030-1037}
}
Despite impressive progress in people detection the performance on challenging datasets like Caltech Pedestrians or TUD-Brussels is still unsatisfactory. In this work we show that motion features derived from optic flow yield substantial improvements on image sequences, if implemented correctly — even in the case of low-quality video and consequently degraded flow fields. Furthermore, we introduce a new feature, self-similarity on color channels, which consistently improves detection… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 374 CITATIONS

Efficient Pedestrian Detection in Urban Traffic Scenes

VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

How to Improve the Quality of Pedestrian Detection Using the Priori Knowledge

  • 2013 IEEE 13th International Conference on Data Mining Workshops
  • 2013
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Local Transform Features and Hybridization for Accurate Face and Human Detection

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Differential Features for Pedestrian Detection: A Taylor Series Perspective

  • IEEE Transactions on Intelligent Transportation Systems
  • 2019
VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

LBP Channels for Pedestrian Detection

  • 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Pedestrian Detection Using Visual Saliency and Deep Learning

VIEW 8 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Pedestrian detection with motion features via two-stream ConvNets

  • IPSJ Transactions on Computer Vision and Applications
  • 2018
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Too Far to See? Not Really!—Pedestrian Detection With Scale-Aware Localization Policy

  • IEEE Transactions on Image Processing
  • 2017
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2010
2019

CITATION STATISTICS

  • 66 Highly Influenced Citations

  • Averaged 26 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

Classification using intersection kernel support vector machines is efficient

  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Histograms of oriented gradients for human detection

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

A discriminatively trained, multiscale, deformable part model

  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Detecting pedestrians using patterns of motion and appearance

  • Proceedings Ninth IEEE International Conference on Computer Vision
  • 2003
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

An HOG-LBP human detector with partial occlusion handling

  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
VIEW 3 EXCERPTS