ML Anthology

Pedestrian Detection at 100 Frames per Second

Rodrigo Benenson, Markus Mathias, Radu Timofte, Luc Van Gool
CVPR 2012 pp. 2903-2910
doi:10.1109/CVPR.2012.6248017 /cvpr/2012/benenson2012cvpr-pedestrian/

Abstract

We present a new pedestrian detector that improves both in speed and quality over state-of-the-art. By efficiently handling different scales and transferring computation from test time to training time, detection speed is improved. When processing monocular images, our system provides high quality detections at 50 fps. We also propose a new method for exploiting geometric context extracted from stereo images. On a single CPU+GPU desktop machine, we reach 125 fps, when processing street scenes, from rectified input to detections output.

CVPR Semantic Scholar

Cite

Text

Benenson et al. "Pedestrian Detection at 100 Frames per Second." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6248017

Markdown

[Benenson et al. "Pedestrian Detection at 100 Frames per Second." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/benenson2012cvpr-pedestrian/) doi:10.1109/CVPR.2012.6248017

BibTeX

@inproceedings{benenson2012cvpr-pedestrian,
  title     = {{Pedestrian Detection at 100 Frames per Second}},
  author    = {Benenson, Rodrigo and Mathias, Markus and Timofte, Radu and Van Gool, Luc},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2903-2910},
  doi       = {10.1109/CVPR.2012.6248017},
  url       = {https://mlanthology.org/cvpr/2012/benenson2012cvpr-pedestrian/}
}