ML Anthology

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients

Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng, Shai Avidan
CVPR 2006 pp. 1491-1498
doi:10.1109/CVPR.2006.119 /cvpr/2006/zhu2006cvpr-fast/

Abstract

We integrate the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system. The features used in our system are HoGs of variable-size blocks that capture salient features of humans automatically. Using AdaBoost for feature selection, we identify the appropriate set of blocks, from a large set of possible blocks. In our system, we use the integral image representation and a rejection cascade which significantly speed up the computation. For a 320 × 250 image, the system can process 5 to 30 frames per second depending on the density in which we scan the image, while maintaining an accuracy level similar to existing methods. © 2006 IEEE.

CVPR Semantic Scholar

Cite

Text

Zhu et al. "Fast Human Detection Using a Cascade of Histograms of Oriented Gradients." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.119

Markdown

[Zhu et al. "Fast Human Detection Using a Cascade of Histograms of Oriented Gradients." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/zhu2006cvpr-fast/) doi:10.1109/CVPR.2006.119

BibTeX

@inproceedings{zhu2006cvpr-fast,
  title     = {{Fast Human Detection Using a Cascade of Histograms of Oriented Gradients}},
  author    = {Zhu, Qiang and Yeh, Mei-Chen and Cheng, Kwang-Ting and Avidan, Shai},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {1491-1498},
  doi       = {10.1109/CVPR.2006.119},
  url       = {https://mlanthology.org/cvpr/2006/zhu2006cvpr-fast/}
}