Hardware Architecture for High-Accuracy Real-Time Pedestrian Detection with CoHOG Features

Abstract

Co-occurrence histograms of oriented gradients (CoHOG) is a powerful feature descriptor for pedestrian detection. However, its calculation cost is large because the feature vector for the CoHOG descriptor is very high-dimensional. In this paper, in order to achieve real-time detection on embedded systems, we propose a novel hardware architecture for the CoHOG feature extraction. Our architecture exploits high degree of fine-grained parallelism and adopts an efficient histogram generator combined with a linear SVM classifier. The proposed architecture is implemented on a Xilinx Virtex-5 FPGA and it achieves real-time pedestrian detection on 38 fps 320×240 video. That is more than 100 times faster than the execution on a state-of-the-art Intel CPU.

Cite

Text

Hiromoto and Miyamoto. "Hardware Architecture for High-Accuracy Real-Time Pedestrian Detection with CoHOG Features." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457609

Markdown

[Hiromoto and Miyamoto. "Hardware Architecture for High-Accuracy Real-Time Pedestrian Detection with CoHOG Features." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/hiromoto2009iccvw-hardware/) doi:10.1109/ICCVW.2009.5457609

BibTeX

@inproceedings{hiromoto2009iccvw-hardware,
  title     = {{Hardware Architecture for High-Accuracy Real-Time Pedestrian Detection with CoHOG Features}},
  author    = {Hiromoto, Masayuki and Miyamoto, Ryusuke},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {894-899},
  doi       = {10.1109/ICCVW.2009.5457609},
  url       = {https://mlanthology.org/iccvw/2009/hiromoto2009iccvw-hardware/}
}