CE-PeopleSeg: Real-Time People Segmentation with 10% CPU Usage for Video Conference

Abstract

Nowadays, video conference solutions are widely adopted for companies, education, and government. People segmentation is crucial for supporting virtual back-ground, an essential video conference function to protect users’ privacy. This paper demonstrated a people segmentation framework called CE-PeopleSeg, which employed an efficient segmentation method, structural pruning, and dynamic frame skipping techniques, leading to a fast inference speed on CPU. Our extensive experiments show that the proposed CE-PeopleSeg can achieve a high prediction mIoU of 87.9% on Supervised People Dataset while reaching a real-time inference speed of 32.40 fps on CPU with very low usage of 10%. Our code would be released at https://github.com/geekJZY/EfficientPeopleSeg.git.

Cite

Text

Jiang et al. "CE-PeopleSeg: Real-Time People Segmentation with 10% CPU Usage for Video Conference." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00102

Markdown

[Jiang et al. "CE-PeopleSeg: Real-Time People Segmentation with 10% CPU Usage for Video Conference." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/jiang2021cvprw-cepeopleseg/) doi:10.1109/CVPRW53098.2021.00102

BibTeX

@inproceedings{jiang2021cvprw-cepeopleseg,
  title     = {{CE-PeopleSeg: Real-Time People Segmentation with 10% CPU Usage for Video Conference}},
  author    = {Jiang, Ziyu and He, Zhenhua and Huang, Xueqin and Yang, Zibin and Tan, Pearl},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {914-922},
  doi       = {10.1109/CVPRW53098.2021.00102},
  url       = {https://mlanthology.org/cvprw/2021/jiang2021cvprw-cepeopleseg/}
}