Human Segmentation by Fusing Visible-Light and Thermal Imaginary

Abstract

This paper describes a system for robust segmentation of human in video sequences by fusing the visible-light and thermal imaginary. The system first performs a simple calibration procedure to rectify the two camera views without knowing the cameras' intrinsic characteristics. Then a blob-to-blob homography is learned on-the-fly by estimating the disparity of each blob so that a pixel level registration can be achieved. The multi-modality information is then combined under a two-tier tracking algorithm and a unified background model to attain precise segmentation. Preliminary experimental results shows significant improvements over existing schemes under various difficult scenarios.

Cite

Text

Zhao and Cheung. "Human Segmentation by Fusing Visible-Light and Thermal Imaginary." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457476

Markdown

[Zhao and Cheung. "Human Segmentation by Fusing Visible-Light and Thermal Imaginary." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/zhao2009iccvw-human/) doi:10.1109/ICCVW.2009.5457476

BibTeX

@inproceedings{zhao2009iccvw-human,
  title     = {{Human Segmentation by Fusing Visible-Light and Thermal Imaginary}},
  author    = {Zhao, Jian and Cheung, Sen-Ching S.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {1185-1192},
  doi       = {10.1109/ICCVW.2009.5457476},
  url       = {https://mlanthology.org/iccvw/2009/zhao2009iccvw-human/}
}