Where Is the Rat? Tracking in Low Contrast Thermographic Images

Abstract

This paper presents a method to track an animal in low-contrast thermographic images in order to obtain its body temperature. This work was done in the context of the study of atypical febrile seizures. To solve this tracking problem, we propose a method based on morphological operations on the area to track using regions resulting from consec-utive frame differences. A Gaussian model is then used to classify tracked area pixels into animal and background pix-els to further remove outliers. The temperature of the ani-mal is taken as the mean of the tracked area. Experimental results show that we obtain, in general, temperature esti-mation within 1oC from ground-truth for videos as long as 16000 frames. 1.

Cite

Text

Bilodeau et al. "Where Is the Rat? Tracking in Low Contrast Thermographic Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011. doi:10.1109/CVPRW.2011.5981685

Markdown

[Bilodeau et al. "Where Is the Rat? Tracking in Low Contrast Thermographic Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011.](https://mlanthology.org/cvprw/2011/bilodeau2011cvprw-rat/) doi:10.1109/CVPRW.2011.5981685

BibTeX

@inproceedings{bilodeau2011cvprw-rat,
  title     = {{Where Is the Rat? Tracking in Low Contrast Thermographic Images}},
  author    = {Bilodeau, Guillaume-Alexandre and Ghali, Ramla and Desgent, Sébastien and Langlois, Pierre and Farah, Rana and St-Onge, Pier-Luc and Duss, Sandra and Carmant, Lionel},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2011},
  pages     = {55-60},
  doi       = {10.1109/CVPRW.2011.5981685},
  url       = {https://mlanthology.org/cvprw/2011/bilodeau2011cvprw-rat/}
}