In-Vehicle Occupancy Detection with Convolutional Networks on Thermal Images

Farzan Erlik Nowruzi, Wassim A. El Ahmar, Robert Laganière, Amir H. Ghods

CVPRW 2019 pp. 941-948

doi:10.1109/CVPRW.2019.00124 /cvprw/2019/nowruzi2019cvprw-invehicle/

Abstract

Counting people is a growing field of interest for researchers in recent years. In-vehicle passenger counting is an interesting problem in this domain that has several applications including High Occupancy Vehicle (HOV) lanes. In this paper, present a new in-vehicle thermal image dataset. We propose a tiny convolutional model to count on-board passengers and compare it to well known methods. We show that our model surpasses state-of-the-art methods in classification and has comparable performance in detection. Moreover, our model outperforms the state-of-the-art architectures in terms of speed, making it suitable for deployment on embedded platforms. We present the results of multiple deep learning models and thoroughly analyze them.

CVPRW Semantic Scholar

Cite

Text

Nowruzi et al. "In-Vehicle Occupancy Detection with Convolutional Networks on Thermal Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00124

Markdown

[Nowruzi et al. "In-Vehicle Occupancy Detection with Convolutional Networks on Thermal Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/nowruzi2019cvprw-invehicle/) doi:10.1109/CVPRW.2019.00124

BibTeX

@inproceedings{nowruzi2019cvprw-invehicle,
  title     = {{In-Vehicle Occupancy Detection with Convolutional Networks on Thermal Images}},
  author    = {Nowruzi, Farzan Erlik and El Ahmar, Wassim A. and Laganière, Robert and Ghods, Amir H.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {941-948},
  doi       = {10.1109/CVPRW.2019.00124},
  url       = {https://mlanthology.org/cvprw/2019/nowruzi2019cvprw-invehicle/}
}