Advanced search
1 file | 329.52 KB Add to list

Automatic annotation of pedestrians in thermal images using background/foreground segmentation for training deep neural networks

Zuhaib Ahmed Shaikh (UGent) , Gianni Allebosch (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
Deep Neural Networks for object detection have become of significant interest with the substantial improvement in their efficiency and increase in their applications. However, training such a network requires a large annotated dataset, which is very expensive in term of time and human effort. In this context, several automatic image annotation solutions have been proposed which are dependent on rich visual features and thus suitable for color images only. On the other hand, recent experiments have proven that color cameras alone are not enough for pedestrian related applications and there is a need to use other visual sensors as well, such as thermal cameras. In this paper, we propose an automatic image annotation technique for pedestrian detection in thermal images using an adaptive background/foreground estimation model to train Faster-RCNN. The results presented in this paper, obtained through longterm experiments demonstrate the efficacy of our technique. The results also show that our proposed technique is be very useful to generate image annotations automatically and to train a deep neural network without having a manually annotated dataset for cameras with different modalities.
Keywords
Auto-Image Annotation, Adaptive Background/Foreground estimation, Faster-RCNN

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 329.52 KB

Citation

Please use this url to cite or link to this publication:

MLA
Ahmed Shaikh, Zuhaib, et al. “Automatic Annotation of Pedestrians in Thermal Images Using Background/Foreground Segmentation for Training Deep Neural Networks.” 2020 IEEE Symposium Series on Computational Intelligence (SSCI), IEEE, 2020, pp. 1444–51, doi:10.1109/ssci47803.2020.9308531.
APA
Ahmed Shaikh, Z., Allebosch, G., Veelaert, P., & Philips, W. (2020). Automatic annotation of pedestrians in thermal images using background/foreground segmentation for training deep neural networks. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1444–1451). Canberra, Australia: IEEE. https://doi.org/10.1109/ssci47803.2020.9308531
Chicago author-date
Ahmed Shaikh, Zuhaib, Gianni Allebosch, Peter Veelaert, and Wilfried Philips. 2020. “Automatic Annotation of Pedestrians in Thermal Images Using Background/Foreground Segmentation for Training Deep Neural Networks.” In 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 1444–51. IEEE. https://doi.org/10.1109/ssci47803.2020.9308531.
Chicago author-date (all authors)
Ahmed Shaikh, Zuhaib, Gianni Allebosch, Peter Veelaert, and Wilfried Philips. 2020. “Automatic Annotation of Pedestrians in Thermal Images Using Background/Foreground Segmentation for Training Deep Neural Networks.” In 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 1444–1451. IEEE. doi:10.1109/ssci47803.2020.9308531.
Vancouver
1.
Ahmed Shaikh Z, Allebosch G, Veelaert P, Philips W. Automatic annotation of pedestrians in thermal images using background/foreground segmentation for training deep neural networks. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE; 2020. p. 1444–51.
IEEE
[1]
Z. Ahmed Shaikh, G. Allebosch, P. Veelaert, and W. Philips, “Automatic annotation of pedestrians in thermal images using background/foreground segmentation for training deep neural networks,” in 2020 IEEE Symposium Series on Computational Intelligence (SSCI), Canberra, Australia, 2020, pp. 1444–1451.
@inproceedings{8691354,
  abstract     = {{Deep Neural Networks for object detection have become of significant interest with the substantial improvement in their efficiency and increase in their applications. However, training such a network requires a large annotated dataset, which is very expensive in term of time and human effort. In this context, several automatic image annotation solutions have been proposed which are dependent on rich visual features and thus suitable for color images only. On the other hand, recent experiments have proven that color cameras alone are not enough for pedestrian related applications and there is a need to use other visual sensors as well, such as thermal cameras. In this paper, we propose an automatic image annotation technique for pedestrian detection in thermal images using an adaptive background/foreground estimation model to train Faster-RCNN. The results presented in this paper, obtained through longterm experiments demonstrate the efficacy of our technique. The results also show that our proposed technique is be very useful to generate image annotations automatically and to train a deep neural network without having a manually annotated dataset for cameras with different modalities.}},
  author       = {{Ahmed Shaikh, Zuhaib and Allebosch, Gianni and Veelaert, Peter and Philips, Wilfried}},
  booktitle    = {{2020 IEEE Symposium Series on Computational Intelligence (SSCI)}},
  isbn         = {{9781728125473}},
  keywords     = {{Auto-Image Annotation,Adaptive Background/Foreground estimation,Faster-RCNN}},
  language     = {{eng}},
  location     = {{Canberra, Australia}},
  pages        = {{1444--1451}},
  publisher    = {{IEEE}},
  title        = {{Automatic annotation of pedestrians in thermal images using background/foreground segmentation for training deep neural networks}},
  url          = {{http://dx.doi.org/10.1109/ssci47803.2020.9308531}},
  year         = {{2020}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: