Advanced search
2 files | 16.85 MB Add to list

Indoor person identification using a low-power FMCW radar

Author
Organization
Abstract
Contemporary surveillance systems mainly use video cameras as their primary sensor. However, video cameras possess fundamental deficiencies, such as the inability to handle low-light environments, poor weather conditions, and concealing clothing. In contrast, radar devices are able to sense in pitchdark environments and to see through walls. In this paper, we investigate the use of micro-Doppler (MD) signatures retrieved from a low-power radar device to identify a set of persons based on their gait characteristics. To that end, we propose a robust feature learning approach based on deep convolutional neural networks. Given that we aim at providing a solution for a real-world problem, people are allowed to walk around freely in two different rooms. In this setting, the IDentification with Radar data data set is constructed and published, consisting of 150 min of annotated MD data equally spread over five targets. Through experiments, we investigate the effectiveness of both the Doppler and time dimension, showing that our approach achieves a classification error rate of 24.70% on the validation set and 21.54% on the test set for the five targets used. When experimenting with larger time windows, we are able to further lower the error rate.
Keywords
MICRO-DOPPLER, CLASSIFICATION, Convolutional neural network (CNN), feature learning, gait, classification, indoor sensing, low-power radar, micro-Doppler (MD), person identification

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 11.42 MB
  • 7180 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 5.43 MB

Citation

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

MLA
Vandersmissen, Baptist, Nicolas Knudde, Azarakhsh Jalalvand, et al. “Indoor Person Identification Using a Low-power FMCW Radar.” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 56.7 (2018): 3941–3952. Print.
APA
Vandersmissen, B., Knudde, N., Jalalvand, A., Couckuyt, I., Bourdoux, A., De Neve, W., & Dhaene, T. (2018). Indoor person identification using a low-power FMCW radar. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 56(7), 3941–3952.
Chicago author-date
Vandersmissen, Baptist, Nicolas Knudde, Azarakhsh Jalalvand, Ivo Couckuyt, Andre Bourdoux, Wesley De Neve, and Tom Dhaene. 2018. “Indoor Person Identification Using a Low-power FMCW Radar.” Ieee Transactions on Geoscience and Remote Sensing 56 (7): 3941–3952.
Chicago author-date (all authors)
Vandersmissen, Baptist, Nicolas Knudde, Azarakhsh Jalalvand, Ivo Couckuyt, Andre Bourdoux, Wesley De Neve, and Tom Dhaene. 2018. “Indoor Person Identification Using a Low-power FMCW Radar.” Ieee Transactions on Geoscience and Remote Sensing 56 (7): 3941–3952.
Vancouver
1.
Vandersmissen B, Knudde N, Jalalvand A, Couckuyt I, Bourdoux A, De Neve W, et al. Indoor person identification using a low-power FMCW radar. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. Piscataway: Ieee-inst Electrical Electronics Engineers Inc; 2018;56(7):3941–52.
IEEE
[1]
B. Vandersmissen et al., “Indoor person identification using a low-power FMCW radar,” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 56, no. 7, pp. 3941–3952, 2018.
@article{8572862,
  abstract     = {{Contemporary surveillance systems mainly use video cameras as their primary sensor. However, video cameras possess fundamental deficiencies, such as the inability to handle low-light environments, poor weather conditions, and concealing clothing. In contrast, radar devices are able to sense in pitchdark environments and to see through walls. In this paper, we investigate the use of micro-Doppler (MD) signatures retrieved from a low-power radar device to identify a set of persons based on their gait characteristics. To that end, we propose a robust feature learning approach based on deep convolutional neural networks. Given that we aim at providing a solution for a real-world problem, people are allowed to walk around freely in two different rooms. In this setting, the IDentification with Radar data data set is constructed and published, consisting of 150 min of annotated MD data equally spread over five targets. Through experiments, we investigate the effectiveness of both the Doppler and time dimension, showing that our approach achieves a classification error rate of 24.70% on the validation set and 21.54% on the test set for the five targets used. When experimenting with larger time windows, we are able to further lower the error rate.}},
  author       = {{Vandersmissen, Baptist and Knudde, Nicolas and Jalalvand, Azarakhsh and Couckuyt, Ivo and Bourdoux, Andre and De Neve, Wesley and Dhaene, Tom}},
  issn         = {{0196-2892}},
  journal      = {{IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING}},
  keywords     = {{MICRO-DOPPLER,CLASSIFICATION,Convolutional neural network (CNN),feature learning,gait,classification,indoor sensing,low-power radar,micro-Doppler (MD),person identification}},
  language     = {{eng}},
  number       = {{7}},
  pages        = {{3941--3952}},
  publisher    = {{Ieee-inst Electrical Electronics Engineers Inc}},
  title        = {{Indoor person identification using a low-power FMCW radar}},
  url          = {{http://dx.doi.org/10.1109/TGRS.2018.2816812}},
  volume       = {{56}},
  year         = {{2018}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: