Direct tracking from compressive imagers

A proof of concept

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The compressive sensing paradigm holds promise for more cost-effective imaging outside of the visible range, particularly in infrared wavelengths. However, the process of reconstructing compressively sensed images remains computationally expensive. The proof-of-concept tracker described here uses a particle filter with a likelihood update based on a 'smashed filter' which estimates correlation directly, avoiding the reconstruction step. This approach leads to increased noise in correlation estimates, but by implementing the track-before-detect concept in the particle filter, tracker convergence may still be achieved with reasonable sensing rates. The tracker has been successfully tested on sequences of moving cars in the PETS2000 dataset.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8139-8142
Number of pages4
ISBN (Print)9781479928927
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: May 4 2014May 9 2014

Other

Other2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
CountryItaly
CityFlorence
Period5/4/145/9/14

Fingerprint

Image sensors
Railroad cars
Infrared radiation
Imaging techniques
Wavelength
Costs

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Braun, H., Turaga, P., & Spanias, A. (2014). Direct tracking from compressive imagers: A proof of concept. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 8139-8142). [6855187] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2014.6855187

Direct tracking from compressive imagers : A proof of concept. / Braun, Henry; Turaga, Pavan; Spanias, Andreas.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 8139-8142 6855187.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Braun, H, Turaga, P & Spanias, A 2014, Direct tracking from compressive imagers: A proof of concept. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6855187, Institute of Electrical and Electronics Engineers Inc., pp. 8139-8142, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, Florence, Italy, 5/4/14. https://doi.org/10.1109/ICASSP.2014.6855187
Braun H, Turaga P, Spanias A. Direct tracking from compressive imagers: A proof of concept. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 8139-8142. 6855187 https://doi.org/10.1109/ICASSP.2014.6855187
Braun, Henry ; Turaga, Pavan ; Spanias, Andreas. / Direct tracking from compressive imagers : A proof of concept. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 8139-8142
@inproceedings{b9f7fee6b5624f2ab167dc11c16e5ad4,
title = "Direct tracking from compressive imagers: A proof of concept",
abstract = "The compressive sensing paradigm holds promise for more cost-effective imaging outside of the visible range, particularly in infrared wavelengths. However, the process of reconstructing compressively sensed images remains computationally expensive. The proof-of-concept tracker described here uses a particle filter with a likelihood update based on a 'smashed filter' which estimates correlation directly, avoiding the reconstruction step. This approach leads to increased noise in correlation estimates, but by implementing the track-before-detect concept in the particle filter, tracker convergence may still be achieved with reasonable sensing rates. The tracker has been successfully tested on sequences of moving cars in the PETS2000 dataset.",
author = "Henry Braun and Pavan Turaga and Andreas Spanias",
year = "2014",
doi = "10.1109/ICASSP.2014.6855187",
language = "English (US)",
isbn = "9781479928927",
pages = "8139--8142",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Direct tracking from compressive imagers

T2 - A proof of concept

AU - Braun, Henry

AU - Turaga, Pavan

AU - Spanias, Andreas

PY - 2014

Y1 - 2014

N2 - The compressive sensing paradigm holds promise for more cost-effective imaging outside of the visible range, particularly in infrared wavelengths. However, the process of reconstructing compressively sensed images remains computationally expensive. The proof-of-concept tracker described here uses a particle filter with a likelihood update based on a 'smashed filter' which estimates correlation directly, avoiding the reconstruction step. This approach leads to increased noise in correlation estimates, but by implementing the track-before-detect concept in the particle filter, tracker convergence may still be achieved with reasonable sensing rates. The tracker has been successfully tested on sequences of moving cars in the PETS2000 dataset.

AB - The compressive sensing paradigm holds promise for more cost-effective imaging outside of the visible range, particularly in infrared wavelengths. However, the process of reconstructing compressively sensed images remains computationally expensive. The proof-of-concept tracker described here uses a particle filter with a likelihood update based on a 'smashed filter' which estimates correlation directly, avoiding the reconstruction step. This approach leads to increased noise in correlation estimates, but by implementing the track-before-detect concept in the particle filter, tracker convergence may still be achieved with reasonable sensing rates. The tracker has been successfully tested on sequences of moving cars in the PETS2000 dataset.

UR - http://www.scopus.com/inward/record.url?scp=84905216443&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905216443&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2014.6855187

DO - 10.1109/ICASSP.2014.6855187

M3 - Conference contribution

SN - 9781479928927

SP - 8139

EP - 8142

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -