Person re-identification from gait using an autocorrelation network
Publication
, Conference
Carley, C; Ristani, E; Tomasi, C
Published in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
June 1, 2019
We propose a new biometric feature based on autocorrelation using an end-to-end trained network to capture human gait from different viewpoints. Our method condenses an unbounded image stream into a fixed size descriptor, and capitalizes on the periodic nature of walking to leverage sequence self-similarity. Autocorrelation is invariant to start or end of the gait cycle, can be efficiently computed online, and is well suited for capturing pose frequencies. We demonstrate empirically that under equal settings an autocorrelation network provides a more complete representation for gait than existing work, resulting in improved person re-identification performance.
Duke Scholars
Published In
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
DOI
EISSN
2160-7516
ISSN
2160-7508
Publication Date
June 1, 2019
Volume
2019-June
Start / End Page
2345 / 2353
Citation
APA
Chicago
ICMJE
MLA
NLM
Carley, C., Ristani, E., & Tomasi, C. (2019). Person re-identification from gait using an autocorrelation network. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (Vol. 2019-June, pp. 2345–2353). https://doi.org/10.1109/CVPRW.2019.00288
Carley, C., E. Ristani, and C. Tomasi. “Person re-identification from gait using an autocorrelation network.” In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2019-June:2345–53, 2019. https://doi.org/10.1109/CVPRW.2019.00288.
Carley C, Ristani E, Tomasi C. Person re-identification from gait using an autocorrelation network. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2019. p. 2345–53.
Carley, C., et al. “Person re-identification from gait using an autocorrelation network.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2019-June, 2019, pp. 2345–53. Scopus, doi:10.1109/CVPRW.2019.00288.
Carley C, Ristani E, Tomasi C. Person re-identification from gait using an autocorrelation network. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2019. p. 2345–2353.
Published In
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
DOI
EISSN
2160-7516
ISSN
2160-7508
Publication Date
June 1, 2019
Volume
2019-June
Start / End Page
2345 / 2353