Augmented inputs for surveillance re-identification
Issued Date
2024-03-01
Resource Type
ISSN
21926611
eISSN
2192662X
Scopus ID
2-s2.0-85181483093
Journal Title
International Journal of Multimedia Information Retrieval
Volume
13
Issue
1
Rights Holder(s)
SCOPUS
Bibliographic Citation
International Journal of Multimedia Information Retrieval Vol.13 No.1 (2024)
Suggested Citation
Kasantikul R., Kusakunniran W. Augmented inputs for surveillance re-identification. International Journal of Multimedia Information Retrieval Vol.13 No.1 (2024). doi:10.1007/s13735-023-00309-1 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/95796
Title
Augmented inputs for surveillance re-identification
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Person Re-Identification (Re-ID) is one of the important applications for Surveillance. However, the performance of Re-ID is dependent on the input quality, which cannot be guaranteed from the surveillance systems. We explored the technique from Gait Re-ID to address viewpoint changes. From our findings, adding horizontally mirrored image into an auxiliary pipeline can achieve a modest performance uplift in our test (0.8% net increase in mean average precision and 0.9% increase in Rank-1 accuracy) in MARS dataset. This extra pipeline can be substituted by Heterogeneous Input Triplet Loss (hiTri) for minimal performance loss. The overall performance of the proposed method outperforms state-of-the-art techniques on well-known datasets. Further investigations on other auxiliary input types are warranted.