Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data
Walking gait data acquired with force platforms may be used for person re-identification (re-ID) in various authentication, surveillance, and forensics applications. Current force platformbased re-ID systems classify a fixed set of identities (IDs), which presents a problem when IDs are added or rem...
Published in: | Sensors |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/2440/138041 https://doi.org/10.3390/s23073392 |
id |
ftunivadelaidedl:oai:digital.library.adelaide.edu.au:2440/138041 |
---|---|
record_format |
openpolar |
spelling |
ftunivadelaidedl:oai:digital.library.adelaide.edu.au:2440/138041 2023-12-17T10:29:26+01:00 Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data Duncanson, K.A. Thwaites, S. Booth, D. Hanly, G. Robertson, W.S.P. Abbasnejad, E. Thewlis, D. 2023 application/pdf https://hdl.handle.net/2440/138041 https://doi.org/10.3390/s23073392 en eng MDPI AG http://purl.org/au-research/grants/nhmrc/1126229 Sensors, 2023; 23(7):3392-3392 1424-8220 https://hdl.handle.net/2440/138041 doi:10.3390/s23073392 Duncanson, K.A. [0000-0002-8256-3450] Thwaites, S. [0000-0001-9049-2165] Robertson, W.S.P. [0000-0001-7351-8378] Thewlis, D. [0000-0001-6614-8663] © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). http://dx.doi.org/10.3390/s23073392 gait recognition biometric ground reaction force deep learning zero-shot re-ID center of pressure time series gait analysis force plate classification Journal article 2023 ftunivadelaidedl https://doi.org/10.3390/s23073392 2023-11-20T23:21:44Z Walking gait data acquired with force platforms may be used for person re-identification (re-ID) in various authentication, surveillance, and forensics applications. Current force platformbased re-ID systems classify a fixed set of identities (IDs), which presents a problem when IDs are added or removed from the database. We formulated force platform-based re-ID as a deep metric learning (DML) task, whereby a deep neural network learns a feature representation that can be compared between inputs using a distance metric. The force platform dataset used in this study is one of the largest and the most comprehensive of its kind, containing 193 IDs with significant variations in clothing, footwear, walking speed, and time between trials. Several DML model architectures were evaluated in a challenging setting where none of the IDs were seen during training (i.e., zero-shot re-ID) and there was only one prior sample per ID to compare with each query sample. The best architecture was 85% accurate in this setting, though an analysis of changes in walking speed and footwear between measurement instances revealed that accuracy was 28% higher on same-speed, same-footwear comparisons, compared to cross-speed, cross-footwear comparisons. These results demonstrate the potential of DML algorithms for zero-shot re-ID using force platform data, and highlight challenging cases. Kayne A. Duncanson, Simon Thwaites, David Booth, Gary Hanly, William S. P. Robertson, Ehsan Abbasnejad, and Dominic Thewlis Article in Journal/Newspaper DML The University of Adelaide: Digital Library Sensors 23 7 3392 |
institution |
Open Polar |
collection |
The University of Adelaide: Digital Library |
op_collection_id |
ftunivadelaidedl |
language |
English |
topic |
gait recognition biometric ground reaction force deep learning zero-shot re-ID center of pressure time series gait analysis force plate classification |
spellingShingle |
gait recognition biometric ground reaction force deep learning zero-shot re-ID center of pressure time series gait analysis force plate classification Duncanson, K.A. Thwaites, S. Booth, D. Hanly, G. Robertson, W.S.P. Abbasnejad, E. Thewlis, D. Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data |
topic_facet |
gait recognition biometric ground reaction force deep learning zero-shot re-ID center of pressure time series gait analysis force plate classification |
description |
Walking gait data acquired with force platforms may be used for person re-identification (re-ID) in various authentication, surveillance, and forensics applications. Current force platformbased re-ID systems classify a fixed set of identities (IDs), which presents a problem when IDs are added or removed from the database. We formulated force platform-based re-ID as a deep metric learning (DML) task, whereby a deep neural network learns a feature representation that can be compared between inputs using a distance metric. The force platform dataset used in this study is one of the largest and the most comprehensive of its kind, containing 193 IDs with significant variations in clothing, footwear, walking speed, and time between trials. Several DML model architectures were evaluated in a challenging setting where none of the IDs were seen during training (i.e., zero-shot re-ID) and there was only one prior sample per ID to compare with each query sample. The best architecture was 85% accurate in this setting, though an analysis of changes in walking speed and footwear between measurement instances revealed that accuracy was 28% higher on same-speed, same-footwear comparisons, compared to cross-speed, cross-footwear comparisons. These results demonstrate the potential of DML algorithms for zero-shot re-ID using force platform data, and highlight challenging cases. Kayne A. Duncanson, Simon Thwaites, David Booth, Gary Hanly, William S. P. Robertson, Ehsan Abbasnejad, and Dominic Thewlis |
format |
Article in Journal/Newspaper |
author |
Duncanson, K.A. Thwaites, S. Booth, D. Hanly, G. Robertson, W.S.P. Abbasnejad, E. Thewlis, D. |
author_facet |
Duncanson, K.A. Thwaites, S. Booth, D. Hanly, G. Robertson, W.S.P. Abbasnejad, E. Thewlis, D. |
author_sort |
Duncanson, K.A. |
title |
Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data |
title_short |
Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data |
title_full |
Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data |
title_fullStr |
Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data |
title_full_unstemmed |
Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data |
title_sort |
deep metric learning for scalable gait-based person re-identification using force platform data |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://hdl.handle.net/2440/138041 https://doi.org/10.3390/s23073392 |
genre |
DML |
genre_facet |
DML |
op_source |
http://dx.doi.org/10.3390/s23073392 |
op_relation |
http://purl.org/au-research/grants/nhmrc/1126229 Sensors, 2023; 23(7):3392-3392 1424-8220 https://hdl.handle.net/2440/138041 doi:10.3390/s23073392 Duncanson, K.A. [0000-0002-8256-3450] Thwaites, S. [0000-0001-9049-2165] Robertson, W.S.P. [0000-0001-7351-8378] Thewlis, D. [0000-0001-6614-8663] |
op_rights |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). |
op_doi |
https://doi.org/10.3390/s23073392 |
container_title |
Sensors |
container_volume |
23 |
container_issue |
7 |
container_start_page |
3392 |
_version_ |
1785581813323792384 |