Temporally Deformable Convolution for Gait Recognition
Gait recognition is a biometric technology that identifies individuals based on the unique characteristics of their gait. With the advancement of deep learning based computer vision technology, gait recognition has significantly improved in performance and gained significant attention due to its non...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10830518/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542599099285504 |
|---|---|
| author | Juyoung Kim Beomseong Kim Heesung Lee |
| author_facet | Juyoung Kim Beomseong Kim Heesung Lee |
| author_sort | Juyoung Kim |
| collection | DOAJ |
| description | Gait recognition is a biometric technology that identifies individuals based on the unique characteristics of their gait. With the advancement of deep learning based computer vision technology, gait recognition has significantly improved in performance and gained significant attention due to its non-invasive nature. This paper proposes a vision-based gait recognition model that enhances performance by applying deformable convolution in the temporal dimension. Gait is a periodic behavior, and understanding the body’s changing patterns during walking is crucial for improving recognition accuracy. Important features for gait recognition can appear in both short and long moments of the walking process. Therefore, this study proposes a model that performs deformable convolution in the temporal dimension to effectively extract such features. This allows for a more flexible understanding of temporal patterns, eliminating the need for hand-crafted design of filters for extracting temporal features and enabling the model to learn important features for gait recognition that appear in both short and long time intervals in a unified manner. As a result, the proposed model achieved state-of-the-art performance on the CASIA-B dataset. |
| format | Article |
| id | doaj-art-f8259da6f4a74332ba2164b60332ab22 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-f8259da6f4a74332ba2164b60332ab222025-01-14T00:02:41ZengIEEEIEEE Access2169-35362025-01-01136475648610.1109/ACCESS.2025.352688610830518Temporally Deformable Convolution for Gait RecognitionJuyoung Kim0https://orcid.org/0009-0009-9486-4101Beomseong Kim1https://orcid.org/0000-0003-4394-2260Heesung Lee2https://orcid.org/0000-0001-9944-3976Department of Railroad Electrical and Information Engineering, Korea National University of Transportation, Uiwang-si, Gyeonggi-do, South KoreaDepartment of Artificial Intelligence, Gyeonggi University of Science and Technology, Siheung-si, Gyeonggi-do, South KoreaDepartment of Railroad Electrical and Information Engineering, Korea National University of Transportation, Uiwang-si, Gyeonggi-do, South KoreaGait recognition is a biometric technology that identifies individuals based on the unique characteristics of their gait. With the advancement of deep learning based computer vision technology, gait recognition has significantly improved in performance and gained significant attention due to its non-invasive nature. This paper proposes a vision-based gait recognition model that enhances performance by applying deformable convolution in the temporal dimension. Gait is a periodic behavior, and understanding the body’s changing patterns during walking is crucial for improving recognition accuracy. Important features for gait recognition can appear in both short and long moments of the walking process. Therefore, this study proposes a model that performs deformable convolution in the temporal dimension to effectively extract such features. This allows for a more flexible understanding of temporal patterns, eliminating the need for hand-crafted design of filters for extracting temporal features and enabling the model to learn important features for gait recognition that appear in both short and long time intervals in a unified manner. As a result, the proposed model achieved state-of-the-art performance on the CASIA-B dataset.https://ieeexplore.ieee.org/document/10830518/Biometric identificationpattern recognitionneural networkscomputer visionmachine learning for images |
| spellingShingle | Juyoung Kim Beomseong Kim Heesung Lee Temporally Deformable Convolution for Gait Recognition IEEE Access Biometric identification pattern recognition neural networks computer vision machine learning for images |
| title | Temporally Deformable Convolution for Gait Recognition |
| title_full | Temporally Deformable Convolution for Gait Recognition |
| title_fullStr | Temporally Deformable Convolution for Gait Recognition |
| title_full_unstemmed | Temporally Deformable Convolution for Gait Recognition |
| title_short | Temporally Deformable Convolution for Gait Recognition |
| title_sort | temporally deformable convolution for gait recognition |
| topic | Biometric identification pattern recognition neural networks computer vision machine learning for images |
| url | https://ieeexplore.ieee.org/document/10830518/ |
| work_keys_str_mv | AT juyoungkim temporallydeformableconvolutionforgaitrecognition AT beomseongkim temporallydeformableconvolutionforgaitrecognition AT heesunglee temporallydeformableconvolutionforgaitrecognition |