IEICE TRANSACTIONS on Information
Individuality-Preserving Silhouette Extraction for Gait Recognition and Its Speedup
Summary :
Most gait recognition approaches rely on silhouette-based representations due to high recognition accuracy and computational efficiency. A fundamental problem for those approaches is how to extract individuality-preserved silhouettes from real scenes accurately. Foreground colors may be similar to background colors, and the background is cluttered. Therefore, we propose a method of individuality-preserving silhouette extraction for gait recognition using standard gait models (SGMs) composed of clean silhouette sequences of various training subjects as shape priors. The SGMs are smoothly introduced into a well-established graph-cut segmentation framework. Experiments showed that the proposed method achieved better silhouette extraction accuracy by more than 2.3% than representative methods and better identification rate of gait recognition (improved by more than 11.0% at rank 20). Besides, to reduce the computation cost, we introduced approximation in the calculation of dynamic programming. As a result, without reducing the segmentation accuracy, we reduced 85.0% of the computational cost.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.7 pp.992-1001
- Publication Date
- 2021/07/01
- Publicized
- 2021/03/24
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2020ZDP7500
- Type of Manuscript
- PAPER
- Category
- Pattern Recognition
Authors
Masakazu IWAMURA
Osaka Prefecture University
Shunsuke MORI
Osaka Prefecture University
Koichiro NAKAMURA
Osaka Prefecture University
Takuya TANOUE
Osaka University
Yuzuko UTSUMI
Osaka Prefecture University
Yasushi MAKIHARA
Osaka University
Daigo MURAMATSU
Osaka University
Koichi KISE
Osaka Prefecture University
Yasushi YAGI
Osaka University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Masakazu IWAMURA, Shunsuke MORI, Koichiro NAKAMURA, Takuya TANOUE, Yuzuko UTSUMI, Yasushi MAKIHARA, Daigo MURAMATSU, Koichi KISE, Yasushi YAGI, "Individuality-Preserving Silhouette Extraction for Gait Recognition and Its Speedup" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 7, pp. 992-1001, July 2021, doi: 10.1587/transinf.2020ZDP7500.
Abstract: Most gait recognition approaches rely on silhouette-based representations due to high recognition accuracy and computational efficiency. A fundamental problem for those approaches is how to extract individuality-preserved silhouettes from real scenes accurately. Foreground colors may be similar to background colors, and the background is cluttered. Therefore, we propose a method of individuality-preserving silhouette extraction for gait recognition using standard gait models (SGMs) composed of clean silhouette sequences of various training subjects as shape priors. The SGMs are smoothly introduced into a well-established graph-cut segmentation framework. Experiments showed that the proposed method achieved better silhouette extraction accuracy by more than 2.3% than representative methods and better identification rate of gait recognition (improved by more than 11.0% at rank 20). Besides, to reduce the computation cost, we introduced approximation in the calculation of dynamic programming. As a result, without reducing the segmentation accuracy, we reduced 85.0% of the computational cost.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020ZDP7500/_p
Copy
@ARTICLE{e104-d_7_992,
author={Masakazu IWAMURA, Shunsuke MORI, Koichiro NAKAMURA, Takuya TANOUE, Yuzuko UTSUMI, Yasushi MAKIHARA, Daigo MURAMATSU, Koichi KISE, Yasushi YAGI, },
journal={IEICE TRANSACTIONS on Information},
title={Individuality-Preserving Silhouette Extraction for Gait Recognition and Its Speedup},
year={2021},
volume={E104-D},
number={7},
pages={992-1001},
abstract={Most gait recognition approaches rely on silhouette-based representations due to high recognition accuracy and computational efficiency. A fundamental problem for those approaches is how to extract individuality-preserved silhouettes from real scenes accurately. Foreground colors may be similar to background colors, and the background is cluttered. Therefore, we propose a method of individuality-preserving silhouette extraction for gait recognition using standard gait models (SGMs) composed of clean silhouette sequences of various training subjects as shape priors. The SGMs are smoothly introduced into a well-established graph-cut segmentation framework. Experiments showed that the proposed method achieved better silhouette extraction accuracy by more than 2.3% than representative methods and better identification rate of gait recognition (improved by more than 11.0% at rank 20). Besides, to reduce the computation cost, we introduced approximation in the calculation of dynamic programming. As a result, without reducing the segmentation accuracy, we reduced 85.0% of the computational cost.},
keywords={},
doi={10.1587/transinf.2020ZDP7500},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Individuality-Preserving Silhouette Extraction for Gait Recognition and Its Speedup
T2 - IEICE TRANSACTIONS on Information
SP - 992
EP - 1001
AU - Masakazu IWAMURA
AU - Shunsuke MORI
AU - Koichiro NAKAMURA
AU - Takuya TANOUE
AU - Yuzuko UTSUMI
AU - Yasushi MAKIHARA
AU - Daigo MURAMATSU
AU - Koichi KISE
AU - Yasushi YAGI
PY - 2021
DO - 10.1587/transinf.2020ZDP7500
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2021
AB - Most gait recognition approaches rely on silhouette-based representations due to high recognition accuracy and computational efficiency. A fundamental problem for those approaches is how to extract individuality-preserved silhouettes from real scenes accurately. Foreground colors may be similar to background colors, and the background is cluttered. Therefore, we propose a method of individuality-preserving silhouette extraction for gait recognition using standard gait models (SGMs) composed of clean silhouette sequences of various training subjects as shape priors. The SGMs are smoothly introduced into a well-established graph-cut segmentation framework. Experiments showed that the proposed method achieved better silhouette extraction accuracy by more than 2.3% than representative methods and better identification rate of gait recognition (improved by more than 11.0% at rank 20). Besides, to reduce the computation cost, we introduced approximation in the calculation of dynamic programming. As a result, without reducing the segmentation accuracy, we reduced 85.0% of the computational cost.
ER -
English
