<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Accurate and fast identification of a person from a security point of view is a key procedure. The most common technique of person identification uses identity cards. In contrary to the common approach we focus our research on identification based on the body movement such as the gait in this paper. The gait and the posture belong to the unique characteristics of the person that helps us to facilitate the identification. The proposed methodology allows us to incorporate personal characteristics into the access control systems using the color depth camera (RGBD). For the sake of gait analysis, the important task is to recognize the figure and extract the skeleton data from a video recording. Besides the usage of the mathematical statistics methods, we are opting to use computer animation and computer vision methods, which makes the research interdisciplinary. The main novelty of the paper is the definition and extraction of the feature vector from motion capture data, the analysis methodology and finally the selection of few statistically dominant motion attributes for the identification purposes. Besides the development of new approaches in this field, we validate proposed approaches from the perspective of accuracy.</p></abstract>

Accurate and fast identification of a person from a security point of view is a key procedure. The most common technique of person identification uses identity cards. In contrary to the common approach we focus our research on identification based on the body movement such as the gait in this paper. The gait and the posture belong to the unique characteristics of the person that helps us to facilitate the identification. The proposed methodology allows us to incorporate personal characteristics into the access control systems using the color depth camera (RGBD). For the sake of gait analysis, the important task is to recognize the figure and extract the skeleton data from a video recording. Besides the usage of the mathematical statistics methods, we are opting to use computer animation and computer vision methods, which makes the research interdisciplinary. The main novelty of the paper is the definition and extraction of the feature vector from motion capture data, the analysis methodology and finally the selection of few statistically dominant motion attributes for the identification purposes. Besides the development of new approaches in this field, we validate proposed approaches from the perspective of accuracy.

Application of Motion Capture Attributes to Individual Identification under Corridor Surveillance

Faculty of Mathematics, Physics and Informatics

Journal of Applied Mathematics, Statistics and Informatics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Accurate and fast identification of a person from a security point of view is a key procedure. The most common technique of person identification uses identity...

Application of Motion Capture Attributes to Individual Identification under Corridor Surveillance

Online veröffentlicht: 19. Juni 2018

Seitenbereich: 37 - 56

DOI: https://doi.org/10.2478/jamsi-2018-0004

Schlüsselwörter
Motion identification, Security, Feature vector, Mocap data

© 2018 Faculty of Natural Sciences, University of Saint Cyril and Metodius, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Application of Motion Capture Attributes to Individual Identification under Corridor Surveillance

Online veröffentlicht: 19. Juni 2018

Seitenbereich: 37 - 56

DOI: https://doi.org/10.2478/jamsi-2018-0004

SchlüsselwörterMotion identification, Security, Feature vector, Mocap data

© 2018 Faculty of Natural Sciences, University of Saint Cyril and Metodius, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Schlüsselwörter
Motion identification, Security, Feature vector, Mocap data