Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition
Individual recognition based on skeletal sequence is a challenging computer vision task with multiple important applications, such as public security, human–computer interaction, and surveillance. However, much of the existing work usually fails to provide any explicit quantitative differe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/19/1/56 |
| _version_ | 1811306922591125504 |
|---|---|
| author | Jianhai Zhang Zhiyong Feng Yong Su Meng Xing Wanli Xue |
| author_facet | Jianhai Zhang Zhiyong Feng Yong Su Meng Xing Wanli Xue |
| author_sort | Jianhai Zhang |
| collection | DOAJ |
| description | Individual recognition based on skeletal sequence is a challenging computer vision task with multiple important applications, such as public security, human–computer interaction, and surveillance. However, much of the existing work usually fails to provide any explicit quantitative differences between different individuals. In this paper, we propose a novel 3D spatio-temporal geometric feature representation of locomotion on Riemannian manifold, which explicitly reveals the intrinsic differences between individuals. To this end, we construct mean sequence by aligning related motion sequences on the Riemannian manifold. The differences in respect to this mean sequence are modeled as spatial state descriptors. Subsequently, a temporal hierarchy of covariance are imposed on the state descriptors, making it a higher-order statistical spatio-temporal feature representation, showing unique biometric characteristics for individuals. Finally, we introduce a kernel metric learning method to improve the classification accuracy. We evaluated our method on two public databases: the CMU Mocap database and the UPCV Gait database. Furthermore, we also constructed a new database for evaluating running and analyzing two major influence factors of walking. As a result, the proposed approach achieves promising results in all experiments. |
| first_indexed | 2024-04-13T08:54:17Z |
| format | Article |
| id | doaj.art-38aedcc084004323b1a6539f6eb38516 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T08:54:17Z |
| publishDate | 2018-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-38aedcc084004323b1a6539f6eb385162022-12-22T02:53:22ZengMDPI AGSensors1424-82202018-12-011915610.3390/s19010056s19010056Riemannian Spatio-Temporal Features of Locomotion for Individual RecognitionJianhai Zhang0Zhiyong Feng1Yong Su2Meng Xing3Wanli Xue4College of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaIndividual recognition based on skeletal sequence is a challenging computer vision task with multiple important applications, such as public security, human–computer interaction, and surveillance. However, much of the existing work usually fails to provide any explicit quantitative differences between different individuals. In this paper, we propose a novel 3D spatio-temporal geometric feature representation of locomotion on Riemannian manifold, which explicitly reveals the intrinsic differences between individuals. To this end, we construct mean sequence by aligning related motion sequences on the Riemannian manifold. The differences in respect to this mean sequence are modeled as spatial state descriptors. Subsequently, a temporal hierarchy of covariance are imposed on the state descriptors, making it a higher-order statistical spatio-temporal feature representation, showing unique biometric characteristics for individuals. Finally, we introduce a kernel metric learning method to improve the classification accuracy. We evaluated our method on two public databases: the CMU Mocap database and the UPCV Gait database. Furthermore, we also constructed a new database for evaluating running and analyzing two major influence factors of walking. As a result, the proposed approach achieves promising results in all experiments.http://www.mdpi.com/1424-8220/19/1/56individual recognitionRiemannian manifoldspatio-temporal representationRiemannian mean motion |
| spellingShingle | Jianhai Zhang Zhiyong Feng Yong Su Meng Xing Wanli Xue Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition Sensors individual recognition Riemannian manifold spatio-temporal representation Riemannian mean motion |
| title | Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition |
| title_full | Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition |
| title_fullStr | Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition |
| title_full_unstemmed | Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition |
| title_short | Riemannian Spatio-Temporal Features of Locomotion for Individual Recognition |
| title_sort | riemannian spatio temporal features of locomotion for individual recognition |
| topic | individual recognition Riemannian manifold spatio-temporal representation Riemannian mean motion |
| url | http://www.mdpi.com/1424-8220/19/1/56 |
| work_keys_str_mv | AT jianhaizhang riemannianspatiotemporalfeaturesoflocomotionforindividualrecognition AT zhiyongfeng riemannianspatiotemporalfeaturesoflocomotionforindividualrecognition AT yongsu riemannianspatiotemporalfeaturesoflocomotionforindividualrecognition AT mengxing riemannianspatiotemporalfeaturesoflocomotionforindividualrecognition AT wanlixue riemannianspatiotemporalfeaturesoflocomotionforindividualrecognition |