Vector space based augmented structural kinematic feature descriptor for human activity recognition in videos

被引:8
作者
Dharmalingam, Sowmiya [1 ]
Palanisamy, Anandhakumar [2 ]
机构
[1] Anna Univ, Dept Informat & Commun Engn, Madras, Tamil Nadu, India
[2] Anna Univ, Madras Inst Technol, Dept Comp Technol, Madras, Tamil Nadu, India
关键词
human activity recognition; kinematic features; multiclass support vector machine classifier; structural features; vector space based augmented structural kinematic; HUMAN ACTION CATEGORIES; SILHOUETTE;
D O I
10.4218/etrij.2018-0102
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is built by integrating the structural and kinematic properties of the actor using vector space based augmented matrix representation. Using the local or global information separately may not provide sufficient action characteristics. The proposed action descriptor combines both the local (pose) and global (position and velocity) features using augmented matrix schema and thereby increases the robustness of the descriptor. A multiclass support vector machine (SVM) is used to learn each action descriptor for the corresponding activity classification and understanding. The performance of the proposed descriptor is experimentally analyzed using the Weizmann and KTH datasets. The average recognition rate for the Weizmann and KTH datasets is 100% and 99.89%, respectively. The computational time for the proposed descriptor learning is 0.003 seconds, which is an improvement of approximately 1.4% over the existing methods.
引用
收藏
页码:499 / 510
页数:12
相关论文
共 50 条
[41]   A spatiotemporal multi-feature extraction framework with space and channel based squeeze-and-excitation blocks for human activity recognition [J].
Zhang, Beibei ;
Xu, Hongji ;
Xiong, Hailiang ;
Sun, Xiaojie ;
Shi, Leixin ;
Fan, Shidi ;
Li, Juan .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 12 (07) :7983-7995
[42]   A spatiotemporal multi-feature extraction framework with space and channel based squeeze-and-excitation blocks for human activity recognition [J].
Beibei Zhang ;
Hongji Xu ;
Hailiang Xiong ;
Xiaojie Sun ;
Leixin Shi ;
Shidi Fan ;
Juan Li .
Journal of Ambient Intelligence and Humanized Computing, 2021, 12 :7983-7995
[43]   AN ONLINE FEATURE SELECTION ARCHITECTURE FOR HUMAN ACTIVITY RECOGNITION [J].
Karagiannaki, Katerina ;
Panousopoulou, Athanasia ;
Tsakalides, Panagiotis .
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, :2522-2526
[44]   Comparative study for feature detectors in human activity recognition [J].
Bebars, Amira Ali ;
Hemayed, Elsayed E. .
2013 9TH INTERNATIONAL COMPUTER ENGINEERING CONFERENCE (ICENCO 2013): TODAY INFORMATION SOCIETY WHAT'S NEXT?, 2014, :19-24
[45]   A Benchmark Study on Feature Selection for Human Activity Recognition [J].
Karagiannaki, Katerina ;
Panousopoulou, Athanasia ;
Tsakalides, Panagiotis .
UBICOMP'16 ADJUNCT: PROCEEDINGS OF THE 2016 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING, 2016, :105-108
[46]   A Novel Feature Selection Method for Video-Based Human Activity Recognition Systems [J].
Siddiqi, Muhammad Hameed ;
Alruwaili, Madallah ;
Ali, Amjad .
IEEE ACCESS, 2019, 7 :119593-119602
[47]   MFCANN: A feature diversification framework based on local and global attention for human activity recognition [J].
Yang, Zhixuan ;
Li, Kewen ;
Huang, Zongchao .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
[48]   An Integration of feature extraction and Guided Regularized Random Forest feature selection for Smartphone based Human Activity Recognition [J].
Thakur, Dipanwita ;
Biswas, Suparna .
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2022, 204
[49]   Human Activity Recognition Based on Feature Fusion of Millimeter Wave Radar and Inertial Navigation [J].
Shi, Jiajia ;
Zhu, Yihan ;
He, Jiaqing ;
Xu, Zhihuo ;
Chu, Liu ;
Braun, Robin ;
Shi, Quan .
IEEE JOURNAL OF MICROWAVES, 2025, 5 (02) :409-424
[50]   A Hybrid Network Based on Dense Connection and Weighted Feature Aggregation for Human Activity Recognition [J].
Lv, Tianqi ;
Wang, Xiaojuan ;
Jin, Lei ;
Xiao, Yabo ;
Song, Mei .
IEEE ACCESS, 2020, 8 :68320-68332