Human Activity Recognition using Optical Flow based Feature Set

被引：0

作者：

Kumar, S. Santhosh ^{[1
]}

John, Mala ^{[1
]}

机构：

[1] Anna Univ, Dept Elect Engn, Madras Inst Technol, Madras, Tamil Nadu, India

来源：

2016 IEEE INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST) | 2016年

关键词：

optical flow; feature descriptor; support vector machine; classification; human activity recognition; VIDEOS;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

An optical flow based approach for recognizing human actions and human-human interactions in video sequences has been addressed in this paper. We propose a local descriptor built by optical flow vectors along the edges of the action performer(s). By using the proposed feature descriptor with multi-class SVM classifier, recognition rates as high as 95.69% and 94.62% have been achieved for Weizmann action dataset and KTH action dataset respectively. The recognition rate achieved is 92.7% for UT interaction Set_1, 90.21% for UT interaction Set_2. The results demonstrate that the method is simple and efficient.

引用

页码：138 / 142

页数：5

共 50 条

[21] Human Activity Recognition and Feature Selection for Stroke Early Diagnosis
Ramon Villar, Jose
Gonzalez, Silvia
Sedano, Javier
Chira, Camelia
Trejo, Jose M.
HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, 2013, 8073 : 659 - 668
[22] Human actions recognition using bag of optical flow words
Zhang, Xu
Miao, Zhenjiang
Wan, Lili
FOURTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2012), 2012, 8334
[23] Enhanced Human Activity Recognition Using Wearable Sensors via a Hybrid Feature Selection Method
Fan, Changjun
Gao, Fei
SENSORS, 2021, 21 (19)
[24] Human Activity Recognition from Accelerometry, Based on a Radius of Curvature Feature
Cavita-Huerta, Elizabeth
Reyes-Reyes, Juan
Romero-Ugalde, Hector M.
Osorio-Gordillo, Gloria L.
Escobar-Jimenez, Ricardo F.
Alvarado-Martinez, Victor M.
MATHEMATICAL AND COMPUTATIONAL APPLICATIONS, 2024, 29 (05)
[25] Speech emotion recognition using a novel feature set
Yang, J. (jsjyj0801@163.com), 1600, Binary Information Press, P.O. Box 162, Bethel, CT 06801-0162, United States (09): : 6097 - 6104
[26] Invariant Feature Learning for Sensor-Based Human Activity Recognition
Hao, Yujiao
Zheng, Rong
Wang, Boyu
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2022, 21 (11) : 4013 - 4024
[27] A Novel Sensor-Based Human Activity Recognition Method Based on Hybrid Feature Selection and Combinational Optimization
Tian, Yiming
Zhang, Jie
Li, Lipeng
Liu, Zuojun
IEEE ACCESS, 2021, 9 : 107235 - 107249
[28] Radar-Based Human Activity Recognition Using Hyperdimensional Computing
Yao, Yirong
Liu, Wenbo
Zhang, Gong
Hu, Wen
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2022, 70 (03) : 1605 - 1619
[29] Smartphone sensors-based human activity recognition using feature selection and deep decision fusion
Zhang, Yijia
Yao, Xiaolan
Fei, Qing
Chen, Zhen
IET CYBER-PHYSICAL SYSTEMS: THEORY & APPLICATIONS, 2023, 8 (02) : 76 - 90
[30] Physiotherapy-based human activity recognition using deep learning
Deotale, Disha
Verma, Madhushi
Suresh, P.
Kumar, Neeraj
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (15) : 11431 - 11444

← 1 2 3 4 5 →