Classification of human actions using pose-based features and stacked auto encoder

被引：23

作者：

Ijjina, Earnest Paul ^{[1
]}

Mohan, Krishna C. ^{[1
]}

机构：

[1] Indian Inst Technol, Visual Learning & Intelligence Grp VIGIL, Dept Comp Sci & Engn, Hyderabad 502285, Telangana, India

来源：

PATTERN RECOGNITION LETTERS | 2016年 / 83卷

关键词：

Human action recognition; Stacked auto encoder; Pose-based features; Fuzzy membership functions; ACTIVITY RECOGNITION; REPRESENTATION;

D O I：

10.1016/j.patrec.2016.03.021

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a method for classification of human actions using pose based features. We demonstrate that statistical information of key movements of actions can be utilized in designing an efficient input representation, using fuzzy membership functions. The ability of stacked auto encoder to learn the underlying features of input data is exploited to recognize human actions. The efficacy of the proposed approach is demonstrated on CMU MOCAP and Berkeley MHAD datasets. (C) 2016 Elsevier B.V. All rights reserved.

引用

页码：268 / 277

页数：10

共 50 条

[1] Abnormal Infant Movements Classification With Deep Learning on Pose-Based Features
McCay, Kevin D.
Ho, Edmond S. L.
Shum, Hubert P. H.
Fehringer, Gerhard
Marcroft, Claire
Embleton, Nicholas D.
IEEE ACCESS, 2020, 8 (08): : 51582 - 51592
[2] Anticipation of Human Actions with Pose-based Fine-grained Representations
Agethen, Sebastian
Lee, Hu-Cheng
Hsu, Winston H.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 2956 - 2959
[3] Genetic optimized stacked auto encoder based diabetic retinopathy classification
Saranya Rubini, S.
Kunthavai, A.
Journal of Multiple-Valued Logic and Soft Computing, 2021, 37 (1-2): : 191 - 206
[4] A Study on Text Classification Based on Stacked Contractive Auto-Encoder
Yu, YangZhen
JingHui
Yu, YangZhen
JingHui
PROCEEDINGS FIRST INTERNATIONAL CONFERENCE ON ELECTRONICS INSTRUMENTATION & INFORMATION SYSTEMS (EIIS 2017), 2017, : 718 - 723
[5] Genetic Optimized Stacked Auto Encoder Based Diabetic Retinopathy Classification
Rubini, S. Saranya
Kunthavai, A.
JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING, 2021, 37 (1-2) : 191 - 206
[6] Skip-Pose Vectors: Pose-based motion embedding using Encoder-Decoder models
Shirakawa, Yuta
Kozakaya, Tatsuo
PROCEEDINGS OF MVA 2019 16TH INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA), 2019,
[7] An efficient human action recognition framework with pose-based spatiotemporal features
Agahian, Saeid
Negin, Farhood
Kose, Cemal
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH, 2020, 23 (01): : 196 - 203
[8] Gender Classification from Pose-Based GEIs
Martin-Felez, Raul
Mollineda, Ramon A.
Salvador Sanchez, J.
COMPUTER VISION AND GRAPHICS, 2012, 7594 : 501 - 508
[9] Deep Stacked Sparse Auto-encoder based on Patches for Image Classification
Jemel, Intidar
Hassairi, Salima
Ejbali, Ridha
Zaied, Mourad
TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), 2020, 11433
[10] Human action recognition using Pose-based discriminant embedding
Saghafi, Behrouz
Rajan, Deepu
SIGNAL PROCESSING-IMAGE COMMUNICATION, 2012, 27 (01) : 96 - 111

← 1 2 3 4 5 →