Human Action Recognition using 3D Convolutional Neural Networks with 3D Motion Cuboids in Surveillance Videos

被引：59

作者：

Arunnehru, J. ^{[1
]}

Chamundeeswari, G. ^{[1
]}

Bharathi, S. Prasanna ^{[2
]}

机构：

[1] SRM Inst Sci & Technol, Dept CSE, Vadapalani Campus, Chennai 26, Tamil Nadu, India

[2] SRM Inst Sci & Technol, Dept ECE, Vadapalani Campus, Chennai 26, Tamil Nadu, India

来源：

INTERNATIONAL CONFERENCE ON ROBOTICS AND SMART MANUFACTURING (ROSMA2018) | 2018年 / 133卷

关键词：

Human action recognition; 3D Convolutional neural network; 3D motion information; Temporal difference; Classification; FEATURES;

D O I：

10.1016/j.procs.2018.07.059

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In recent days, suspicious action recognition is a significant topic in intelligent video surveillance and computer vision research. Action recognition methodologies are specially needed for surveillance systems which are required to prevent crimes and treacherous actions before occurring. In this paper, we present 3D - Convolutional Neural Networks (3D-CNN) with 3D motion cuboid for action detection and recognizing in videos. The experiments are conducted on benchmark KTH and Weizmann dataset. The proposed method is compared with the existing methods in terms of accuracy. The results show that this approach is outperforms previously published results. (C) 2018 The Authors. Published by Elsevier Ltd.

引用

页码：471 / 477

页数：7

共 16 条

[1]

[Anonymous], 2008, P 2008 IEEE C COMPUT, DOI DOI 10.1109/CVPR.2008.4587735

[2] Maximum Intensity Block Code for Action Recognition in Video Using Tree-based Classifiers [J].

Arunnehru, J. ;

Geetha, M. Kalaiselvi .

ARTIFICIAL INTELLIGENCE AND EVOLUTIONARY ALGORITHMS IN ENGINEERING SYSTEMS, VOL 2, 2015, 325 :715-722

[3]

Arunnehru J., 2013, Mining Intelligence and Knowledge Exploration. First International Conference, MIKE 2013. Proceedings: LNCS 8284, P70, DOI 10.1007/978-3-319-03844-5_8

[4]

Geetha M. K., EMERGING TECHNOLOGIE

[5]

Gharaee Z., APPL SOFT COMPUTING

[6] Actions as space-time shapes [J].

Gorelick, Lena ;

Blank, Moshe ;

Shechtman, Eli ;

Irani, Michal ;

Basri, Ronen .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2007, 29 (12) :2247-2253

[7]

Han Y., PATTERN RECOGNITION

[8]

Jhuang H, 2007, IEEE I CONF COMP VIS, P1253

[9] 3D Convolutional Neural Networks for Human Action Recognition [J].

Ji, Shuiwang ;

Xu, Wei ;

Yang, Ming ;

Yu, Kai .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (01) :221-231

[10]

Ji X., SIGNAL PROCESSING

← 1 2 →