TFP3D human behavior recognition algorithm based on T-Fusion

被引：0

作者：

Zeng M. ^{[1
]}

Xiong J. ^{[1
]}

Zhu Q. ^{[1
,2
]}

机构：

[1] School of Information Engineering, Nanchang University, Nanchang

[2] School of Public Policy and Administration, Nanchang University, Nanchang

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2023年 / 29卷 / 12期

基金：

中国国家自然科学基金;

关键词：

behavior recognition; deep learning; pre-train; temporal fusion network; TFP3D network;

D O I：

10.13196/j.cims.2022.0081

中图分类号：

学科分类号：

摘要：

In view of the shortcomings of current human behavior recognition algorithms, such as the poor timeliness of two stream convolutional neural network, the large number of parameters of 3D convolutional neural network and the high complexity of the algorithm, a space-time fusion pseudo-3D convolutional neural network model TFP3D was proposed based on 3D convolutional network and temporal fusion network. The 3D convolution splitting was used to reduce the large number of parameters brought by 3D convolution kernels. The temporal fusion module was added to ensure the effective transmission of the spatio-temporal features of human behavior information. Finally, the Kinetics dataset was used to pre-train the deep model to improve network speed while maintaining accuracy. A lot of experimental analyses were carried out on the common human behavior recognition dataset UCF101, and the recognition results were compared with the current popular algorithms. The results showed that the proposed TFP3D designed was better than other methods, and the average recognition rate was greatly improved compared with other methods. © 2023 CIMS. All rights reserved.

引用

页码：4032 / 4039

页数：7

共 22 条

[1]

ZHANG Xiaoping, JI Jiahui, Overview of video based human abnormal behavior recognition and detection methods[J], Control and Decision, 37, 1, pp. 14-27, (2022)

[2]

WANG Jiacheng, BAO Jinsong, Liu Tianyuan, Et al., Online method for worker operation recognition based on attention of workpiece, Computer Integrated Manufacturing Systems, 27, 4, pp. 1099-1107, (2021)

[3]

ZHANG Qing, WANG Xingjian, MIAO YlNan, Et al., Human motion direction prediction method based on eye tracking, pose and scene video, Journal of Beijing University of Aeronautics and Astronautics, 47, 9, pp. 1857-1865, (2021)

[4]

ZHOU Feiyan, JIN Linpeng, Dong Jun, Review of convolution neural network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)

[5]

ZHANG Xiaojun, LI Chenzheng, SUN Lingyun, Et al., Behavior recognition method based on improved 3D convolutional neural network[J], Computer Integrated Manufacturing Systems, 25, 8, pp. 2000-2006, (2019)

[6]

WANG X, ZHANG W., Anti-occlusion face recognition algorithm based on a deep convolutional neural network, Computers & Electrical Engineering, 96, (2021)

[7]

SIMON YANK, ZISSERMAN A., Two-stream convolutional networks for action recognition in videos

[8]

FEICHTENHOFER C, PINZ A, ZISSERMAN A., Convolutional two-stream network fusion for video action recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933-1941, (2016)

[9]

NGJY H, HAUSKNECHT M, VIJAYANARASIMHAN S, Et al., Beyond short snippets: Deep networks for video clas-sification, Proceedings of the IEEE Conference on Computer Vision And Pattern Recognition, pp. 4694-4702, (2015)

[10]

LIN J, GAN C, HAN S., TSM: Temporal shift module for efficient video understanding, Proceedings ofthe IEEE/ CVF International Conference on Computer Vision (ICCV), pp. 7082-7092, (2019)

← 1 2 3 →