23,552 Hits in 5.5 sec

Deep Learning for Human Action Recognition with Convolution Neural Network

S. Karthickkumar, K. Kumar
2020 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
In recent years, deep learning for human action recognition is one of the most popular researches.  ...  In this paper to propose a Two-Dimensional (2D) Convolutional Neural Network for recognizing Human Activities. Here the WISDM dataset is used to tarin and test the data.  ...  In this paper Fig.3. shows structure of Convolution Neural Network for Human Action Recognition [4].  ... 
doi:10.32628/cseit206466 fatcat:zk5ge4ne2zfxtj6al2lkdolapu

Multi-filter dynamic graph convolutional networks for skeleton-based action recognition

Yating Yuan, Bo Yu, Wei Wang, Bihui Yu
2021 Procedia Computer Science  
on the convolutional neural network, namely, the multi-filter dynamic graph convolutional neural network.  ...  on the convolutional neural network, namely, the multi-filter dynamic graph convolutional neural network.  ...  The title of the project is Research on voice print recognition and Character Action Recognition of Network Culture service.  ... 
doi:10.1016/j.procs.2021.02.099 fatcat:sbws5wfz7bamfomqeaqhbmtvny

Design of National Sports Action Feature Extraction System Based on Convolutional Neural Network

Yajun Pang, Baiyuan Ding
2022 Scientific Programming  
Human action recognition is one of the hotspots in computer vision research.  ...  Based on the action features of famous sports, this paper proposes an action recognition scheme based on RGB-D video compression to establish action features and deep learning as a means of recognition  ...  Convolutional Neural Network One of the most common algorithms for image recognition is a model built based on a convolutional neural network (CNN), which can be regarded as a forward feedback neural network  ... 
doi:10.1155/2022/5747647 fatcat:seonk6m735gihasgkjhd4auk3i

Design and Implementation of Behavior Recognition System Based on Convolutional Neural Network

Bo Yu, L. Long, Y. Li, X. Li, Y. Dai, H. Yang
2017 ITM Web of Conferences  
We build a set of human behavior recognition system based on the convolution neural network constructed for the specific human behavior in public places.  ...  The result show that the convolution neural network can study human behavior model automatically and identify human's behaviors without any manually annotated trainings.  ...  Acknowledgment This paper proposes a behavior recognition method based on convolutional neural network, learning the characteristics of human behavior through convolution unsupervised neural networks,  ... 
doi:10.1051/itmconf/20171201025 fatcat:4l7ol5m4ynctpfe4hackg7qdzq

Extraction and Recognition Method of Basketball Players' Dynamic Human Actions Based on Deep Learning

Qiulin Wang, Baole Tao, Fulei Han, Wenting Wei, Sang-Bing Tsai
2021 Mobile Information Systems  
This method uses the deep convolutional neural network VGG model on the TensorFlow platform to extract and recognize human actions.  ...  This paper implements human action recognition algorithm based on deep learning.  ...  Many scholars at home and abroad have conducted related researches on three aspects: feature collection, deep convolutional neural networks, and human action recognition.  ... 
doi:10.1155/2021/4437146 fatcat:hb4yrvdo5vcovcr3njs3ovvyry

An Action Recognition Algorithm for Sprinters Using Machine Learning

Fengqing Jiang, Xiao Chen
2021 Mobile Information Systems  
This paper takes sprint as the research problem and constructs the image of sprinter's action recognition based on machine learning.  ...  In view of the shortcomings of traditional dual-stream convolutional neural network for processing long-term video information, the time-segmented dual-stream network, based on sparse sampling, is used  ...  Recognition Network Model. is paper uses a time-segmented convolutional neural network based on a sparse sampling strategy.  ... 
doi:10.1155/2021/9919992 doaj:03e3874be23e49d29c9fa64b5f53b61b fatcat:bnm3ykmhqrf25n4qghhkimefra

Action Recognition Based on the Modified Twostream CNN

Dan zheng, Software College, Shenyang Normal University, Shenyang 110034, China, Hang Li, Shoulin Yin, Software College, Shenyang Normal University, Shenyang 110034, China, Software College, Shenyang Normal University, Shenyang 110034, China
2020 International Journal of Mathematical Sciences and Computing  
In this paper, a action recognition method based on improved space-time two-channel convolutional neural network is proposed.  ...  Compared with other neural network models, it has more advantages in human action recognition.  ...  The behavior recognition method proposed in this paper has practical engineering value, especially for the elderly behavior prediction, it provides a great guarantee for their safety.  ... 
doi:10.5815/ijmsc.2020.06.03 fatcat:esdu3cv4gnabll5hyhnpayhyuu

Using Artificial Intelligence to Achieve Auxiliary Training of Table Tennis Based on Inertial Perception Data

Pu Yanan, Yan Jilong, Zhang Heng
2021 Sensors  
Finally, we propose a new method based on multi-dimensional feature fusion convolutional neural network and fine-grained evaluation of human table tennis actions.  ...  The experimental results prove that our proposed multi-dimensional feature fusion convolutional neural network has an average recognition rate that is 0.17 and 0.16 higher than that of CNN and Inception-CNN  ...  neural network for human action recognition research.  ... 
doi:10.3390/s21196685 pmid:34641004 pmcid:PMC8513010 fatcat:vdoutwxosrge7csc7jabp7ptsq

Adaptive Recognition of Motion Posture in Sports Video Based on Evolution Equation

Rui Yuan, Zhendong Zhang, Yanyan Le, Enqing Chen, Miaochao Chen
2021 Advances in Mathematical Physics  
The two-level neural network intelligent recognition algorithm effectively recognizes similar actions by splitting the traditional single-level neural network into two-level neural networks.  ...  Secondly, a two-level neural network intelligent motion gesture recognition algorithm is proposed.  ...  The early ones include research based on monocular video and research based on multiview video [7, 8] .  ... 
doi:10.1155/2021/2148062 fatcat:4d3zswpasja4zax47knmcuisse

A Survey of Machine Learning Techniques For Human Activity Recognition and Their Methods and Algorithm

R. Bagavathi Lakshmi
2018 International Journal of Applied Science and Engineering  
The recognition model is constructed and concentrated on different machine learning algorithm to set the feature illustration in this research work based upon the efficient of HAR.  ...  The main objective of activity recognition is to offer information on a user's actions for permitting the computing systems to proactively help users with their tasks.  ...  A user-independent human activity recognition issue was addressed depended on Convolutional Neural Networks (CNN).  ... 
doi:10.30954/2322-0465.2.2018.2 fatcat:msxxlle34zb7xf6iwdcgsrq5qm

Study of Human Motion Recognition Algorithm Based on Multichannel 3D Convolutional Neural Network

Yang Ju, Zhihan Lv
2021 Complexity  
Aiming at the problem that it is difficult to balance the speed and accuracy of human behaviour recognition, this paper proposes a method of motion recognition based on random projection.  ...  Thirdly, a multichannel 3D convolutional neural network is proposed, and the multiple information extracted by the network is fused to form an output recognizer.  ...  Improved Action Recognition Algorithm of 3D Convolutional Neural Network. e core of the 3D convolutional neural network constructed in this paper uses a dual-stream 3D convolutional neural network, and  ... 
doi:10.1155/2021/7646813 fatcat:ynqu4ky5szgebjo67pz6n4i3qq

A Review on Human Action Recognition in Surveillance Videos

Hemangee De, Aanisha Bhattacharyya, Rachna Agarwal, Sudeshna Roy Chowdhury
2019 International Journal of Advanced Science and Engineering  
Triparna Datta, to allow us a chance to showcase our ideas in form of this research paper.  ...  Depth Maps and Postures are used for Human Action Recognition using Deep Convolution Neural Networks. This is a more effective method.  ...  Each and every level of sub-action descriptor is one convolutional neural network (CNN)based classifier which captures different appearance Using Multi-CNN Action Classifier [6] three appearance-based  ... 
doi:10.29294/ijase.6.s1.2019.60-63 fatcat:3iqrtplb5jar3hzxzmyluxwnhq

Remarkable Skeleton Based Human Action Recognition

Sushma Jaiswal, Tarun Jaiswal
2020 Artificial Intelligence Evolution  
Skeleton-based human-action-recognition (SBHAR) has wide applications in cognitive science and automatic surveillance.  ...  However, the most challenging and crucial task of the skeleton-based human-action-recognition (SBHAR) is a significant view variation while capturing the data.  ...  The authors trust the APSR for depth construction and RGB+D based action-recognition. View Adaptation Neural Network (VA-NN).  ... 
doi:10.37256/aie.122020562 fatcat:2wdzis5ax5bdfnwdhlzgvoh6xu

Residual Neural Network Model for Detecting Waste Disposing Action in Images

I Made Arsa Suyadnya, Duman Care Khrisne
2021 Journal of Electrical Electronics and Informatics  
This research was conducted to detect the actions carried out by humans in the activities/actions of disposing of waste in an image.  ...  We use a Convolutional Neural Network model with a Residual Neural Network architecture to detect the types of activities that objects perform in an image.  ...  to colleagues who cannot be named one by one, support and suggestions that help in completion of this research.  ... 
doi:10.24843/jeei.2021.v05.i02.p03 fatcat:stcfasgrgva5np5sxtrfbo5hey

Recognition of Basketball Player's Shooting Action Based on the Convolutional Neural Network

Rui Liu, Ziqi Liu, Shuyong Liu, Shah Nazir
2021 Scientific Programming  
defined a priori knowledge, while another kind is based on training the convolution neural network model.  ...  The test results of the network model are taken as the prior knowledge, and then, a convolutional neural network dynamic target recognition model is constructed based on the prior knowledge.  ...  Image analysis technology is applied to human posture recognition earlier. e technology is relatively mature; the early ones are based on monocular video research and multiview video research.  ... 
doi:10.1155/2021/3045418 fatcat:scw54exl2rfyzpywl2xbyyys44
« Previous Showing results 1 — 15 out of 23,552 results