Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Robust Method or Human Action Recognition in Video Streams Using Skeleton Graph based CNN


Affiliations
1 Department of Computer Science and Engineering, KVG College of Engineering, India
2 Department of Information Science, NITTE University, India
     

   Subscribe/Renew Journal


Understanding the action of human plays an important role in public gatherings and recognition of human action is a major problem which leads to analysis the human activities. In many years, people are interested for detecting the human activity. Human behavior analysis are used in many areas like video surveillance, banks to increase public security. To detect the human behavior from the videos, essential features are to be detected. The major challenge in human action recognition is to generate the required features significance changes occurred in human action. Nowadays skeleton data-based action detection becoming more popular. In order to counterpart such limitations, this paper brings a method using Skeleton Graph based deep learning convolutional neural network. The proposed method gives accuracy of 0.93.

Keywords

Human Action Recognition, Skeletization, Convolutional Neural Network, Skeleton Graph
Subscription Login to verify subscription
User
Notifications
Font Size

  • Chengfei Wu and Zixuan Cheng, “A Novel Detection Framework for Detecting Abnormal”, Mathematical Problems in Engineering, Vol. 2020, pp. 1-9, 2020.
  • Matthias Straka., Stefan Hauswiesner, Matthias Ruther and Horst Bischof, “Skeletal Graph Based Human Pose Estimation in Real-Time”, Proceedings of British Conference on Machine Vision, pp. 1-6, 2011.
  • Lei Shi, Yifan Zhang, Jian Cheng and Hanqing Lu, “Skeleton-Based Action Recognition with Directed Graph Neural Networks”, Proceedings of International Conference on Computer Vision, pp. 1-5, 2018.
  • M. Vrigkas and A.A. Ioannis, “A Review of Human Activity Recognition Methods”, Sensors, Vol. 19, No. 17, pp. 3680-3688, 2019.
  • Ali Mottaghi, Mohsen Soryani and Hamid Seifi, “Action Recognition in Freestyle Wrestling using Silhouette-Skeleton Features”, Engineering Science and Technology, Vol. 23, pp. 921-930, 2020.
  • M. Feng and J. Meunier, “Skeleton Graph-Neural-Network-Based Human Action Recognition: A Survey”, Sensors, Vol. 22, pp. 2091-2099, 2022.
  • K. Zhou, “Skeleton Based Abnormal Behavior Recognition using Spatio-Temporal Convolution and Attention-Based LSTM”, Procedia Computer Science, Vol. 174, pp. 424-432, 2021.
  • X. Zhen and L. Shao, “Action Recognition Via Spatio-Temporal Local Features: A Comprehensive Study”, Image and Vision Computing, Vol. 50, pp. 1-13, 2016.
  • M. Straka, Stefan Hauswiesner and Matthias Ruther, “Skeletal Graph based Human Pose Estimation”, Proceedings of British Conference on Machine Vision, pp. 1-12, 2011.
  • Nicolas Thome, Djamel Merad and Serge Miguet, “Human Body Part Labeling and Tracking using Graph Matching Theory”, Proceedings of IEEE Conference on Video and Signal Based Surveillance, pp. 1-14, 2006.
  • P.M. Pandit and S.G. Akojwar, “Skeletonization and Classification by Bayesian Classifier Algorithm for Object Recognition”, International Refereed Journal of Engineering and Science, Vol. 2, No. 5, pp. 24-31, 2013.
  • Meng Li and Q. Sun, “3DSkeletalHumanAction Recognition Using a CNN Fusion Model”, Mathematical Problems in Engineering, Vol. 2021, pp. 1-9, 2021.
  • S. Nowozin, G. Bakir and K. Tsuda, “Discriminative Subsequence Mining for Action Classification”, Proceedings of International Conference on Computer Vision, pp. 1-12, 2007.
  • J.C. Niebles, H. Wang and L. Fei-Fei, “Unsupervised Learning of Human Action Categories using Spatial-Temporal Words”, Proceedings of British Conference on Machine Vision, pp. 1-7, 2006.
  • A. Krizhevsky, I. Sutskever and G.E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks”, Proceedings of Annual Conference on Advances in Neural Information Processing Systems, pp. 1-13, 2021.
  • J. Arunnehru,, G. Chamundeeswari and S. Prasanna Bharathi, “Human Action Recognition using 3D Convolutional Neural Networks with 3D Motion Cuboids in Surveillance Videos”, Proceedings of International Conference on Robotics and Smart Manufacturing, Vol. 133, pp. 471-477, 2018.
  • P. Antonik, N. Marsal and D. Brunner, “Human Action Recognition with a Large-Scale Brain-Inspired Photonic Computer”, Nature Machine Intelligence, Vol. 1, pp. 530-537, 2019.
  • Zahraa Salim David and Amel Hussain Abbas, “Human Action Recogntion using Interest Point Detector with Kth Dataset”, International Journal of Civil Engineering and Technology, Vol. 10, No. 4, pp. 333-343, 2019.
  • Y. Du, W. Wang and L. Wang, “Hierarchical Recurrent Neural Network for Skeleton based Action Recognition”, Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 1110-1118, 2015.
  • P. Zhang, “View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 41, No. 8, pp. 1963-1978, 2019.
  • Noor Almaadeed, “A Novel Approach for Robust Multi Human Action Detection and Recognition based on 3D-Dimentional Convolutional Neural Networks”, Proceedings of British Conference on Machine Vision, pp. 1-12, 2019.

Abstract Views: 235

PDF Views: 2




  • Robust Method or Human Action Recognition in Video Streams Using Skeleton Graph based CNN

Abstract Views: 235  |  PDF Views: 2

Authors

K.L. Bhagya Jyothi
Department of Computer Science and Engineering, KVG College of Engineering, India
Vasudeva
Department of Information Science, NITTE University, India

Abstract


Understanding the action of human plays an important role in public gatherings and recognition of human action is a major problem which leads to analysis the human activities. In many years, people are interested for detecting the human activity. Human behavior analysis are used in many areas like video surveillance, banks to increase public security. To detect the human behavior from the videos, essential features are to be detected. The major challenge in human action recognition is to generate the required features significance changes occurred in human action. Nowadays skeleton data-based action detection becoming more popular. In order to counterpart such limitations, this paper brings a method using Skeleton Graph based deep learning convolutional neural network. The proposed method gives accuracy of 0.93.

Keywords


Human Action Recognition, Skeletization, Convolutional Neural Network, Skeleton Graph

References