Loading...

Time-invariant 3d human action recognition with positive and negative movement memory using convolutional neural networks

Khezeli, F ; Sharif University of Technology | 2019

357 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/PRIA.2019.8785987
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2019
  4. Abstract:
  5. Developing time-invariant solutions for recognition of human action is still an important and open challenge. Three issues make time-invariant solutions so important: different speed of performing the same action by different people, latency in doing the actions and the existence of redundant frames in the recorded video. To overcome these problems, we propose a method based on the so-called memory of the joints to remember only the cumulative positive and negative movement of each joint. Hence, we transform action recognition from time-space to shape-space and the action recognition becomes the problem of shape classification. These shape features contain highly discriminative information and are robust against execution rate. After extracting these features, convolutional neural networks are used to classify the actions. UTKinect and UTD-MHAD skeleton dataset are used for testing this method and the results demonstrate the effectiveness of the proposed method. © 2019 IEEE
  6. Keywords:
  7. Convolutional neural networks ; Shape-space ; Time-invariant ; Convolution ; Image analysis ; Neural networks ; Statistical tests ; Action recognition ; Convolutional neural network ; Positive and negative movement ; Shape space ; Time invariants ; Pattern recognition
  8. Source: 4th International Conference on Pattern Recognition and Image Analysis, IPRIA 2019, 6 March 2019 through 7 March 2019 ; 2019 , Pages 26-31 ; 9781728116211 (ISBN)
  9. URL: https://ieeexplore.ieee.org/abstract/document/8785987