Time-Invariant 3D Human Action Recognition with Positive and Negative Movement Memory using Convolutional Neural Networks

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Khezeli, Farhad, Mohammadzade, Hoda
Format: Conference Proceeding
Language:English
Subjects:
Action recognition
Convolutional neural networks
Feature extraction
Hidden Markov models
Pattern recognition
positive and negative movement
Robustness
Sensors
shape-space
Skeleton
time-invariant
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2049-3630
DOI:10.1109/PRIA.2019.8785987