A Comparison of Machine Learning Models with Data Augmentation Techniques for Skeleton-based Human Action Recognition
Open Access
- 3 September 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Abstract
3D skeleton motion recognition plays a crucial role in the field of human action recognition (HAR) due to its efficiency and reliability. This paper introduces data augmentation techniques applied to skeleton data with the aim of improving the accuracy of machine learning models and examining the effectiveness of different augmentation methods for different activities. Spatial transformations are applied to generate augmented samples from the original 3D skeleton sequences, while temporal augmentation techniques are employed to capture the temporal differences in motion. We evaluated the effects of spatial and temporal data augmentation at different levels on the MSR Daily Activity 3D dataset using SVM, CNN, LSTM, and CNNLSTM models. The results show that temporal augmentation significantly improves model performance, while spatial augmentation has only a limited effect on model performance. Simultaneously applying both spatial and temporal augmentation further improved model performance, highlighting the importance of temporal information in action sequence data.Keywords
This publication has 20 references indexed in Scilit:
- 3D Skeleton-Based Video Action Recognition by Graph Convolution Network2019
- A survey on Image Data Augmentation for Deep LearningJournal of Big Data, 2019
- Sample Fusion Network: An End-to-End Data Augmentation Network for Skeleton-Based Human Action RecognitionIEEE Transactions on Image Processing, 2019
- Encoding Pose Features to Images With Data Augmentation for 3-D Action RecognitionIEEE Transactions on Industrial Informatics, 2019
- A Comprehensive Survey of Vision-Based Human Action Recognition MethodsSensors, 2019
- Spatial-Temporal Data Augmentation Based on LSTM Autoencoder Network for Skeleton-Based Human Action Recognition2018
- Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks2017
- Action Recognition From Depth Maps Using Deep Convolutional Neural NetworksIEEE Transactions on Human-Machine Systems, 2015
- Mining actionlet ensemble for action recognition with depth cameras2012
- Long Short-Term MemoryNeural Computation, 1997