3D Skeletal Volume Templates for Deep Learning-Based Activity Recognition
Open Access
- 1 November 2022
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 11 (21) , 3567
Abstract
Due to advances in depth sensor technologies, the use of these sensors has positively impacted studies of human-computer interaction and activity recognition. This study proposes a novel 3D action template generated from depth sequence data and two methods to classify single-person activities using this 3D template. Initially, joint skeleton-based three-dimensional volumetric templates are constructed from depth information. In the first method, images are obtained from various view angles of these three-dimensional templates and used for deep feature extraction using a pre-trained convolutional neural network. In our experiments, a pre-trained AlexNet model trained with the ImageNet dataset is used as a feature extractor. Activities are classified by combining deep features and Histogram of Oriented Gradient (HOG) features. The second approach proposes a three-dimensional convolutional neural network that uses volumetric templates as input for activity classification. Proposed methods have been tested with two publicly available datasets. Experiments provided promising results compared with the other studies presented in the literature.Keywords
This publication has 29 references indexed in Scilit:
- Action Recognition From Depth Maps Using Deep Convolutional Neural NetworksIEEE Transactions on Human-Machine Systems, 2015
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Learning contrastive feature distribution model for interaction recognitionJournal of Visual Communication and Image Representation, 2015
- Spatio-temporal feature extraction and representation for RGB-D human action recognitionPattern Recognition Letters, 2014
- Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition2014
- HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences2013
- Real-time human pose recognition in parts from single depth imagesCommunications of the ACM, 2013
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Real-time classification of dance gestures from skeleton animation2011
- The recognition of human movement using temporal templatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001