Independent Component feature-based human activity recognition via Linear Discriminant Analysis and Hidden Markov Model
- 1 August 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Vol. 2008 (1094687X), 5168-5171
- https://doi.org/10.1109/iembs.2008.4650378
Abstract
In proactive computing, human activity recognition from image sequences is an active research area. This paper presents a novel approach of human activity recognition based on Linear Discriminant Analysis (LDA) of Independent Component (IC) features from shape information. With extracted features, Hidden Markov Model (HMM) is applied for training and recognition. The recognition performance using LDA of IC features has been compared to other approaches including Principle Component Analysis (PCA), LDA of PC, and ICA. The preliminary results show much improved performance in the recognition rate with our proposed method.Keywords
This publication has 6 references indexed in Scilit:
- Recognizing Human Activities in Video by Multi-resolutional Optical FlowsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Inference of human postures by classification of 3D human body shapePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Recognizing human action in time-sequential images using hidden Markov modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Face recognition by independent component analysisIEEE Transactions on Neural Networks, 2002
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980