Cargando…
Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis
Video-based human activity recognition (HAR) means the analysis of motions and behaviors of human from the low level sensors. Over the last decade, automatic HAR is an exigent research area and is considered a significant concern in the field of computer vision and pattern recognition. In this paper...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2014
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4029654/ https://www.ncbi.nlm.nih.gov/pubmed/24714390 http://dx.doi.org/10.3390/s140406370 |
_version_ | 1782317250221441024 |
---|---|
author | Siddiqi, Muhammad Hameed Ali, Rahman Rana, Md. Sohel Hong, Een-Kee Kim, Eun Soo Lee, Sungyoung |
author_facet | Siddiqi, Muhammad Hameed Ali, Rahman Rana, Md. Sohel Hong, Een-Kee Kim, Eun Soo Lee, Sungyoung |
author_sort | Siddiqi, Muhammad Hameed |
collection | PubMed |
description | Video-based human activity recognition (HAR) means the analysis of motions and behaviors of human from the low level sensors. Over the last decade, automatic HAR is an exigent research area and is considered a significant concern in the field of computer vision and pattern recognition. In this paper, we have presented a robust and an accurate activity recognition system called WS-HAR that consists of wavelet transform coupled with stepwise linear discriminant analysis (SWLDA) followed by hidden Markov model (HMM). Symlet wavelet has been employed in order to extract the features from the activity frames. The most prominent features were selected by proposing a robust technique called stepwise linear discriminant analysis (SWLDA) that focuses on selecting the localized features from the activity frames and discriminating their class based on regression values (i.e., partial F-test values). Finally, we applied a well-known sequential classifier called hidden Markov model (HMM) to give the appropriate labels to the activities. In order to validate the performance of the WS-HAR, we utilized two publicly available standard datasets under two different experimental settings, n–fold cross validation scheme based on subjects; and a set of experiments was performed in order to show the effectiveness of each approach. The weighted average recognition rate for the WS-HAR was 97% across the two different datasets that is a significant improvement in classication accuracy compared to the existing well-known statistical and state-of-the-art methods. |
format | Online Article Text |
id | pubmed-4029654 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2014 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-40296542014-05-22 Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis Siddiqi, Muhammad Hameed Ali, Rahman Rana, Md. Sohel Hong, Een-Kee Kim, Eun Soo Lee, Sungyoung Sensors (Basel) Article Video-based human activity recognition (HAR) means the analysis of motions and behaviors of human from the low level sensors. Over the last decade, automatic HAR is an exigent research area and is considered a significant concern in the field of computer vision and pattern recognition. In this paper, we have presented a robust and an accurate activity recognition system called WS-HAR that consists of wavelet transform coupled with stepwise linear discriminant analysis (SWLDA) followed by hidden Markov model (HMM). Symlet wavelet has been employed in order to extract the features from the activity frames. The most prominent features were selected by proposing a robust technique called stepwise linear discriminant analysis (SWLDA) that focuses on selecting the localized features from the activity frames and discriminating their class based on regression values (i.e., partial F-test values). Finally, we applied a well-known sequential classifier called hidden Markov model (HMM) to give the appropriate labels to the activities. In order to validate the performance of the WS-HAR, we utilized two publicly available standard datasets under two different experimental settings, n–fold cross validation scheme based on subjects; and a set of experiments was performed in order to show the effectiveness of each approach. The weighted average recognition rate for the WS-HAR was 97% across the two different datasets that is a significant improvement in classication accuracy compared to the existing well-known statistical and state-of-the-art methods. MDPI 2014-04-04 /pmc/articles/PMC4029654/ /pubmed/24714390 http://dx.doi.org/10.3390/s140406370 Text en © 2014 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/3.0/). |
spellingShingle | Article Siddiqi, Muhammad Hameed Ali, Rahman Rana, Md. Sohel Hong, Een-Kee Kim, Eun Soo Lee, Sungyoung Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis |
title | Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis |
title_full | Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis |
title_fullStr | Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis |
title_full_unstemmed | Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis |
title_short | Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis |
title_sort | video-based human activity recognition using multilevel wavelet decomposition and stepwise linear discriminant analysis |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4029654/ https://www.ncbi.nlm.nih.gov/pubmed/24714390 http://dx.doi.org/10.3390/s140406370 |
work_keys_str_mv | AT siddiqimuhammadhameed videobasedhumanactivityrecognitionusingmultilevelwaveletdecompositionandstepwiselineardiscriminantanalysis AT alirahman videobasedhumanactivityrecognitionusingmultilevelwaveletdecompositionandstepwiselineardiscriminantanalysis AT ranamdsohel videobasedhumanactivityrecognitionusingmultilevelwaveletdecompositionandstepwiselineardiscriminantanalysis AT hongeenkee videobasedhumanactivityrecognitionusingmultilevelwaveletdecompositionandstepwiselineardiscriminantanalysis AT kimeunsoo videobasedhumanactivityrecognitionusingmultilevelwaveletdecompositionandstepwiselineardiscriminantanalysis AT leesungyoung videobasedhumanactivityrecognitionusingmultilevelwaveletdecompositionandstepwiselineardiscriminantanalysis |