Pose-based approach for human action recognition

In the recent times, human action recognition has been active research area in computer vision research due to the increase of security threats like terrorism and proliferation of advanced technologies used between the interaction of human and electronic devices. The objective of this project is to...

Full description

Saved in:
Bibliographic Details
Main Author: Kong, Richard Jia Qing
Other Authors: Teoh Eam Khwang
Format: Final Year Project
Language:English
Published: 2014
Subjects:
Online Access:http://hdl.handle.net/10356/60199
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-60199
record_format dspace
spelling sg-ntu-dr.10356-601992023-07-07T16:04:28Z Pose-based approach for human action recognition Kong, Richard Jia Qing Teoh Eam Khwang School of Electrical and Electronic Engineering DRNTU::Engineering In the recent times, human action recognition has been active research area in computer vision research due to the increase of security threats like terrorism and proliferation of advanced technologies used between the interaction of human and electronic devices. The objective of this project is to look at the possibility of using pose-based approach for human action recognition, and examine its usability and performance using various methodologies. Multi-view of human action is designed with two main methods. Firstly, in the action representation method, the human body is used as a posture vectors to train the Self-Organizing Map (SOM), which in turn, produces a topographic map. This map shows the key poses that represent the entire action videos. Next, the posture vectors are mapped into the Fuzzy Membership Vectors to produce the action videos. Each action video is a feature of an action. In the second method, action classification, different classifiers like Backpropagation Training Algorithm, Extreme Learning Machine (ELM) and Naïve Bayes Classifier were chosen to classify the action classes. Backpropagation Training Algorithm was chosen because of its ability to solve non-linearly separable problems. To achieve the concurrent objectives of short computing time and high accuracy in multi-class classification, ELM was chosen. Lastly, in the Naïve Bayes classifier, a tiny portion of data is required to approximate the mean and variance of the variable needed for classification. The robustness of this aforementioned system was tested on 4 events from WVU multi-view Action Recognition datasets and 10 actions from single view Weizmann datasets. This system was subsequently compared with the power spectrum feature technique. It was shown that human action recognition using posed-based approach proved superior to power spectrum feature technique. Bachelor of Engineering 2014-05-23T06:26:19Z 2014-05-23T06:26:19Z 2014 2014 Final Year Project (FYP) http://hdl.handle.net/10356/60199 en Nanyang Technological University 144 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering
spellingShingle DRNTU::Engineering
Kong, Richard Jia Qing
Pose-based approach for human action recognition
description In the recent times, human action recognition has been active research area in computer vision research due to the increase of security threats like terrorism and proliferation of advanced technologies used between the interaction of human and electronic devices. The objective of this project is to look at the possibility of using pose-based approach for human action recognition, and examine its usability and performance using various methodologies. Multi-view of human action is designed with two main methods. Firstly, in the action representation method, the human body is used as a posture vectors to train the Self-Organizing Map (SOM), which in turn, produces a topographic map. This map shows the key poses that represent the entire action videos. Next, the posture vectors are mapped into the Fuzzy Membership Vectors to produce the action videos. Each action video is a feature of an action. In the second method, action classification, different classifiers like Backpropagation Training Algorithm, Extreme Learning Machine (ELM) and Naïve Bayes Classifier were chosen to classify the action classes. Backpropagation Training Algorithm was chosen because of its ability to solve non-linearly separable problems. To achieve the concurrent objectives of short computing time and high accuracy in multi-class classification, ELM was chosen. Lastly, in the Naïve Bayes classifier, a tiny portion of data is required to approximate the mean and variance of the variable needed for classification. The robustness of this aforementioned system was tested on 4 events from WVU multi-view Action Recognition datasets and 10 actions from single view Weizmann datasets. This system was subsequently compared with the power spectrum feature technique. It was shown that human action recognition using posed-based approach proved superior to power spectrum feature technique.
author2 Teoh Eam Khwang
author_facet Teoh Eam Khwang
Kong, Richard Jia Qing
format Final Year Project
author Kong, Richard Jia Qing
author_sort Kong, Richard Jia Qing
title Pose-based approach for human action recognition
title_short Pose-based approach for human action recognition
title_full Pose-based approach for human action recognition
title_fullStr Pose-based approach for human action recognition
title_full_unstemmed Pose-based approach for human action recognition
title_sort pose-based approach for human action recognition
publishDate 2014
url http://hdl.handle.net/10356/60199
_version_ 1772828502984228864