Multiple human action recognition from video streams

In recent times, the focus of researchers has been on understanding the human behavior under different circumstances. An important aspect of this research is to understand how a person would act in a given scenario. Human action recognition forms an integral part of such analysis. The objective of t...

Full description

Saved in:
Bibliographic Details
Main Author: Koh, Khai Huat
Other Authors: Teoh Eam Khwang
Format: Final Year Project
Language:English
Published: 2014
Subjects:
Online Access:http://hdl.handle.net/10356/60181
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-60181
record_format dspace
spelling sg-ntu-dr.10356-601812023-07-07T15:53:28Z Multiple human action recognition from video streams Koh, Khai Huat Teoh Eam Khwang School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering In recent times, the focus of researchers has been on understanding the human behavior under different circumstances. An important aspect of this research is to understand how a person would act in a given scenario. Human action recognition forms an integral part of such analysis. The objective of this project is to build a framework to recognize multiple human actions in different scenarios. Firstly, the author looks at several possible methods of human detection and action recognition. Each method is then evaluated based on the results obtained. Finally, the viability of each framework is discussed. In this project, the author combines two main methods to form the Multiple Human Action Recognition system. In the first technique, the human detection method, a Histogram of Oriented Gradient is used to extract the human features of the image. Next, the features are send into the Extreme Learning Machine classifier which predicts whether the image has a human. Sampled images with positive human detection are then compiled and passed to the second step. The second step involves preprocessing of compiled images, namely to extract the human subject from the image and the removal of background. Subsequently, the image is converted into a image mask for action feature extraction. In the action recognition process, features that represent an action are extracted. This is carried out via calculation of power spectrum feature from the image volume, and then sending it into the Weighted Euclidean Distance for possible match retrieval. Comparison is also done with the pose base feature to determine which method produce better results. The results detailed in this report consist of two sections, human detection and action recognition. Using a test time of 0.25 seconds, the reported results are at 94% accuracy for human detection with HOG features, 65% accuracy for Power spectrum features and 90% for pose base action features. These results are tested using MVU dataset. Bachelor of Engineering 2014-05-23T02:57:44Z 2014-05-23T02:57:44Z 2014 2014 Final Year Project (FYP) http://hdl.handle.net/10356/60181 en Nanyang Technological University 90 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::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Koh, Khai Huat
Multiple human action recognition from video streams
description In recent times, the focus of researchers has been on understanding the human behavior under different circumstances. An important aspect of this research is to understand how a person would act in a given scenario. Human action recognition forms an integral part of such analysis. The objective of this project is to build a framework to recognize multiple human actions in different scenarios. Firstly, the author looks at several possible methods of human detection and action recognition. Each method is then evaluated based on the results obtained. Finally, the viability of each framework is discussed. In this project, the author combines two main methods to form the Multiple Human Action Recognition system. In the first technique, the human detection method, a Histogram of Oriented Gradient is used to extract the human features of the image. Next, the features are send into the Extreme Learning Machine classifier which predicts whether the image has a human. Sampled images with positive human detection are then compiled and passed to the second step. The second step involves preprocessing of compiled images, namely to extract the human subject from the image and the removal of background. Subsequently, the image is converted into a image mask for action feature extraction. In the action recognition process, features that represent an action are extracted. This is carried out via calculation of power spectrum feature from the image volume, and then sending it into the Weighted Euclidean Distance for possible match retrieval. Comparison is also done with the pose base feature to determine which method produce better results. The results detailed in this report consist of two sections, human detection and action recognition. Using a test time of 0.25 seconds, the reported results are at 94% accuracy for human detection with HOG features, 65% accuracy for Power spectrum features and 90% for pose base action features. These results are tested using MVU dataset.
author2 Teoh Eam Khwang
author_facet Teoh Eam Khwang
Koh, Khai Huat
format Final Year Project
author Koh, Khai Huat
author_sort Koh, Khai Huat
title Multiple human action recognition from video streams
title_short Multiple human action recognition from video streams
title_full Multiple human action recognition from video streams
title_fullStr Multiple human action recognition from video streams
title_full_unstemmed Multiple human action recognition from video streams
title_sort multiple human action recognition from video streams
publishDate 2014
url http://hdl.handle.net/10356/60181
_version_ 1772828656821862400