Video annotation using convolution neural network

In this project, the problem addressed is human activity recognition (HAR) from video sequence. The focussing in this project is to annotate objects and actions in video using Convolutional Neural Network (CNN) and map their temporal relationship using full connected layer and softmax layer. The con...

全面介绍

Saved in:

书目详细资料
主要作者:	Wan Abd. Kadir, Wan Zahiruddin
格式:	Thesis
语言:	English
出版:	2018
主题:	TK Electrical engineering Electronics Nuclear engineering
在线阅读:	http://eprints.utm.my/id/eprint/79083/1/WanZahiruddinWAbdKadirMFKE2018.pdf
标签:	添加标签没有标签, 成为第一个标记此记录!

id	my-utm-ep.79083
record_format	uketd_dc
spelling	my-utm-ep.790832018-09-27T06:07:25Z Video annotation using convolution neural network 2018-01 Wan Abd. Kadir, Wan Zahiruddin TK Electrical engineering. Electronics Nuclear engineering In this project, the problem addressed is human activity recognition (HAR) from video sequence. The focussing in this project is to annotate objects and actions in video using Convolutional Neural Network (CNN) and map their temporal relationship using full connected layer and softmax layer. The contribution is a deep learning fusion framework that more effectively exploits spatial features from CNN model (Inception v3 model) and combined with fully connected layer and softmax layer for classifying the action in dataset. Dataset used was UCF11 with 11 classes of human action. This project also extensively evaluate their strength and weakness compared previous project. By combining both the set of features between Inception v3 model with fully connected layer and softmax layer can classify actions from UCF11 dataset effectively upto 100% for certain human actions. The lowest accuracy is 27% by using this method, because the background and motion is similar with other actions. The evaluation results demonstrate that this method can be used to classify action in video annotation. 2018-01 Thesis http://eprints.utm.my/id/eprint/79083/ http://eprints.utm.my/id/eprint/79083/1/WanZahiruddinWAbdKadirMFKE2018.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:108253 masters Universiti Teknologi Malaysia, Faculty of Electrical Engineering Faculty of Electrical Engineering
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	TK Electrical engineering Electronics Nuclear engineering
spellingShingle	TK Electrical engineering Electronics Nuclear engineering Wan Abd. Kadir, Wan Zahiruddin Video annotation using convolution neural network
description	In this project, the problem addressed is human activity recognition (HAR) from video sequence. The focussing in this project is to annotate objects and actions in video using Convolutional Neural Network (CNN) and map their temporal relationship using full connected layer and softmax layer. The contribution is a deep learning fusion framework that more effectively exploits spatial features from CNN model (Inception v3 model) and combined with fully connected layer and softmax layer for classifying the action in dataset. Dataset used was UCF11 with 11 classes of human action. This project also extensively evaluate their strength and weakness compared previous project. By combining both the set of features between Inception v3 model with fully connected layer and softmax layer can classify actions from UCF11 dataset effectively upto 100% for certain human actions. The lowest accuracy is 27% by using this method, because the background and motion is similar with other actions. The evaluation results demonstrate that this method can be used to classify action in video annotation.
format	Thesis
qualification_level	Master's degree
author	Wan Abd. Kadir, Wan Zahiruddin
author_facet	Wan Abd. Kadir, Wan Zahiruddin
author_sort	Wan Abd. Kadir, Wan Zahiruddin
title	Video annotation using convolution neural network
title_short	Video annotation using convolution neural network
title_full	Video annotation using convolution neural network
title_fullStr	Video annotation using convolution neural network
title_full_unstemmed	Video annotation using convolution neural network
title_sort	video annotation using convolution neural network
granting_institution	Universiti Teknologi Malaysia, Faculty of Electrical Engineering
granting_department	Faculty of Electrical Engineering
publishDate	2018
url	http://eprints.utm.my/id/eprint/79083/1/WanZahiruddinWAbdKadirMFKE2018.pdf
_version_	1747818142624645120

Video annotation using convolution neural network

相似书籍