Human detection and tracking in surveillance videos

This project aims to evaluate current human and object detection and tracking methods in surveillance video systems. Since foreground detection is the foremost requirement for tracking and other further studies, the attention of the project is on foreground detection. From the previous researches, f...

Full description

Saved in:
Bibliographic Details
Main Author: Ren, Yi.
Other Authors: Chan Kap Luk
Format: Final Year Project
Language:English
Published: 2013
Subjects:
Online Access:http://hdl.handle.net/10356/54453
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-54453
record_format dspace
spelling sg-ntu-dr.10356-544532023-07-07T17:18:35Z Human detection and tracking in surveillance videos Ren, Yi. Chan Kap Luk School of Electrical and Electronic Engineering DRNTU::Engineering This project aims to evaluate current human and object detection and tracking methods in surveillance video systems. Since foreground detection is the foremost requirement for tracking and other further studies, the attention of the project is on foreground detection. From the previous researches, four well-known detection methods have been analyzed, namely frame difference, OpenCV Gaussian mixture model, adaptive Gaussian mixture model and optical flow. At least one algorithm developed from each method has been implemented with the same dataset, in order to compare the performance of the methods. The dataset of this project consists of indoor dataset and outdoor dataset to provide a comprehensive analysis. From the result, BackgroundSubtractorMOG, one of the Gaussian mixture model methods, is suggested to be applied in a real-life surveillance video system. Because it is robust to background changes and it has a relatively fast processing speed. Bachelor of Engineering 2013-06-20T07:35:00Z 2013-06-20T07:35:00Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/54453 en Nanyang Technological University 45 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
Ren, Yi.
Human detection and tracking in surveillance videos
description This project aims to evaluate current human and object detection and tracking methods in surveillance video systems. Since foreground detection is the foremost requirement for tracking and other further studies, the attention of the project is on foreground detection. From the previous researches, four well-known detection methods have been analyzed, namely frame difference, OpenCV Gaussian mixture model, adaptive Gaussian mixture model and optical flow. At least one algorithm developed from each method has been implemented with the same dataset, in order to compare the performance of the methods. The dataset of this project consists of indoor dataset and outdoor dataset to provide a comprehensive analysis. From the result, BackgroundSubtractorMOG, one of the Gaussian mixture model methods, is suggested to be applied in a real-life surveillance video system. Because it is robust to background changes and it has a relatively fast processing speed.
author2 Chan Kap Luk
author_facet Chan Kap Luk
Ren, Yi.
format Final Year Project
author Ren, Yi.
author_sort Ren, Yi.
title Human detection and tracking in surveillance videos
title_short Human detection and tracking in surveillance videos
title_full Human detection and tracking in surveillance videos
title_fullStr Human detection and tracking in surveillance videos
title_full_unstemmed Human detection and tracking in surveillance videos
title_sort human detection and tracking in surveillance videos
publishDate 2013
url http://hdl.handle.net/10356/54453
_version_ 1772828540254814208