Study on Statistical Background Modeling for Visual Surveillance
碩士 === 國立成功大學 === 電機工程學系碩博士班 === 96 === The main purpose of a visual surveillance system is to detect suspicious objects or erratic changes in the environment. In a visual surveillance system, object tracking and object classification rely on the accuracy of motion detection. Therefore, it is essent...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2008
|
Online Access: | http://ndltd.ncl.edu.tw/handle/77158613559363237808 |
id |
ndltd-TW-096NCKU5442105 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-096NCKU54421052015-11-23T04:02:52Z http://ndltd.ncl.edu.tw/handle/77158613559363237808 Study on Statistical Background Modeling for Visual Surveillance 統計式背景模型應用於視覺監視之研究 Cheng-Chun Chung 鍾承君 碩士 國立成功大學 電機工程學系碩博士班 96 The main purpose of a visual surveillance system is to detect suspicious objects or erratic changes in the environment. In a visual surveillance system, object tracking and object classification rely on the accuracy of motion detection. Therefore, it is essential to quickly and accurately identify a moving object in an intricate environment. Background subtraction is commonly used in motion detection. The system must update the alteration of the environment into the background model quickly and accurately for best performance. A suitable background model for changing environments was developed in this thesis. In general, there are two methods of constructing a statistical background model. One is the parametric method, which includes the Gaussian mixture model and the spatial distribution of Gaussian. The other is the nonparametric method, which includes the kernel density estimation and the k-nearest neighbors method. In this thesis, several experiments have been conducted to provide a performance comparison between the Gaussian mixture model and kernel density estimation. Ming-Yang Cheng 鄭銘揚 2008 學位論文 ; thesis 82 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 電機工程學系碩博士班 === 96 === The main purpose of a visual surveillance system is to detect suspicious objects or erratic changes in the environment. In a visual surveillance system, object tracking and object classification rely on the accuracy of motion detection. Therefore, it is essential to quickly and accurately identify a moving object in an intricate environment. Background subtraction is commonly used in motion detection. The system must update the alteration of the environment into the background model quickly and accurately for best performance. A suitable background model for changing environments was developed in this thesis. In general, there are two methods of constructing a statistical background model. One is the parametric method, which includes the Gaussian mixture model and the spatial distribution of Gaussian. The other is the nonparametric method, which includes the kernel density estimation and the k-nearest neighbors method. In this thesis, several experiments have been conducted to provide a performance comparison between the Gaussian mixture model and kernel density estimation.
|
author2 |
Ming-Yang Cheng |
author_facet |
Ming-Yang Cheng Cheng-Chun Chung 鍾承君 |
author |
Cheng-Chun Chung 鍾承君 |
spellingShingle |
Cheng-Chun Chung 鍾承君 Study on Statistical Background Modeling for Visual Surveillance |
author_sort |
Cheng-Chun Chung |
title |
Study on Statistical Background Modeling for Visual Surveillance |
title_short |
Study on Statistical Background Modeling for Visual Surveillance |
title_full |
Study on Statistical Background Modeling for Visual Surveillance |
title_fullStr |
Study on Statistical Background Modeling for Visual Surveillance |
title_full_unstemmed |
Study on Statistical Background Modeling for Visual Surveillance |
title_sort |
study on statistical background modeling for visual surveillance |
publishDate |
2008 |
url |
http://ndltd.ncl.edu.tw/handle/77158613559363237808 |
work_keys_str_mv |
AT chengchunchung studyonstatisticalbackgroundmodelingforvisualsurveillance AT zhōngchéngjūn studyonstatisticalbackgroundmodelingforvisualsurveillance AT chengchunchung tǒngjìshìbèijǐngmóxíngyīngyòngyúshìjuéjiānshìzhīyánjiū AT zhōngchéngjūn tǒngjìshìbèijǐngmóxíngyīngyòngyúshìjuéjiānshìzhīyánjiū |
_version_ |
1718134048958709760 |