Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms
碩士 === 國立高雄大學 === 資訊工程學系碩士班 === 103 === In top-view surveillance videos, head tracking can monitor the number of persons entering and leaving a building without more hardware requirements. In this research, we tried to use circle Hough transforms (CHT) to do head tracking. The CHT is one of major to...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2015
|
Online Access: | http://ndltd.ncl.edu.tw/handle/60885121511128430782 |
id |
ndltd-TW-103NUK05392007 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-103NUK053920072016-08-17T04:23:21Z http://ndltd.ncl.edu.tw/handle/60885121511128430782 Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms 應用圓形霍夫轉換於俯視影像中人頭移動軌跡之偵測 Po-yi Lee 李柏儀 碩士 國立高雄大學 資訊工程學系碩士班 103 In top-view surveillance videos, head tracking can monitor the number of persons entering and leaving a building without more hardware requirements. In this research, we tried to use circle Hough transforms (CHT) to do head tracking. The CHT is one of major tools to find round objects in images with many successful applications. However, human heads are not pure round objects, but have variations such as different hair styles, bald, and wearing hats. To overcome this, repeated tests were made on the same image objects across frames. From binomial distributions, the increased recognition rates were mathematically validated. In the experiments on the videos without nonhuman objects such as umbrellas, the CHT with repeated tests have over than 90% accuracy. Finally, experimental results showed that in crowded top-view surveillance videos, our system can effectively track and count the numbers of people ingoing or outgoing the gate with the average accuracy rate of 88.68%. Tang-kai Yin 殷堂凱 2015 學位論文 ; thesis 61 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立高雄大學 === 資訊工程學系碩士班 === 103 === In top-view surveillance videos, head tracking can monitor the number of persons entering and leaving a building without more hardware requirements. In this research, we tried to use circle Hough transforms (CHT) to do head tracking. The CHT is one of major tools to find round objects in images with many successful applications. However, human heads are not pure round objects, but have variations such as different hair styles, bald, and wearing hats. To overcome this, repeated tests were made on the same image objects across frames. From binomial distributions, the increased recognition rates were mathematically validated. In the experiments on the videos without nonhuman objects such as umbrellas, the CHT with repeated tests have over than 90% accuracy. Finally, experimental results showed that in crowded top-view surveillance videos, our system can effectively track and count the numbers of people ingoing or outgoing the gate with the average accuracy rate of 88.68%.
|
author2 |
Tang-kai Yin |
author_facet |
Tang-kai Yin Po-yi Lee 李柏儀 |
author |
Po-yi Lee 李柏儀 |
spellingShingle |
Po-yi Lee 李柏儀 Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms |
author_sort |
Po-yi Lee |
title |
Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms |
title_short |
Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms |
title_full |
Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms |
title_fullStr |
Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms |
title_full_unstemmed |
Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms |
title_sort |
head detection and tracking in top-view videos using circle hough transforms |
publishDate |
2015 |
url |
http://ndltd.ncl.edu.tw/handle/60885121511128430782 |
work_keys_str_mv |
AT poyilee headdetectionandtrackingintopviewvideosusingcirclehoughtransforms AT lǐbǎiyí headdetectionandtrackingintopviewvideosusingcirclehoughtransforms AT poyilee yīngyòngyuánxínghuòfūzhuǎnhuànyúfǔshìyǐngxiàngzhōngréntóuyídòngguǐjīzhīzhēncè AT lǐbǎiyí yīngyòngyuánxínghuòfūzhuǎnhuànyúfǔshìyǐngxiàngzhōngréntóuyídòngguǐjīzhīzhēncè |
_version_ |
1718378066903826432 |