國立高雄大學圖資館 |

Language: English

Back

應用圓形霍夫轉換於俯視影像中人頭移動軌跡之偵測 = Head Detec...

國立高雄大學資訊工程學系碩士班

應用圓形霍夫轉換於俯視影像中人頭移動軌跡之偵測 = Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms

Record Type:	Language materials, printed : monographic
Paralel Title:	Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms
Author:	李柏儀,
Secondary Intellectual Responsibility:	國立高雄大學
Place of Publication:	[高雄市]
Published:	撰者;
Year of Publication:	2015[民104]
Description:	61面圖，表 : 30公分;
Subject:	圓形霍夫轉換
Subject:	Circle Hough Transforms
Online resource:	http://handle.ncl.edu.tw/11296/ndltd/35268972884364797418
Notes:	104年10月31日公開
Notes:	參考書目：面49-52
Summary:	在俯視(top-view)的監視器影像中,使用人頭追蹤來統計行人進入與離開建築物的數量,是不需要額外硬體的。在本研究中,我們使用霍夫轉換圓偵測(circle Hough transforms),來實現人頭追蹤;視訊影像中尋找圓形物體時,霍夫轉換圓偵測一直是主要的工具之一且有許多成功的應用。然而,人的頭不是純粹的圓形物體,它會有各種變化,如不同的髮型、光頭、戴帽子等等。為了克服這個,我們對同一個圓形物體在不同幀(frame)上的影像進行反覆試驗,在數學的驗證二項式分佈下,提高了人頭偵測的準確率;在沒有非人物體(如雨傘)的實驗中,反覆試驗的霍夫轉換圓偵測有超過90%的準確率。最後人數統計的實驗結果顯示,在人數眾多且擁擠的俯視影像中,我們的系統能有效地追蹤行人與計算行人,平均正確率達到88.68%。 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%.

應用圓形霍夫轉換於俯視影像中人頭移動軌跡之偵測 = Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms
李, 柏儀

應用圓形霍夫轉換於俯視影像中人頭移動軌跡之偵測 = Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms / 李柏儀撰 - [高雄市] : 撰者, 2015[民104]. - 61面 ; 圖，表 ; 30公分.
104年10月31日公開參考書目：面49-52.
圓形霍夫轉換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 = Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms
LDR:03075nam0a2200289 450 001 458394
005 20170214101001.0
009 458394
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214d2015 k y0chiy50 e
101 0 $a chi
102 $a tw
105 $a ak am 000yy
200 1 $a 應用圓形霍夫轉換於俯視影像中人頭移動軌跡之偵測 $d Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms $z eng $f 李柏儀撰
210 $a [高雄市] $c 撰者 $d 2015[民104]
215 0 $a 61面 $c 圖，表 $d 30公分
300 $a 104年10月31日公開
300 $a 參考書目：面49-52
314 $a 指導教授：殷堂凱博士
328 $a 碩士論文--國立高雄大學資訊工程學系碩士班
330 $a 在俯視(top-view)的監視器影像中,使用人頭追蹤來統計行人進入與離開建築物的數量,是不需要額外硬體的。在本研究中,我們使用霍夫轉換圓偵測(circle Hough transforms),來實現人頭追蹤;視訊影像中尋找圓形物體時,霍夫轉換圓偵測一直是主要的工具之一且有許多成功的應用。然而,人的頭不是純粹的圓形物體,它會有各種變化,如不同的髮型、光頭、戴帽子等等。為了克服這個,我們對同一個圓形物體在不同幀(frame)上的影像進行反覆試驗,在數學的驗證二項式分佈下,提高了人頭偵測的準確率;在沒有非人物體(如雨傘)的實驗中,反覆試驗的霍夫轉換圓偵測有超過90%的準確率。最後人數統計的實驗結果顯示,在人數眾多且擁擠的俯視影像中,我們的系統能有效地追蹤行人與計算行人,平均正確率達到88.68%。 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%.
510 1 $a Head Detection and Tracking in Top-View Videos Using Circle Hough Transforms $z eng
610 0 $a 圓形霍夫轉換 $a 人頭追蹤 $a 俯視影像 $a 人數計數
610 1 $a Circle Hough Transforms $a Head Tracking $a Top-View Videos $a People Counting
681 $a 008M/0019 $b 464103 4042.1 $v 2007年版
700 1 $a 李 $b 柏儀 $4 撰 $3 709638
712 0 2 $a 國立高雄大學 $b 資訊工程學系碩士班 $3 353878
801 0 $a tw $b NUK $c 20151021 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/35268972884364797418