![]() |
|
以作者查詢圖書館館藏 、以作者查詢臺灣博碩士 、以作者查詢全國書目 、勘誤回報 、線上人數:22 、訪客IP:3.144.3.63
姓名 蘇耘德(Yun-Te Su) 查詢紙本館藏 畢業系所 土木工程學系 論文名稱 視訊資料中移動物體軌跡之萃取
(The Extraction of the Track and the Route of Moving Objects on the Video Images)相關論文 檔案 [Endnote RIS 格式]
[Bibtex 格式]
[相關文章]
[文章引用]
[完整記錄]
[館藏目錄]
[檢視]
[下載]
- 本電子論文使用權限為同意立即開放。
- 已達開放權限電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
- 請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
摘要(中) 為了進行自動化地從視訊資料中萃取出移動物體的軌跡與路徑線,本研究的視訊資料是利用固定方位與視角的攝影機,以一至兩台正在移動的機車或汽車為目標,由高處拍攝地面取得。利用以下3步驟對視訊資料進行軌跡與路徑線的萃取:1. 興趣視訊段落萃取:利用背景影像將減法快速偵測出視訊資料中含有移動物體的興趣視訊段落,並且將其萃取出來,以利後續的軌跡萃取與路徑線萃取等步驟;2. 軌跡萃取:利用主成分分析(Principal Component Analysis,PCA)與區域增長法為主的步驟,從各個興趣視訊段落中萃取出移動物體的軌跡;3. 路徑線萃取:萃取出軌跡的中心線作為路徑線,並針對不同的路徑線型態對路徑線進行匹配,得到物體的移動路徑線與方向。測試影片包含了單一移動物體、平行軌跡雙物體、X型軌跡雙物體、Y型軌跡雙物體等不同型態的興趣視訊段落。三段影片的測試結果顯示,不論測試影片中的各興趣視訊段落的型態為上述何者,本研究都能夠從測試影片中將其萃取出來,並且從興趣視訊段落中萃取出移動物體軌跡,且利用軌跡更進一步萃取出物體移動的路徑線與移動方向。 摘要(英) In order to extract the track and route of moving object from the video token by a static camera (which means a camera with fixed position and view angel), there are three steps in our algorithm: (1) Interest Clip Extraction: an interested clip means the clip containing moving object .The main purpose of this step is using background subtraction method to detect moving object and extracting interest clips from video data rapidly. (2) Track Extraction: this step employs principal component analysis (PCA) on each interested clips to produce principal component (PC) images, and then uses the segmentation technique to extract track regions from each PC images.(3) Route Extraction: this step extracts the central route from each interested clips, and applies different route matching algorithm on different type of route. In the end, we extract the routes with the direction of each moving objects.
The test data includes number of moving objects in each interested clip that contains: (1) An interested clip that has only single moving object. (2) An interested clip that has two moving objects move with parallel track. (3) An interested clip that has two moving objects move with X-shaped track. (4) An interested clip that has two moving objects move with Y-shaped track. The experimental result indicates that our algorithm is able to reach the goal of extracting the track and route of moving object from each set of video data.關鍵字(中) ★ 視訊資料
★ 主成分分析
★ 路徑線
★ 軌跡
★ 移動物體關鍵字(英) ★ PCA
★ route
★ track
★ moving object
★ video論文目次 第一章 序論 1
1-1 研究背景與動機 1
1-2 文獻回顧 2
1-2-1 影像相減法 2
1-2-1-1 背景影像相減法 2
(a)背景影像之產生 3
(b)利用背景影像相減法追蹤移動物體 5
1-2-1-2 時序相減法 7
1-2-2 特徵匹配法 9
1-3 研究目的與論文架構 10
第二章 研究方法 12
2-1 興趣視訊段落萃取 14
2-1-1 前處理 15
2-1-2 背景影像相減 17
2-1-3 取出興趣視訊段落 18
2-2 軌跡萃取 20
2-2-1 興趣視訊段落之主成分分析 21
2-2-1-1 PCA的數學原理 23
2-2-1-2 興趣視訊段落之PC影像獲取 26
2-2-2 軌跡影像萃取 28
2-2-2-1 區塊分割 29
2-2-2-2 去除雜訊與背景 30
2-2-2-3 找出軌跡 31
2-2-3 軌跡填補 32
2-3 路徑線萃取 34
2-3-1 移動物體搜尋 35
2-3-1-1 物體點位萃取 36
2-3-1-1-1 雜訊濾除 37
2-3-1-1-2 填補物件 38
2-3-1-1-3 質心萃取 38
2-3-1-2 起點與終點搜尋 39
2-3-2 路徑線影像萃取 41
2-3-2-1 軌跡細線化 42
2-3-2-2 去除分支線 45
2-3-2-2-1 端點搜尋 45
2-3-2-2-2 起點終點匹配與分支線去除 46
2-3-3 移動物體路徑線匹配 47
2-3-3-1 路徑線型態判定 49
2-3-3-1-1 交會點搜尋 50
2-3-3-1-2 路徑線分段與型態判定 51
2-3-3-1-3 點對線匹配 51
2-3-3-2 Y型路徑線匹配 52
2-3-3-3 X型路徑線匹配 52
第三章 測試資料 55
3-1 測試影片1 56
3-1-1 影片內容 56
3-2 測試影片2 60
3-2-1 影片內容 60
3-3 測試影片3 64
3-3-1 影片內容 64
第四章 測試結果與討論 68
4-1 測試影片1 68
4-1-1 興趣視訊段落萃取 68
4-1-2 軌跡萃取 70
4-1-2-1 測試影像1之第一段興趣視訊段落 71
4-1-2-2 測試影像1之第二段興趣視訊段落 73
4-1-3 路徑線萃取 75
4-1-3-1 測試影像1之第一段興趣視訊段落 75
4-1-3-2 測試影像1之第二段興趣視訊段落 76
4-2 測試影片2 77
4-2-1 興趣視訊段落萃取 77
4-2-2 軌跡萃取 79
4-2-2-1 測試影像2之第一段興趣視訊段落 80
4-2-2-2 測試影像2之第二段興趣視訊段落 82
4-2-3 路徑線萃取 84
4-2-3-1 測試影像2之第一段興趣視訊段落 84
4-2-3-2 測試影像2之第二段興趣視訊段落 85
4-3 測試影片3 86
4-3-1 興趣視訊段落萃取 86
4-3-2 軌跡萃取 88
4-3-2-1 測試影像3之第一段興趣視訊段落 89
4-3-2-2 測試影像3之第二段興趣視訊段落 91
4-3-3 路徑線萃取 93
4-3-3-1 測試影像3之第一段興趣視訊段落 93
4-3-3-2 測試影像3之第二段興趣視訊段落 94
第五章 與背景影像相減法的成果比較 96
5-1 背景影像相減法之路徑線萃取演算法 96
5-1-1 產生漸進式背景影像 96
5-1-2 產生Blob 97
5-1-3 追蹤移動物體 97
5-2 背景影像相減法之路徑線萃取成果 97
5-2-1 測試影片1 98
5-2-1-1 測試影像1之第一段興趣視訊 98
5-2-1-2 測試影像1之第二段興趣視訊 99
5-2-2 測試影片2 100
5-2-2-1 測試影像2之第一段興趣視訊 100
5-2-2-2 測試影像2之第二段興趣視訊 101
5-2-3 測試影片3 102
5-2-3-1 測試影像3之第一段興趣視訊 103
5-2-3-2 測試影像3之第二段興趣視訊 104
5-3 成果分析 104
第六章 結論與建議 106
6-1 結論 106
6-2 建議 108
參考文獻 110參考文獻 王俊明及陳世旺,2002,「漸進背景影像的建構」,師大學報:數理與科技類,47(2),43-54.
Arseneau, S., and J. R. Cooperstock, 1999. Presenter Tracking in a Classroom Environment, The 25th Annual Conference of the IEEE on Industrial Electronics Society, Vol. 1, 145-148.
Heikkil?, J. and O. Silv?n, 2004. A Real-Time System for Monitoring of Cyclists and Pedestrians, Image and Vision Computing, Vol. 22, Issue 7, 563-570.
KaewTrakulPong, P. and R. Bowden, 2003. A Real Time Adaptive Visual Surveillance System for Tracking Low-Resolution Colour Targets in Dynamically Changing Scenes, Image and Vision Computing, Vol. 21, Issue 10,913-929.
Kim, J. B. and H. J. Kim, 2003. Efficient Region-Based Motion Segmentation for a Video Monitoring System, Pattern Recognition Letters, Vol. 24, Issue 1-3, 113-128.
Lai, A. H. S. and N. H. C. Yung, 1998. A Fast and Accurate Scoreboard Algorithm for Estimating Stationary Background in an Image Sequence, Proc. of IEEE Int’l Symp. on Circuits and Systems, Vol. 4, 241-244.
Lipton, A. J, H. Fujiyoshi, and R. S. Patil, 1998. Moving Target Classification and Tracking from Real-Time Video, Proc. of IEEE Workshop on Applications of Computer Vision, Vol. 4, 8-14.
Makris, D. and T. Ellis, 2002. Path Detection in Video Surveillance, Image and Vision Computing, Vol. 20, Issue 12, 895-903.
Masoud, O. and N. P. Papanikolopoulos, 2001. A Novel Method for Tracking and Counting Pedestrians in Real-Time using a Single Camera, IEEE trans. Vehicular Tech., Vol. 50, No. 5, 1267-1278.
Pai, C. J., H. R. Tyan, Y. M. Liang, H. Y. M. Liao, and S. W. Chen, 2004. Pedestrian Detection and Tracking at Crossroads, Pattern Recognition, Vol. 37, Issue 5, 1025-1034.
Rigoll, G. H. Breit, and F. Wallhoff, 2004. Robust Tracking of Persons in Real-World Scenarios Using a Statistical Computer Vision Approach, Image and Vision Computing, Vol. 22, Issue 7, 571-582.
Shao, J., S. K. Zhou, and Q. Zheng, 2004. Robust Appearance-Based Tracking of Moving Object from Moving Platform, Proc. of IEEE on Pattern Recognition, Vol. 4, 215-218.
Shin, J., S. Kim, S. Kang, S. W. Lee, J. Paik, B. Abidi, and M. Abidi, 2005. Optical Flow-Based Real-Time Object Tracking Using Non-Prior Training Active Feature Model, Real-Time Imaging, Vol. 11, Issue 3, 204-218.
Smith, L. I., 2002. A Tutorial on Principal Components Analysis, http://neurobot.bio.auth.gr/archives/000012a_tutorial_on_principal_components_analysis.php
Yung, N. H. C. and A. H. S. Lai, 2001. An Effective Video Analysis Method for Detecting Red Light Runners, IEEE trans. Vehicular Tech., Vol. 50, No. 4, 1074-1084.
Zaletelj, J. and J. F. Tasic, 2001. Video Object Segmentation Based on Edge Tracking, Proc. of IEEE on Image Processing, Vol. 2, 813-816.
Zhang, T. Y. and C. Y. Suen, 1984. A Fast Parallel Algorithm for Thinning Digital Patterns., Comm. ACM, Vol. 27, No. 3, 236-239.指導教授 陳繼藩(Chi-Farn Chen) 審核日期 2006-7-11 推文 plurk
funp
live
udn
HD
myshare
netvibes
friend
youpush
delicious
baidu
網路書籤 Google bookmarks
del.icio.us
hemidemi
myshare