臺灣博碩士論文加值系統

目錄
指導教授推薦書..........................................................................................
口詴委員審定書..........................................................................................
致謝............................................................................................................iii
中文摘要 ................................................................................................... iv
英文摘要 .................................................................................................... v
目錄............................................................................................................ vi
圖目錄 .....................................................................................................viii
表目錄 ........................................................................................................ x
第一章 緒論 ........................................................................................... 1
1.1 研究背景與動機....................................................................... 1
1.2 文獻回顧 ................................................................................... 2
1.3 研究目的 ................................................................................... 7
1.4 論文架構 ................................................................................... 8
第二章 研究方法 ................................................................................. 10
2.1 硬體架構................................................................................... 10
2.1.1 個人電腦........................................................................ 10
2.1.2 影像擷取卡與攝影機.................................................... 10
2.2 軟體架構................................................................................... 12
2.2.1 Microsoft Visual C++ 2008 ............................................. 12
2.2.2 OpenCV........................................................................... 12
2.2.3 Qt Software...................................................................... 13
2.3 影像處理................................................................................... 13
2.3.1 影像擷取........................................................................ 14
2.3.2 追蹤演算法.................................................................... 14
2.4 多執行緒................................................................................... 20
第三章 實驗結果 ................................................................................. 21
3.1 演算法結果............................................................................... 21
3.2 演算法改良............................................................................... 27
3.2.1 增設更新閥值................................................................ 29
3.2.2 使用Halton sequence..................................................... 30
3.2.3 加入Adaboost (Adaptive Boosting)算法...................... 35
3.3 動態追蹤系統之實現............................................................... 39
3.4 人機介面................................................................................... 39
第四章 結論與未來方向..................................................................... 40
4.1 結論........................................................................................... 40
4.2 未來方向................................................................................... 41
參考文獻 .................................................................................................. 42
附錄........................................................................................................... 45
圖目錄
圖1.1 背景相減法................................ 3
圖 1.2 主動式輪廓偵測應用於交通監測............................... 4
圖 1.3 建立3D 模型................................. 5
圖 2.1 ADlink RTV-24 影像擷取卡................................ 11
圖 2.2 SONY EVI-D70 PTZ 攝影機................................11
圖 2.3 系統架構圖...............................13
圖 2.4 影像資料壓縮示意圖.............................. 17
圖 2.5 更新分類器..............................19
圖 2.6 Compressive Tracking 流程.................20
圖 3.1 圖樣化特徵位置及數值................. 22
圖 3.2 目標框與檢測區域關係圖................. 23
圖 3.3 Compressive Tracking 目標追蹤實現................. 24
圖 3.4 Compressive Tracking 目標發生遮擋交錯.................25
圖 3.5 Compressive Tracking 對影片”David”做人臉追蹤.................26
圖 3.6 改善後的Compressive Tracking 流程圖................. 28
圖 3.7 待測框特徵數經分類器所得的數值................. 29
圖 3.8 二維 Halton sequence 與二維隨機圖形比較................. 32
圖 3.9 二維 Halton sequence 用於畫面搜索................. 33
圖 3.10 增設閥值及應用Halton sequence 於Compressive Tracking..34
圖 3.11 Compressive Tracking 加入Adaboost (分類器為特徵)..... 36
圖 3.12 Compressive Tracking 加入Adaboost (分類器為模板)..... 37
圖3.13 人機介面..............................39
表目錄
表 3.1 Halton sequences b=2, m=1~10 的轉換過程............ 31
表 3.2 比較原演算法和改善後的追蹤結果................ 38

[1] H. Weiming, T. Tieniu, W. Liang, and S. Maybank, "A survey on
visual surveillance of object motion and behaviors," Systems, Man,
and Cybernetics, Part C: Applications and Reviews, IEEE
Transactions on, vol. 34, pp. 334-352, 2004.
[2] S. J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler,
"Tracking groups of people," Computer Vision and Image
Understanding, vol. 80, pp. 42-56, 2000.
[3] 鄒華龍, "即時的人物偵測與追蹤," 大同大學電機工程研究所,
碩士, 2002.
[4] A. Giachetti, "Matching techniques to compute image motion,"
Image and Vision Computing, vol. 18, pp. 247-260, 2000.
[5] 蔡孟儒, "應用即時視覺伺服系統實現平面輪廓追循," 國立東華
大學電機工程研究所, 碩士, 2001.
[6] 郭騰凱, "在複雜背景下以強健視覺伺服為基礎可自動調變倍率
之頭部追蹤系統," 台灣大學電機工程學研究所, 碩士, 2002.
[7] T. K. Kuo, L. C. Fu, J. H. Jean, P. Y. Chen, and Y. M. Chan,
"Zoom-based head tracker in complex environment," Control
Applications, 2002. Proceedings of the 2002 International
Conference on, vol.2, pp. 725-730, 2002.
[8] J. C. Tai, S. T. Tseng, C. P. Lin, and K. T. Song, "Real-time image
tracking for automatic traffic monitoring and enforcement
applications," Image and Vision Computing, vol. 22, pp. 485-501,
2004.
[9] S. T. Tseng and K. T. Song, "Real-time image tracking for traffic
- 43 -
monitoring," Intelligent Transportation Systems, 2002. Proceedings.
The IEEE 5th International Conference on, pp. 1-6, 2002.
[10] 王健權, "以數位影像處理搭配動態攝影機做即時人臉追蹤之研
究," 國立成功大學電機工程學系, 碩士, 2002.
[11] Q. Delamarre and O. Faugeras, "3D articulated models and
multiview tracking with physical forces," Computer Vision and
Image Understanding, vol. 81, pp. 328-357, 2001.
[12] N. Paragios and R. Deriche, "Geodesic active contours and level
sets for the detection and tracking of moving objects," IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 22,
pp. 266-280, 2000.
[13] 宋昭蓉, "循序權重取樣粒子濾波法實現全方位相機之多目標物
影像追蹤, " 台灣大學電機工程學研究所, 碩士, 2007.
[14] Z. Kalal, K. Mikolajczyk, and J. Matas, "Tracking-Learning-
Detection," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 34, pp. 1409-1422, 2012.
[15] 游源展, “光學追蹤平台的學習與偵測演算法之整合,” 長庚大學
機械工程研究所, 碩士, 2013.
[16] K. Zhang, L. Zhang, and M. H. Yang, "Real-Time Compressive
Tracking," ECCV 2012, Part III, LNCS 7574, pp. 866–879, 2012.
[17] G. Bradski, "The OpenCV library," Dr Dobbs Journal, vol. 25, pp.
120-126, 2000.
[18] G. R. Gary, " Computer Vision Face Tracking For Use in a
Perceptual User Interface," Intel Technology Journal, Q2, 1998.
[19] J. H. Halton, "Algorithm 247: Radical-inverse quasi-random point
sequence, " Communications of the ACM, vol. 7, pp. 701-702,
1964.
- 44 -
[20] Y. Freund and