| 研究生: |
黃俊霖 Huang, Chun-lin |
|---|---|
| 論文名稱: |
以CamShift演算法為基礎之目標物即時影像追蹤系統設計與實現 Design of Real-Time Object Tracking System Using CamShift Algorithm |
| 指導教授: |
廖德祿
Liao, Teh-lu |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 工程科學系 Department of Engineering Science |
| 論文出版年: | 2009 |
| 畢業學年度: | 97 |
| 語文別: | 中文 |
| 論文頁數: | 44 |
| 中文關鍵詞: | 目標物追蹤 、移動物偵測 、USB介面 、白平衡 |
| 外文關鍵詞: | USB Interface, CamShift, Lam, Object Tracking |
| 相關次數: | 點閱:94 下載:2 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
視覺是人類最先進的感官,所以影像在人的感知上扮演著極為重要的角色;隨著電腦科技不斷的進步,影像處理的技術也日益的成熟。但過往移動物的偵測與追蹤皆以定點式攝影機為主;當移動物移出鏡頭外,便無法再進行追蹤,為改善此項缺點,以及減少攝影死角,本論文提出目標物即時影像追蹤系統,由一8051架構且具USB2.0功能的MCU以GPIO擷取PAS6311 CMOS Sensor的Bayer矩陣資料,透過USB2.0的BULK傳輸模式送至電腦端,以雙線性內插法,還原成彩色影像資料;再透過Lam自動白平衡演算法,修正影像顏色,並藉由邊緣化與影像相減等方法計算出移動物座標。而針對移動物座標周圍,利用HSV 色彩模型之H(色相)分析其顏色直方圖並計算出顏色分佈機率函數,再透過CamShift演算法對該移動物之顏色進行追蹤。最後由電腦端透過USB下達移動命令給MCU驅動3顆直流馬達,分別為上下、左右與飛彈發射功能,藉此達到移動物追蹤並攻擊的效果;經驗證後確實可以有效偵測移動物並進行追蹤。
Vision was the most advanced sense of human, and it holds a very responsible sense for image capture. Computer techno is moving forward, the technical innovations in image process was maturity, but not completed. In convention, most image target detecting and tracking was based on build-in video camera. Unfortunately, it will inactive when the target out of the shoot. This thesis addressed one real-time target tracking system methodology for improving the tracking dead-zone. Whole system integrates embedded USB 2.0 engine 8051-based MCU, PAS6311LT CMOS image sensor, 3-dimensions DC motor driving controller and addressed image processing algorithm. In the hardware driving part, MCU captures the digital image data and passes through to computer via USB interface channel. Major image processing and tracking algorithm implementation was based on computer (includes Bayer pattern transfer, bilinear interpolation, Lam auto white balance, HSV color space analyze and CamShift algorithm, etc.) This thesis applies addressed methodology in a “Launching-Pads” module to verify the performance, from exprimental, addressed methodology is proved to work well and effective.
[1]“Universal Serial Bus Specification”, USB Implementers Forum, Reversion 2.0, 2000.
[2]“EZ-USB FX2 Technical Reference Manual”, Cypress Semiconductor, Version 2.2, 2001.
[3]“CY7C68013 EZ-USB FX2 USB Microcontroller High-Speed USB Peripheral Controller” ,Cypress Semiconductor,2002.
[4]“USB device with serial interface”, Philips Semiconductor, 1998.
[5]“FS7805 Memory Map & Register Description”, Preliminary, Revision 1.0 ,2006.
[6]“FS7805 Security Built-In High Speed USB Peripheral”, FameG, Revision 1.2, 2007.
[7]“T5B Chip Design Target Specification”, Ethan Jang, 2007.
[8]“PAS6311 Application Note”, PixArt Imaging Inc. ,2007.
[9]“PAS6311LT Specification”, PixArt Imaging Inc. ,2007.
[10]E. Y. Lam, “Combining Gray World and Retinex Theory for AutomaticWhite Balance in Digital Photography”, Proceedings of the Ninth International Symposiumon Consumer Electronics, 2005.
[11]F. Gasparini and R. Schettini, “Color correction for digital photographs” , Proceedings of the 12th International Conference on Image Analysis and Processing, 2003.
[12]Gary R. Bradski, “Computer Vision Face Tracking For Use in a Perceptual User Interface” Intel Technology Journal , Microcomputer Research Lab,1998.
[13]D. Comaniciu, and P. Meer, “Mean Shift: A Robust Approach toward Feature SpaceAnalysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002.
[14]G. Allen John, Y. D. Xu Richard, S. Jin Jesse “Object Tracking Using CamShift Algorithm and Multiple Quantized Feature Spaces”, Madsen Building F09, University of Sydney,2006.
[15]W. Brand, “Morphable 3D models from video” , in Proc. of the 2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 2001.
[16]J. F. Cohn, A. J. Zlochower, J. J. Lien and T. Kanade, “feature-point tracking by optical flow discriminates subtle differences in facial expression” , in Proc. of the 3th International Conference on Automatic Face and Gesture Recognition, 1998.
[17]J. L. Barron, D. J. Fleet, S. S. Beauchemin and T. A. Burkitt, “Performance of Optical Flow Techniques,” in Proc. of the 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992.
[18]F. Gasparini, R. Schettini, “Color correction for digital photographs,” Proceedings of the 12th International Conference on Image Analysis and Processing, 2003.
[19]薛棟樑、許永和,“USB FX2軟體發展平台之操作與應用”,長高科技股份有限公司,2004.
[20]許永和,“USB2.0高速週邊裝置設計之實務應用”,全華科技圖書,2006.
[21]許永和,“微理機-USB週邊裝置設計與應用”,長高科技股份有限公司,2002.
[22]程俊卿,“以FGPA及USB介面為基礎之無線MP3廣播系統設計與實現”,國立成功大學工程科學研究所,碩士論文,2007.
[23]Gonzalez Woods, “Digital Image Processing 2/e”, Pearson Education Taiwan, 2007.
[24]黃國峰,張真誠,陳同孝,“數位影像處理技術”,旗標圖書,2004.
[25]王俊凱,“基於改良式適應性背景相減法與多重影像特徵比對法之多功能即時視覺追蹤系統之設計與實現”,國立成功大學電機工程學系,碩士論文,2004.