透過您的圖書館登入
IP:3.142.144.163
  • 學位論文

使用等高集合法對多目標移動物追蹤之研究

Tracking Multiple Moving Objects Using Level Set Method

指導教授 : 陳永盛
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


想要在動態影像中追蹤多目標移動物至今仍是一個重要且尚待解決的問題。在此篇論文中,我們針對背景會移動的影像序列,提出了一個有系統的方法來解決追蹤多目標移動物會碰到的問題。我們所提出的多目標移動物追蹤方法,主要由以下四個部份所構成︰多目標移動物偵測、物件關係之建立、背景影像的重建,以及各物件陰影的去除。為了有效的追蹤出多目標物件,我們利用影像畫面與初始背景影像的資訊及使用等高集合法(Level Set Method)偵測出多目標移動物,再利用編號演算法(Connected Component Analysis)和物件關係表來追蹤並記錄不同物件及其關係以達到追蹤的目的;為了解決背景移動的問題,我們利用區塊匹配(Block Matching)方式計算出整張影像的動態向量,並利用此資訊來補償背景影像,藉此解決背景變動時動態視訊物件追蹤所會碰到的問題,最後利用物件本身的動量(Moment)資訊配合物件的輪廓資訊來去除各物件的陰影。實驗結果證實我們所提出方法的優越性和穩定性。最後並討論此方法的限制性以及未來的相關應用。

並列摘要


This paper presents a novel approach to track multiple moving objects using the Level-set method. First, in order to overcome the problem of camera motion, a block matching method is used to estimate the information of camera motion for background compensation. Then, the difference image is obtained by subtracting two adjacent frames. With the difference image, different moving objects can be detected using the Level-set method. Furthermore, a Gaussian object model is used to remove object shadows. Finally, through connected component analysis, an object-relation table is created to track all the detected objects efficiently. Experimental results show that the proposed method is much robust and powerful than other traditional methods.

參考文獻


[2]J. M. Berg, “Estimation of parameters appearing in the level set evolution equation,” The Proceedings of the 37th IEEE Conference on Decision and Control, Volume: 2, Page(s): 2323—2328, 1998.
[3]J. M. Berg, “Estimation of parameter values appearing in space and orientation dependent curve evolution process models,” The Proceedings of the 1999 American Control Conference, Volume: 6, Page(s): 3905—3909, 1999.
[4]J. M. Berg, “On parameter estimation using level sets ,” Proceedings of the Conference on American Control, Volume: 6, Page(s): 3758—3762, 1998.
[5]J. M. Berg, A. Yezzi, and A. Tannenbaum, “Curve evolution models for real-time identification with application to plasma etching,” IEEE Transactions on Automatic Control, Volume: 44, No: 1, Page(s): 99—102, Jan. 1999.
[8]M. S. Branicky and G. Zhang, “Solving hybrid control problems: level sets and behavioral programming,” Proceedings of the 2000 Conference on American Control, Volume: 2, Page(s): 1175—1180, 2000.

被引用紀錄


李世安(2008)。即時目標影像追蹤之SoPC 設計〔博士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2008.01053
陳昇焱(2006)。應用影像技術於姐妹染色體型態辨識之研究〔碩士論文,元智大學〕。華藝線上圖書館。https://doi.org/10.6838/YZU.2006.00149
蘇志豪(2006)。以電腦視覺技術開發病房事件監控系統〔碩士論文,亞洲大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0118-0807200916282263
黃秉洋(2007)。以模型為基礎之乳房X光攝影微鈣化群立體定位及重建〔碩士論文,元智大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0009-1607200718384400
鄭權偉(2008)。整合式多攝影機環境車輛路徑追蹤系統〔碩士論文,亞洲大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0118-0807200916283848

延伸閱讀