Intelligent Dynamic Camouflage System

智能化動態偽裝系統

李蕙雯(Huei-Wem Li)

指導教授 ： 陳永昌

國立清華大學/電機資訊學院/電機工程學系/碩士(2010年)

https://doi.org/10.6843/NTHU.2010.00525

摘要

偽裝可以分為兩種類別，分別是自然偽裝與人工偽裝。枯葉蝶是自然偽裝的一個例子，其顏色與紋理和形狀如同牠常出沒的枯木枯葉，使其不易被他的敵人發現，達到生存機率上升的目的。人工偽裝的概念源自於這種動物自我保護的自然偽裝機制。好的人工偽裝不僅僅可以使軍人存活下來，也是打贏一場戰役的重要因素。
傳統的人工偽裝方式多以在待偽裝物上以人工的方式繪製或覆蓋上與週遭環境類似的顏色或圖案，造成敵方觀察者在視覺上的錯覺，以達到欺瞞偽裝的目的。然而傳統的偽裝方式在待偽裝物移動至不同背景區域，通常其效不彰。因此，我們建立一套智能化的動態偽裝系統，使待偽裝物可以隨著地點變化自然融入週遭環境中。
在這篇論文中，我們使用一台UBOT（機器人移動平台）提供動態環境。在其上架設兩台相機分別用來取得前方關於觀察者的資訊和被遮蔽的背景資訊，一台筆記型電腦用來模擬待偽裝物，利用螢幕來顯示背景圖樣。我們提出一個動態偽裝的系統，此系統包含了一個估計觀察者深度與方位的子系統，以及一個找尋並顯示合適背景圖樣的子系統。
我們的系統可以有效的隨著待偽裝物的移動顯示出合適的圖片，達到動態偽裝的目的。雖然目前還無法做到即時偽裝，但花的時間仍在可接受的範圍。

關鍵字

偽裝 ； 動態 ； 智能化

並列摘要

Traditional camouflage is achieved by wearing the camouflage coat with similar colors or textures of the surrounding. There is a serious problem with traditional camouflage, that is, as the place changes, they may be discovered by their enemy because of the difference between the camouflage coat and the new background. The motivation of the thesis is to solve the problem inherent in the traditional camouflage.
In this thesis, we use a U-BOT to provide dynamic environment. We install two cameras on it, one is used to get the information of the observer, and other is used to capture the covered background. A notebook is also put on it as the camouflage object. We propose a dynamic camouflage system including a subsystem used to estimate observer’s depth and position, and a subsystem used to find suitable pattern for display.
In the experiments, our system can show suitable pattern as the relative position changes. The response time of the system is acceptable.

並列關鍵字

camouflage ； dynamic ； intelligent

參考文獻

[1] Lowe, D. 2004, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, 60(2):91-110.

[2] Du-Ming Tsai and Shia-Chih Lai, “Independent Component Analysis-Based Background Subtraction for Indoor Surveillance,” Image Processing, IEEE Transactions onVolume 18, Issue 1, Jan. 2009 Page(s):158 - 167

[9] Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing (2nd ed.), Prentice Hall, Englewood Cliff, NJ (2002).

[3] Chris Stauffer and W.E.L Grimson, “Adaptive background mixture models for real-time tracking.” Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on.Volume 2, 23-25 June 1999

[4] Nir Friedman and Stuart Russell, “Image segmentation in video sequences: A probabilistic approach,” In Proc. of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI), Aug. 1-3, 1997.