(100.25.42.117) 您好!臺灣時間:2021/04/21 17:36
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:林彥廷
研究生(外文):Yen-Ting Lin
論文名稱:應用影像合成技術達到影像模糊補償
論文名稱(外文):Blurred Image Compensation by Using Image Composition
指導教授:鄧洪聲
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
畢業學年度:96
語文別:中文
論文頁數:59
中文關鍵詞:影像穩定系統相機震動影像模糊影像合成
外文關鍵詞:Image stabilization systemcamera shakeimage blurimage composition
相關次數:
  • 被引用被引用:3
  • 點閱點閱:101
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
當無人載具在飛行中,其酬載系統對地面的地形地物進行拍攝影像時,常會因載具震動或搖擺而造成所拍攝的影像模糊,進而使得其後續利用這些影像的模組如目標識別與定位、地形地物研判等任務無法順利進行。影像穩定也稱為震動減低,是一種幫助改善影像模糊的攝影技術,它可以減少因為相機震動、快門速度過慢、或使用望遠鏡頭等因素所造成的影像模糊。本文提出一種可應用於無人載具上有效的影像穩定系統,它採取影像合成之數位影像穩定系統,也就是使用影像處理的技術去補償影像之震動,以達到消除影像模糊的目的。整體來說,我們的方法包含下列步驟:1)先取兩張影像做特徵點偵測;2)特徵比對;3)兩張影像旋轉到相同座標系統;4)再做特徵點偵測;5)特徵比對;6)影像比例合成,最後得到清晰的結果影像。我們曾以實際的影像資料來進行實驗,實驗結果顯示所提的方法是有效的。
When a UAV is operating in the air, its payload system will take images of the terrains and targets on the ground. The images taken by the camera are often blurred due to the shake and pitching of the UAV, and this may cause the subsequent tasks such as target recognition and positioning, terrain identification, etc., which make use of these images, not be able to undertake. Image stabilization, also known as vibration reduction, is a photographic technology which helps prevent images from becoming blurred. It reduces vibration caused by camera shake, slow shutter speed, or when using a telephoto lens. In this paper, an effective image stabilization system, which can be used on the UAV, is developed. It adopts the digital stabilization based on image composition, in which the image processing techniques is used, to compensate for camera vibrations. This image stabilization system will much improve the quality of the blurred images. In general, the proposed method contains the following steps: 1) Detect the feature points on two consecutive images; 2) match the feature points; 3) rotate the images for alignment; 4) detect the feature points again; 5) match the feature points; and 6) compose the images to obtain a deblurred image. We have used real image data to perform experiments. The experimental results show that the proposed method is effective.
第一章 序論 1
1.1 研究背景與發展動機 1
1.2 影像模糊種類 1
1.3 模糊影像形成原因 4
1.4 影像清晰度的判斷標準 5
1.4.1 梯度 6
1.4.2 邊緣檢測器 7
1.5 章節介紹 8
第二章 影像穩定系統 9
2.1 光學影像穩定系統 9
2.1.1 使用移動式鏡片達到影像穩定 9
2.1.2 使用移動式CCD達到影像穩定 12
2.2 數位影像穩定系統 14
2.2.1 使用加大視窗達到影像穩定 14
2.2.2 增加ISO速度達到影像穩定 15
第三章 應用合成技術達到數位影像穩定 16
3.1 概念 16
3.2 影像選取 16
3.3 使用SIFT做特徵偵測 17
3.3.1 尺度空間的極值偵測 17
3.3.2 精確的特徵點確認 22
3.3.3 方向的確認 23
3.3.4 特徵點的描述 27
3.3.5 SIFT實驗結果 28
3.4 特徵比對 30
3.5 預先旋轉 32
3.6 影像合成 34
3.7 系統流程圖 37
第四章 操作介面與實驗結果 38
4.1 圖形介面使用介紹 38
4.2 實驗結果 49
第五章 結論 57
參考文獻 58
[1] Nikon Imaging, “Nikon Imaging | Vibration Reduction,”
http://nikonimaging.com/global/products/digitalcamera/coolpix/cppf/eng/vr_index.htm, 2006.
[2] Panasonic, “Technology that LUMIX takes the shake out,”
http://panasonic.co.jp/pavc/global/lumix/technology/index.html, 2005.
[3] Wikipedia, “Gradient,” http://en.wikipedia.org/wiki/Gradient, 2006.
[4] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision, Vol. I, Addison
Wesley, Reading, MA, 1992.
[5] M.Oshima, et al., "VHS camcorder with electronic image stabilizer," IEEE Trans. on Consumer Electronics, vol. 35no.4,pp. 749-758, Nov. 1989.
[6] K.Sato, et al., "Control techniques for optical image stabilizing system,"IEEE Trans. on Consumer Electronics, vol. 39,no. 3pp. 461-466, Aug, 1993.
[7] Keller, J.,“Digital Camera Resource Page Review: Nikon Coolpix 8800, ” http://www.dcresource.com/reviews/nikon/coolpix8800-review/index.shtml. ,2004
[8] Nikon,“ Precise Camera-Shake Compensation at Every Angle VR (Vibration Reduction) System, ” http://nikon.co.jp/main/eng/portfolio/about/technology/nikon_technology/vr_e/index.htm, 2005.
[9] Canon,“ Optical Shift Image Stabilizer,”http://www.canon.com/bctv/faq/optis.html,2008.
[10] Konica Minolta,“Camera-shake correction of CCD shift type,” http://www.konicaminolta.com/about/research/core_technology/picture/antiblur.html,2008
[11] Chen, J. F. and Fuh, C. S., “ Image stabilization with best shot selector and super resolution reconstruction, ” Proc. CVGIP, Taipei, Taiwan, Aug. 21-23, 2005.
[12] Yuen, P., “Nikon Best Shot Selector TM,” http://digitalimaging.patyuen.com/shootout/Cp5kvg2/bss.htm, 2003
[13]Sheng-Che Hsu, Shung-Fu Liang, Chin-Teng Lin, "A robust digital image stabilization technique based on inverse triangel method and background detection," IEEE Transactions on Consumer Electronics, vol. 51 , no. 2, pp. 335-345, May 2005.
[14] Lowe, D. G., “Distinctive image features from scale-invariant keypoints,” Int. J. of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[15] Harris, C. and Stephens, M.,“A combined corner and edge detector,” Proc. of Alvey Vision Conf., Manchester, UK, pp. 147-151, 1988.
[16] Lowe, D. G., “Method and Apparatus for Identifying Scale Invariant Features in an Image and Use of Same for Locating an Object in an Image,” United States Patent# 6711293, 2004.
[17] Wikipedia, “Scale-Invariant Feature Transform,”
http://en.wikipedia.org/wiki/Scale-invariant_feature_transform, 2006.
[18] Gonzalez, R. C., Woods, R. E. and Eddins, S. L., Digital Image Processing using MATLAB, Prentice-Hall, Upper Saddle River, New Jersey, 2004.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔