(3.238.173.209) 您好!臺灣時間:2021/05/08 15:47
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:龔正豪
研究生(外文):Cheng-Hao Kung
論文名稱:應用於雙眼相片之景深特效
論文名稱(外文):Depth of Field Rendering with Binocular Image
指導教授:莊永裕
口試委員:葉正聖周承復
口試日期:2013-07-19
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2013
畢業學年度:101
語文別:中文
論文頁數:27
中文關鍵詞:景深雙眼相片
外文關鍵詞:depthbinocularshallow focus
相關次數:
  • 被引用被引用:0
  • 點閱點閱:291
  • 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
淺景深(shallow focus)是一種用於呈現攝影主題的特殊拍攝效果,其原理是透過控制景深(Depth-of-Field)大小,來模糊化主題以外的資訊,使得人們的注意力聚焦在攝影師所要呈現的物體或人像上,以產生特殊的美感體驗。但由於一般低價位數位相機硬體構造上限制,無法呈現出類似高價位單眼相機所產生的淺景深效果。而近年來3D攝影器材日益普及,著眼於此,我們提出了一個利用雙眼照片(Binocular Image)來模擬單眼相機拍淺攝景深效果的系統,首先利用雙眼照片計算出深度資訊,再依據圖片的不同深度施加不同程度的濾波器,實現讓使用者能夠自由調整對焦物體的目標,同時,我們也提供一個簡單的互動式介面讓使用者能夠方便地操作相片。

Shallow focus is a kind of photographic technique to emphasize specific objects in a scene. By controlling the size of depth-of-field(DOF) of a camera, objects outside DOF can be blurred, this technique enables photographers to highlight some parts inside a scene, and achieve artistic purposes. However, a common digital camera cannot produce such special effect like a Digital Single Lens Reflex(DSLR) camera does, due to its limitations on aperture and focal length. As 3D filming equipment become more popular and ubiquitous, we develop an system to synthesize shallow focus effect on binocular images, first, we extract depth information from binocular images, then apply a depth-aware filter on the image, thus users are capable of refocusing on any depth of the image, finally, we provide an interactive user interface to let user manipulate the image easily.

誌謝i
摘要ii
Abstract iii
1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Stereo Matching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.3 Depth of Field Rendering . . . . . . . . . . . . . . . . . . . . . . . . 3
2 System Overview 5
3 Method 7
3.1 Stereo Matching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.1.1 Color Segmentation . . . . . . . . . . . . . . . . . . . . . . . 7
3.1.2 Local Matching . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.1.3 Feature Guided Plane Fitting . . . . . . . . . . . . . . . . . . 9
3.1.4 Global Optimization . . . . . . . . . . . . . . . . . . . . . . . 11
3.2 Depth of Field Rendering . . . . . . . . . . . . . . . . . . . . . . . . 12
4 Results 15
4.1 User Interface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.2 Middlebury Stereo Evaluation . . . . . . . . . . . . . . . . . . . . . . 16
4.3 Depth of Field Rendering . . . . . . . . . . . . . . . . . . . . . . . . 17
5 Conclusion and Future Work 25
Bibliography 26

[1] D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space
analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,
2002.
[2] P. F. Felzenszwalb and D. P. Huttenlocher. Efficient belief propagation for early
vision. In Proceedings of Computer Vision and Pattern Recognition, 2004.
[3] P. Fua. Combining stereo and monocular information to compute dense depth
maps that preserve depth discontinuities. In Proceedings of International Joint
Conference on Artificial Intelligence, 1991.
[4] A. Klaus, M. Sormann, and K. Karner. Segment-based stereo matching using
belief propagation and a self-adapting dissimilarity measure. In Proceedings of
International Conference on Pattern Recognition, 2006.
[5] D. G. Lowe. Distinctive image features from scale-invariant keypoints. International
Journal of Computer Vision, 2004.
[6] M. Potmesil and I. Chakravarty. A lens and aperture camera model for synthetic
image generation. In Proceedings of SIGGRAPH 1981, 1981.
[7] D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame
stereo correspondence algorithms. International Journal of Computer Vision,
2002.
[8] Y.-N. Tseng. Realtime depth of field rendering with bokeh effect via interactive
depth labeling. Master’s thesis, National Taiwan University, 2011.
[9] Z. Wang and Z. Zheng. A region based stereo matching algorithm using cooperative
optimization. In Proceedings of Computer Vision and Pattern Recognition,
2008.
[10] Wikipedia. Circle of confusion — Wikipedia, the free encyclopedia, 2013. [Online;
accessed 10-July-2013].
[11] Wikipedia. Depth of field — Wikipedia, the free encyclopedia, 2013. [Online;
accessed 10-July-2013].
[12] Wikipedia. Shallow focus — Wikipedia, the free encyclopedia, 2013. [Online;
accessed 10-July-2013].
[13] Q. Yang, L. Wang, R. Yang, H. Stewenius, and D. Nister. Stereo matching
with color-weighted correlation, hierarchical belief propagation, and occlusion
handling. IEEE Trans. Pattern Anal. Mach. Intell., 31(3):492–504, 2009.

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