簡易檢索 / 詳目顯示

研究生: 劉怡欣
Yi-Sin Liou
論文名稱: 互動式影片處理之特定物件非擬真著色系統
A Non-Photorealistic Rendering of a Video via Interactive Object Selection
指導教授: 楊傳凱
Chuan-Kai Yang
口試委員: 林伯慎
Bor-Shen Lin
孫沛立
Pei-Li Sun
學位類別: 碩士
Master
系所名稱: 管理學院 - 資訊管理系
Department of Information Management
論文出版年: 2017
畢業學年度: 105
語文別: 中文
論文頁數: 40
中文關鍵詞: 非擬真著色影片處理物件選擇
外文關鍵詞: Non-Photorealistic Rendering, Video Processing, Object Selection
相關次數: 點閱:193下載:0
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
  • 非擬真著色(Non-photorealistic Rendering, NPR)在電腦圖學領域中已發展一段時間,至今已發展出許多不同的藝術風格,並應用在各個領域。相對於擬真著色(Photorealistic Rendering, PR)講求細節與寫實度,非擬真著色的演算較著重藝術感與呈現手法,其輸出結果也較為簡潔。

    在非擬真著色的應用中,大部分的研究著重於靜態的影像處理,其輸出結果亦是靜態的影像。而關於影片處理的研究則相對較少,且大多是對整個畫面做非擬真著色處理,對局部的處理則更是少見。

    本研究提供了一套互動式的影片非擬真著色系統。不同於一般的影片處理,本系統以局部處理為目標,不事先進行資料訓練或依靠其他輔助設備,僅根據使用者所選擇的物件線索,自動追蹤影片中的物件。本系統可讓使用者自由選取欲處理的物件,並藉由NVidia的CUDA模組,以GPU運算與降解析度(Down Sampling)達到即時處理(Real-time),此技術可應用於擴增實境(Augmented Reality, AR)。


    Non-photorealistic rendering (NPR) has been developed in the computer graphics field for a while. There are lots of different kinds of artistic styles and various applications. Different from Photorealistic rendering (PR), which focuses on detail and realism, NPR's algorithm emphasizes the sense of art and presentation, the output result is much simpler.

    Most of prior researches apply NPR on static images. The research of applying NPR on a video is rarely found, while most of them process the entire frame instead of part of a frame.
    Our research provided a system of video non-photorealistic rendering via interactive object selection.
    Different from general video processing, our system aims to process the selected object which is not automatically tracked by doing information training or depending on other auxiliary facilities, but rely on the clue from user's selection.

    A user can choose any item to be process, and achieve a real-time processing with GPU calculation through NVidia's CUDA module.
    This method can also be used on Augmented Reality (AR).

    推薦書 .................................................................... I 審定書 .................................................................... II 中文摘要.................................................................. III 英文摘要.................................................................. IV 誌謝 ...................................................................... V 表目錄 .................................................................... VIII 圖目錄 .................................................................... IX 第一章 緒論 .............................................................. 1 1.1 研究背景 .................................................................... 1 1.2 研究動機 .................................................................... 1 1.3 論文架構 .................................................................... 2 第二章 文獻探討 ......................................................... 3 2.1 非擬真著色.................................................................. 3 2.2 影片的非擬真著色.......................................................... 4 2.3 即時影片處理 ............................................................... 6 第三章 研究方法 ......................................................... 8 3.1 系統流程 .................................................................... 8 3.2 物件追蹤(Object Tracking) ................................................ 9 3.3 物件切割(Object Segmentation) ........................................... 10 3.4 非擬真著色.................................................................. 14 3.4.1 油畫 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.4.2 鉛筆素描 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.4.3 平滑化 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.4.4 細節增強 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 3.4.5 風格化 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 第四章 實驗結果 ......................................................... 25 4.1 實驗環境 .................................................................... 25 4.2 非擬真著色效果 ............................................................ 25 4.3 其他實驗組結果 ............................................................ 30 4.4 顯示卡計算加速 ............................................................ 35 第五章 結論 .............................................................. 37 參考文獻.................................................................. 38

    [1] Babenko, B., Yang, M. H., and Belongie, S. Visual tracking with
    online multiple instance learning. In IEEE Conference on Computer Vision
    and Pattern Recognition (2009), pp. 983–990.
    [2] Curtis, C. J., Anderson, S. E., Seims, J. E., Fleischer, K. W., and
    Salesin, D. H. Computer-generated watercolor. In SIGGRAPH 97 The 24th
    International Conference on Computer Graphics and Interactive Techniques
    (1997), pp. 421–430.
    [3] DeCarlo, D., and Santella, A. Stylization and abstraction of photographs.
    ACM Transactions on Graphics 21, 3 (2002), pp. 769–776.
    [4] Gastal, E. S. L., and Oliveira, M. M. Domain transform for edge-aware
    image and video processing. ACM Transactions on Graphics 30, 4 (2011), pp.
    69:1–69:12.
    [5] Gatys, L. A., Ecker, A. S., and Bethge, M. A neural algorithm of
    artistic style. Computing Research Repository (2015).
    [6] Gonzalez, R. C., and Woods, R. E. Digital image processing (3rd edition)(2006).
    [7] Haeberli, P. Paint by numbers: Abstract image representations. In SIGGRAPH
    90 Proceedings of the 17th annual conference on Computer graphics
    and interactive techniques (1990), pp. 207–214.
    [8] Hertzmann, A. Paint by relaxation. In Computer Graphics International
    (2001), pp. 47–54.
    [9] Kim, K.-S., Yoon, Y.-J., Kang, M.-C., Sun, J.-Y., and Ko, S.-J. An
    improved grabcut using a saliency map. In IEEE 3rd Global Conference on
    Consumer Electronics (2014), pp. 317–318.
    [10] Kyprianidis, J. E., Kang, H., and Dollner, J. ¨ Image and video abstraction
    by anisotropic kuwahara filtering. Computer Graphics Forum 28, 7 (2009),
    pp. 1955–1963.
    [11] Paris, S., Kornprobst, P., Tumblin, J., and Durand, F. A gentle
    introduction to bilateral filtering and its applications. In ACM SIGGRAPH
    2007 Courses (2007).
    [12] Rother, C., Kolmogorov, V., and Blake, A. Grabcut: Interactive foreground
    extraction using iterated graph cuts. ACM Transactions on Graphics
    23, 3 (2004), pp. 309–314.
    [13] Santella, A., and DeCarlo, D. Visual interest and npr: An evaluation
    and manifesto. In Proceedings of the 3rd International Symposium on Nonphotorealistic
    Animation and Rendering (2004), pp. 71–150.
    [14] Santhosh, G. Oil paint effect: Implementation of oil painting effect
    on an image (2017). https://www.codeproject.com/Articles/471994/
    OilPaintEffect.
    [15] Tomasi, C., and Manduchi, R. Bilateral filtering for gray and color images.
    In Sixth International Conference on Computer Vision (1998), pp. 839–846.
    [16] Wang, J., Xu, Y., Shum, H.-Y., and Cohen, M. F. Video tooning. ACM
    Transactions on Graphics 23, 3 (2004), pp. 574–583.
    [17] Wikipedia. Drawing – wikipedia, the free encyclopedia (2017). [Online; accessed
    7-July-2017].
    [18] Wikipedia. Sobel operator – wikipedia, the free encyclopedia (2017). [Online;
    accessed 7-July-2017].
    [19] Winnemoller, H., Olsen, S. C., and Gooch, B. ¨ Real-time video abstraction.
    ACM Transactions on Graphics 25, 3 (2006), pp. 1221–1226.
    [20] Yang, C.-K., and Yang, H.-L. Realization of seurat’s pointillism via nonphotorealistic
    rendering. The Visual Computer 24, 5 (2008), pp. 303–322.
    [21] Yi, F., and Moon, I. Image segmentation: A survey of graph-cut methods.
    In International Conference on Systems and Informatics (2012), pp. 1936–1941.

    無法下載圖示 全文公開日期 2022/08/02 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)
    全文公開日期 本全文未授權公開 (國家圖書館:臺灣博碩士論文系統)
    QR CODE