隨著網路快速發展及儲存技術的進步，人們對於視訊影像的要求除了原有的品質外，也開始增加對於互動性的需求，所以在新一代的視訊標準MPEG-4中更是首先採用以物件為基礎的編碼方式，而視訊物件的切割是當中關鍵的技術，過去被提出的演算分成兩類，第一類主要是在時間軸上利用兩張連續圖框間之差異取得物件的移動資訊，此法雖然擁有較低的運算量，但由於是根據直覺的考慮其差異度強健性較弱，而且欲切割之影像容易受外界環境所影響，如亮度與陰影等，切割品質較差；另一類方法結合時間軸與空間軸同時進行分析處理，也是較常見的方式，在此類方法中有常見有兩種作法，第一種作法，通常利用邊緣偵測方法的演算法找出圖框中物件的輪廓，之後再利用時間軸上的分析找出移動區域的邊緣，最後再將前景物件執行填滿的處理，形成物件遮罩。雖然此法雖有強健性較強和切割品質較佳之優點，但其在遮罩補滿處理的過程中會利用型態影像學運算來達成，往往會因預先選用的結構元素不同而影響遮罩與原物件近似程度，不僅如此，一旦選用較大或較複雜的結構元素時會增加處理的運算量導致系統處理速度的效能之降低；另一種方法是利用分水嶺法或色塊分割法，先將畫面切割成多個相似區塊再進行合併及移動偵測找出前景物件，不過由於此類方法會有著過度分割的問題，會造成在之後的處裡過程中物件形狀與特徵的辨視困難度，而且如何將過度分割的結果有效的將歸屬同一物件的區塊合併也是相當大的考驗。
因此，綜合上述的各種方法的優缺點考量下，本文所提出之切割方法，改善了前面所提及利用邊緣偵測配合移動資訊的方法，根據物體的連續性在以往傳統方法中將移動物件輪廓填滿的步驟前加入一個前處理，用以加強移動區域的輪廓邊緣，來符合效率的需求，並獲得較佳的切割效能。

As the technique of storage media and Internet develops rapidly in recent years, the demands for video are not only quality but also interaction. The conventional video coding standard, such as MPEG1, MPEG-2, and H.263 cannot satisfy the demands mentioned above .The MPEG-4 video coding standard is the first one to support randomly accessing video objects by the concept of video-object-plane (VOP). It can support high interaction and more flexible coding. Therefore,  segmenting the shapes of the video objects is very important. Many video object segmentation algorithms have been presented. They can be summarily classified into two types: (1) Temporal Analysis and (2) Temporal-Spatial Analysis. One typical kind of Temporal Analysis is to get the moving information of video objects between two continuous frames on the temporal domain. Although these methods have lower computation load, the quality of segmentation is not good enough. Because the objects needed to be segmented are easily to be influenced by brightness or shadow, some kinds of typical method combine spatial and temporal domain was proposed [14]. This approach uses the algorithms of edge detection to get the shapes of the foreground objects and find out the edge of moving regions by using the analysis on the temporal axis, and then, the filling technique is used to generate the masks of the foreground objects. Although this method has higher robustness and better quality for segmentation, the similarity between the original video objects and masks depends on the chosen morphological structuring element and times of processing during the process of filling masks by using morphological operations. If we choose a complex structuring element, it will raise the computation load and reduce the efficiency of the system. In order to overcome the mentioned shortcomings, we propose a new algorithm by adding a pre-processing mechanism to improve the object segmentation.
A new video object segmentation algorithm using the morphological technique is proposed. Several video object segmentation algorithms used mathematical morphology to generate the object masks, but operations of mathematical morphology have two drawbacks: (1) high computation load, and (2) the quality of masks depends on the chosen morphological structuring element. There are many techniques to speed up the morphological operations by hardware implementation, but no discussions are found about reducing the influence of the choice of structuring elements. By adding a pre-processing mechanism, we effectively reduce the influences of the chosen structuring elements based on continuity of shape features and times of morphological operations. Experimental results indicate that our algorithm can improve the speed of filling operations of the object masks and accuracy of segmentation

目    錄
第一章 緒論………………………………………………1
1.1研究動機與目標……………………………………………1
1.2視訊影像切割簡介……………………………………2
1.3論文架構……………………………………………………3
第二章 影像邊緣偵測演算法……………………4
2.1簡介……………………………………………………4
2.2傳統邊緣偵測簡介……………………………………5
  2.2.1 Sobel 邊緣檢測器……………………………………………5
  2.2.2 Prewit 邊緣檢測器…………………………………………6
  2.2.3 Robert 交叉邊緣檢測器………………………………………7
2.3影像型態學梯度邊緣檢測………………………………9
  2.3.1 影像型態學理論概述…………………………………………9
    2.3.1.1型態學運算子介紹…………………………………10
  2.3.2 影像型態梯度…………………………………………13
第三章 視訊物件切割演算法…………………………15
3.1簡介…………………………………………………15
3.2動態物件切割演算法……………………………16
3.2.1基於動態資訊的切割方法………………………………17
    3.2.1.1 光流運動分析法…………………………………………17
    3.2.1.2 Lucas-Kanade 運動偵測法…………………………18
    3.2.1.3基於區塊比對的視訊切割法……………………………20
    3.2.1.4畫面間差異性偵測法………………………………22
  3.2.2以分水嶺法為基礎之切割方法………………………23
3.3其它相關演算法………………………………………25
  3.3.1基於背景註冊的視訊切割法………………………………26
  3.3.2基於運動資訊與區域填補的視訊物件切割法………………26

第四章 本文所提出之視訊切割演算法…………………29
4.1概述………………………………………………………29
4.2視訊切割流程……………………………………………30
  4.2.1邊緣檢測……………………………………………………31
  4.2.2運動偵測……………………………………………………31
  4.2.3預填滿處理……………………………………………………32
4.3實驗結果…………………………………………………34
  4.3.1處理時間統計…………………………………………………35
  4.3.2切割正確率分析………………………………………………37
第五章 總結…………………………………………44
5.1結論…………………………………………………44
5.2未來發展方向……………………………………………45
參考文獻…………………………………………………46
 
圖目錄
圖2.1 Sobel 邊緣偵測器之乘積矩陣……………………………5
圖2.2 Sobel邊緣偵測器偵測結果………………………………6
圖2.3 Prewitt 邊緣偵測器之乘積矩陣…………………………7
圖2.4 Prewitt邊緣偵測器偵測結果……………………………7
圖2.5 Roberts 邊緣偵測器之乘積矩陣…………………………8
圖2.6 Roberts邊緣偵測器偵測結果……………………………8
圖2.7 常見的Structuring Element……………………………10
圖2.8 輸入影像集合與結構元素……………………………… 11
圖2.9 灰階影像Dilation運算…………………………………11
圖2.10 灰階影像Erosion運算…………………………………12
圖2.11 灰階影像Dilation運算……………………………13
圖2.12 經由型態梯度求得之影像……………………………13
圖3.1一般切割方法流程圖…………………………………15
圖3.2 兩個連續圖框的一維亮度變化圖………………………19
圖3.3 孔徑問題…………………………………………………20
圖3.4 區塊比對概念示意圖……………………………………21

圖3.5 分水嶺法示意圖…………………………………………23
圖3.6 Vicent 和 Soille分水嶺法示意圖……………………24
圖3.7 分水嶺法分割後產生過度分割問題……………………25
圖3.8 分水嶺法分割後產生過度分割問題……………………28
圖4.1本文所提出切割演算法流程圖 …………………………30
圖4.2型態梯度求影像運動邊緣 ………………………………32
圖4.3預填滿處理方法示意圖 …………………………………33
圖4.4標準影像測試序列Akiyo切割正確率比較 ……………38
圖4.5 標準影像測試序列Weather切割正確率比較 …………39
圖4.6 Akiyo Sequence 的分割結果比較(一)…………………41
圖4.7 Akiyo Sequence 的分割結果比較(二)…………………42
圖4.8 Weather Sequence 的分割結果比較(三)………………43
圖5.1不同結構元素選擇下之物件切割結果 …………………44


 
表目錄
表4.1本實驗模擬環境……………………………………………34
表4.2本實驗所使用的測試影像序列規格…………………………34
表4.3 Test Sequence Akiyo的分割時間……………………………36
表4.4 Test Sequence Weather的分割時間……………………………37

[1]T. Sikora, "The MPEG-4 video standard verification model," IEEE Trans. CSVT, vol.1,Feb 1997, pp. 19-31.
[2]Information Technology-Coding of Moving Pictures and Associated Audio for Digital Storage Media up About 1.5Mbit/s : Part 2-Video ISO/IEC 11172-2,International Standard,1993
[3]Information Technology-Generic Coding of Moving Pictures and Associated Audio: Part 2-Video ISO/IEC 13813-2,International Standard, 1995
[4]ITU-T Recommendation H.261: Video codec for audiovisual services at p*64 kbits/s, version2, Mar. 1993
[5]ITU-T Recommendation H.263: Video coding for low bit rate communication, version2, Jan. 1998
[6]R. V. Babu, K. R. Ramakrishnan, and S. H. Srinivasan, "Video object segmentation: a compressed domain approach," IEEE Trans. Circuits and Systems for Video Technology, vol. 14, no. 4, April 2004, pp.462-474.
[7]L. Yang, H. Zhang, and Y. Li, “Automatic segmentation of moving objects in video sequences”, Journal of Computer-Aided Design and Computer graphics, vol. 16, no.3, July 2004, pp. 597-612.
[8]S.-Y.Chien, Y.-W. Huang, and L.-G. Chen, “Predictive watershed: A fast watershed algorithm for video segmentation,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 13, no. 5, May 2003, pp. 453-461. 
[9]Y. Tsaig and A. Averbuch, “Automatic segmentation of moving objects in video sequences: a region labeling approach,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 12, no. 7, July 2002, pp. 597-612.
[10]C. Kim and J.N. Hwang, "Fast and robust moving object segmentation in video sequences," Int. Conf. Image Processing (ICIP'99),vol. 2, Kobe, Japan, 1999, pp. 131-134.
[11]N.R. Paland S.K. Pal, “ A Review on Image Segmentation Techniques,”Pattern Recognition, vol. 26, 1993, pp. 1277-1294
[12]J.F. Haddon and J.F. Boyce, “Image Segmentation by Unifying Region and Boundary Information,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 10, 1990, pp.929-948
[13]A. M. Tekalp, Digital Video Processing, Prentice Hall PTR, (1995)
[14]Y. T. Hsiao, C. L. Chuang, S. H. Yen, and H. J. Lin, "A mathematical morphological approach to thin edge detection in dark region," Proceedings of the 4th IEEE International Symposium on Signal Processing and Information Technology,Rome, Italy, December 18-21, 2004, pp. 310-313.
[15]J. Serra, Image Analysis and Mathematical Morphology, New York: Academic. 1982. 
[16]P. Soille, Morphological Image Analysis: Principles and Applications, Springer: Berlin Heidelberg, 1999.
[17]J. H. Bosworth and S. T. Acton, "Morphological image segmentation by local monotonicity," Proc. Conf. on Signals, Systems, and Computers, vol. 1, 1999.
[18]鄭榮裕，江政欽，植基於運動資訊與區域填補的視訊物件分割：東華大學碩士論文，民國94。