本論文中提出一系列的方法運用在視訊物件分割上，可以讓物件分割時更有效率、精確、並適合各種不同的視訊媒體。我們提出的方法包括在小波頻域中分割物件的方法、兩次改變偵測的方法、總體移動估測的方法、在移動背景中分割物件的方法…等。
首先我們將提出在小波轉換的頻域(Wavelet domain)中，來分割視訊物件。我們利用移動偵測(Change Detection)的方法來對小波的四個頻域作分割，並且分別使用四個不同的門檻值(Threshold)。由實驗的結果證明了我們的方法可以得到較多的物件形狀資訊，以便可以得到較精確的視訊物件。
在兩次改變偵測的方法中，我們將提出使用連續三個影像來作物件分割的方法。在小波轉換的頻域(Wavelet domain)中，我們先使用改變偵測(Change Detection)兩次，並且使用交集運算(Intersect Operation)的方法，我們得到更多的物件移動邊緣和更多的物件輪廓形狀的資訊。
另外，我們探討在動態背景下的總體移動估測方法(Global Motion Estimation)。我們提出一個利用交叉點(Cross Point)的特徵來尋找總體移動估測的方法，而這個方法可以運用在背景重建的視訊影像上。由於我們所提的交叉點有Robust以及交叉點的個數很少的特性，所以我們可以很有效率的在連續鏡頭(Successive Frame)中得到總體移動估測的Affine參數。
最後，我們探討在移動的背景中作視訊物件的分割。利用連續畫面所產生的背景結合成一個沒有物件的大場景(Wide Scene Background)。再利用物件所在的視訊畫面和大場景中相對位置的視訊畫面作比對，如此便可以輕易的將移動物件分割出來。
由實驗的結果可以知道，在這論文中我們所提的所有方法都有很好的效能以及都能適合在各種不同的視訊影片中實現。因此，在本論文中所提的方法是對Mpeg-4中的視訊編碼或是對多媒體科技是有所貢獻。

In this thesis, we proposed the series methods of moving object segmentation and object application. These methods are the moving object segmentation method in wavelet domain, double change detection method, global motion estimation method, and the moving object segmentation in the motion background.
First, we proposed the Video Object Segmentation Method in Wavelet Domain. We use the Change Detection Method with the different thresholds in four wavelet sub-bands. The experiment results show that we obtain further object shape information and more accurately extracting the moving object.
In the double change detection method, we proposed the method for moving object segmentation using three successive frames. We use change detection method twice in wavelet domain. After applying the Intersect Operation, we obtain the accurately moving object edge map and further object shape information.
Besides, we proposed the global motion estimation method in motion scene. We propose a novel global motion estimation using cross point for the reconstruction of background scene in video sequences. Due to the robust character and limit number of cross points, we can get the Affine parameters of global motion in video sequences efficiency.
At last, we proposed the object segmentation method in motion scene. We use the motion estimation method to estimate the global motion between the consecutive frames. We reconstruct a wide scene background without moving objects by the consecutive frames. At last, the moving objects will be segmented easily by comparing the object frame and the relative part in wide scene background.
The Results of our proposed have good performance in the different type of video sequences. Hence, the methods of our thesis contribute to the video coding in Mpeg-4 and multimedia technology.

Contents List
Index
中文摘要
Abstract
Contents List
List Of Figures
List Of Tables
I Introduction
1.1 The Object Concept in Mpeg-4
1.2 The Object Concept in Mpeg-7
1.3 Related Research of the Moving
Object Segmentation
1.4 Related Research of the Global Motion
Estimation
1.5 Organization of the Dissertation
II Wavelet-based Moving Object Segmentation
2.1 Proposed Method
2.2 Results
2.3 Discussion
III Double change detection method for wavelet-based
moving object gmentation
3.1 Proposed Method
3.2 Results
3.3 Discussion
IV Global motion estimation method
4.1 Proposed Method
4.2 Results
4.3 Discussion
V Moving Object Segmentation in the Motion Background
5.1 Proposed Method
5.2 Experimental Results
5.3 Discussion
VI Conclusion and Future Work
6.1 Conclusion
6.2 Future Work
Reference

[01] Ahmad, B.-M., & Choi, T.-S., (2001). "Edge detection-based block motion estimation", IEE Electronics Letters, Vol. 37, No. 1, pp. 17-18.
[02] Babu, R.-V., Ramakrishnan, K.-R., & Srinivasan, S.-H., (2004). "Video object segmentation: a compressed domain approach", IEEE Transactions on Circuits and Systems for Video Technology , Vol. 14, Issue 4, pp. 462-474.
[03] Brown, L.-G., (1992) "A survey of image registration techniques", ACM Computing Surveys, 24, pp. 325-376.
[04] Canny, J., (1986). "A Computational Approach to Edge Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No. 6, pp. 679-698.
[05] Chang, S.-F., Sikora T., & Puri A., (2001). "Overview of the MPEG-7 Standard", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11, No. 6, pp. 688-695.
[06] Chien, S.-Y., Huang Y.-W., & Chen L.-G., (2003). "Predictive Watershed: A Fast Watershed Algorithm for Video Segmentation", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, Issue 5, pp. 453-461.
[07] Chien, S.-Y., Ma, S.-Y., & Chen, L.-G., (2002). "Efficient Moving Object Segmentation Algorithm Using Background Registration Technique," IEEE Trans. Circuits Syst. Video Technol., Vol. 12, No. 7, pp. 577-586.
[08] Daras, P., Kompatsiaris, I., Raptis, T., & Strintzis, M.-G., (2004). "An MPEG-4 tool for composing 3D scenes", IEEE Multimedia, Vol. 11, Issue 2, pp. 58-71.
[09] Dasu, A.-R., & Panchanathan, S., (2004). "A Wavelet-Based Sprite Codec", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, Issue 2, pp. 244-255.
[10] Dufaux, F., & Konrad, J., (2000). "Efficient, Robust, and Fast Global Motion Estimation for Video Coding", IEEE Transactions on Image Processing, Vol. 9, No. 3, pp. 497-501.
[11] Dufaux, F., & Moscheni, F., (1995). "Motion estimation techniques for digital TV: A review and a new contribution", Proc. IEEE, vol. 83, pp. 858-879.
[12] Durucan, E., & Ebrahimi, T., (2001). "Change Detection and Background Extraction by Linear Algebra", Proceedings of the IEEE, Vol. 89, No. 10, pp. 1368-1381.
[13] Erdem, C.-E., Sankur, B., & Tekalp, A.-M., (2004). "Performance Measures for Video Object Segmentation and Tracking", Image Processing, IEEE Transactions on , Vol. 13, Issue 7, pp. 937-951.
[14] Gonzalez, R.-C., & Woods, R.-E., (1992). "Digital Image Processing", Addison-Wesley, pp. 518.
[15] Guo, J., Kim, J.-W., & Kuo C.-J., (1999). "Fast and accurate moving object extraction technique for MPEG-4 object-based video coding", SPIE, Vol. 3653, pp. 1210-1221.
[16] He, G., Li, K., & Hu, D., (1998). "A Fusion Approach of Multi-sensor Remote Sensing Data Based on Wavelet Transform ", Asian Conference on Remote Sensing.
[17] Hsu, C.-T., & Tsan Y.-C., (2001). "Mosaics of Video Sequences with Moving Objects", Proc. ICIP 2001, Thessaloniki, Greece, pp. 387-390.
[18] Huang, J.-C., & Hsieh, W.-S., (2003). "Wavelet-based moving object Segmentation", IEE Electronics Letters, Vol. 39, NO. 19, pp. 1380-1382.
[19] Huang, J.-C., Su, T.-S., Wang, L.-J., & Hsieh, W.-S., (2004). "Double change detection method for wavelet-based moving object segmentation", IEE Electronics Letters, Vol. 40, No. 13, pp. 798-799.
[20] Jeannin, S., & Divakaran, A., (2001). "MPEG-7 Visual Motion Descriptors", IEEE Transactions on Circuits and Systems for Video Technology, VOL. 11, NO. 6, pp. 720-724.
[21] Jeannin, S., & Mory, B., (2000). "Video Motion Representation for Improved Content Access", IEEE Transaction on Consumer Electronics, Vol. 46, No. 3, pp. 645-655.
[22] Kauff, P., Makai, B., Rauthenberg, S., Golz, U., De Lameillieure, J.-L.-P., & Sikora, T., (1997). "Functional Coding of Video Using a Shape-Adaptive DCT Algorithm and an Object-Based Motion Prediction Toolbox", IEEE Trans. on Circuits ad Systems for ideo Technology, Vol. 7, No. 1, pp. 181-196.
[23] Kim, C., & Hwang, J.-N., (2002). "Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications," IEEE Trans. Circuits Syst. Video Technol., Vol. 12, No. 2, pp. 122-129.
[24] Kim, C., & Hwang, J.-N., (2002). "Object-Based Video Abstraction for Video Surveillance Systems", IEEE Trans. Circuits Syst. Video Technol., Vol. 12, No. 12, pp. 1128-1138.
[25] Kim, M., & Kim, J., (2000). "Moving video object segmentation using statistical hypothesis testing", IEE ELECTRONICS LETTERS, Vol. 36, No.2, pp. 128-129.
[26] Koenen, R., (2002). "MPEG-4 Overview", Retrieved from Telecom Italia Lab Web site: http://mpeg.telecomitalialab.com
[27] Kondi, L.-P., Melnikov, G., Katsaggelos, A.-K., (2004). "Joint optimal object shape estimation and encoding", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, Issue 4, pp.528-533.
[28] Liao, H., Mandal, M.-K., & Cockburn, B.-F., (2004). "Efficient architectures for 1-D and 2-D lifting-based wavelet transforms", IEEE Transactions on Signal Processing, Vol. 52, Issue 5, pp.1315-1326.
[29] Long, F., Feng, D., Peng, H., and Siu, W.-C., (2001). "Extracting Semantic Video Objects", IEEE Digital Media, pp. 48-55.
[30] Meier, T., & Ngan, K.-N., (1999). "Segmentation and tracking of moving objects for content-based video coding", Image and Signal Processing, IEE Proceedings, Vol. 146, pp. 144-150.
[31] Neri, A., Colonnese, S., Russo, G., & Talone, P. (1998). "Automatic moving object and background separation", Signal Processing, Vol. 66, No. 2, pp. 219-232.
[32] PARK, W.-B., KWAK, N.-J., SONG, Y.-J., & AHN J.-H., (2003). "Fast Motion Estimation Based on Binary Edge Information", IEICE Trans. Inf. & Syst., Vol. E86-D, No. 8, pp. 1456-1458.
[33] Ranade, S., & Rosenfeld, (1980). "Point pattern matching by relaxation", Patt, Recog. Vol. 12, pp. 269-275.
[34] Salembier, P., & Pardas, M., (1994). "Hierarchical Morphological Segmentation for Image Sequence Coding," IEEE Trans. Image Processing, Vol. 3, No. 5, pp. 639-651.
[35] Sikora, T., (1997). "The MPEG-4 video standard verification model", IEEE Trans. Circuits Syst. Video Technol., vol. 7, pp. 19-31.
[36] Smolic, A., Sikora, T., & Ohm, J.-R., (1999). "Long-Term Global Motion Estimation and Its Application for Sprite Coding, Content Description, and Segmentation", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 8, pp. 1227-1442.
[37] Soille, P., (1999). "Morphological Image Analysis: Principles and Applications", pp. 173-174.
[38] Tsai, T.-H.; Chen, C.-P., (2004). "A Fast Binary Motion Estimation Algorithm for MPEG-4 Shape Coding", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, Issue 6, pp. 908-913.
[39] Tsaig, Y., Averbuch, A., (2002). "Automatic Segmentation of Moving Objects in Video Sequences: A Region Labeling Approach", IEEE Trans. Circuits Syst. Video Technol., Vol. 12, No. 7, pp. 597-612.
[40] Vetro, A., & Sun, H., (2001). "Encoding and Transcoding Multiple Video Objects with variable Temporal Resolution", Proc. ISCAS, pp. 21-24.
[41] Xing, G., Li, J., Li, S., & Zhang, Y.-Q., (2001). "Arbitrarily Shaped Video-Object Coding by Wavelet", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11, No. 10, pp. 1135-139.