本論文提出一種建構於移動向量的目標區域之對應方法，透過此方法可針對影片中之不同畫面框架間的目標區域建立起互相的關聯性，減少進行任何影像處理時所需要的時間與資源。由於影片中移動的物件常被認定為比較重要的部分，因此，在本論文中將影片裡移動的物件定義為目標區域。而對於物件的擷取方式，是透過對定義出畫面群組中的背景區域，間接取得到實際的物間區域。當影片中所有畫面框架的物件定義完成時，即完成了目標區域的擷取。由於影片中目標區域非常相似，本論文將利用這個特性，透過移動向量，把各個畫面框架中之目標區域建立關聯性。在影片目標區域建立關聯性之後，所有的影像處理動作只需要針對影片裡少數畫面框架中的目標區域進行運算，而其他畫面框架透過彼此間的關聯性間接地受到影響，不需要經過其他任何的運算即可達到相同的效果。

　This paper presents a new approach to search ROI based on motion vector. Meanwhile, this approach will reduce time and resource usage when we tend to do any kinds of image process on the ROI. Under the assumption that motion objects region are more important than other regions in the frame, however, we consider that motion objects are our ROI.

　In our approach, we will not extract motion objects directly. Instead, we construct and maintain a background information from the video sequence and compare each frame with the background. If a pixel that is significantly different from the background is assumed to be the motion object. After extract motion objects step, we can get our ROI in each frame. Moreover, in a video sequence, consecutive frames are similar to each other, for the reason, we can map our ROI from one frame to another. Then, we can build a chain relation for all ROI in this video sequence.

　After mapping step, video sequence will be divided in to several parts, in our implementation, GOPs(Group Of Picture) are the basic unit of the chain relation. Therefore, if we modify the ROI in the I frame of a GOP, the influence will be extended to all other frames in the GOP by the chain relation event without any computation.

[1] John W. Wong, “Broadcast Delivery,” Proceedings of the IEEE, Vol. 76, pp. 1566-1577,1988.
[2] 章忠信, "網路著作權之保護", 2003年網際空間：科技、犯罪與法律社會學術研究暨實務研討會.
[3] Y. Bodo, N. Laurent, and J.-L. Dugelay, “Watermarking video, hierarchical embedding in motion vectors,” in Proc. IEEE Int. Conf. Image Processing, vol. 2, pp.739-742,2003.
[4] ISO/IEC, “Coding of moving pictures and associated audio for digital storage media at up to 1.5 Mbit/s,” in ISO/IEC 11172-2 (MPEG-1), 1992.
[5] ISO/IEC, “Generic coding of moving pictures and associated audio information – part 2: video,” ITU-T and ISO/IEC JTC 1, ITU-T Recommendation H.262 and ISO/IEC 13818-2 (MPEG-2), 1994.
[6] ISO/IEC, “Coding of audio-visual objects – part 2: visual,” in ISO/IEC 14496-2 (MPEG-4 Visual Version 1), Apr. 1999.
[7] ISP/IEC, “Draft ITU-T recommendation and final draft international standard of joint video specification (ITU-T Rec. H.264/ISO/IEC 14 496-10 AVC)", JVTG050, 2003.
[8] D. Stinson, “Visual cryptography and threshold schemes,” IEEE Potentials, Vol. 18, pp.13–16, 2003.
[9] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision. Reading, MA: Addison-Wesley, 1992, pp. 28–48.
[10] T. Aach, A. Kaup, and R. Mester, “Statistical model-based change detection in moving video,” Signal Processing, vol. 31, pp. 165–180, 1993.
[11] R. Mech and M. Wollborn, “A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera,” Signal Processing, vol. 66, pp. 203–217, 1998.
[12] J. W. Hsieh, W. F. Hu, C. J. Chang, and Y. S. Chen, “Shadow elimination for effective moving object detection by Gaussian shadow modeling,” Image and Vision Computing 21(2003)505-516.
[13] Toyoda, H., “Auto Focus system for video camera,” ITEJ TEBS 87-10 pp7-12.
[14] R. Mech and M. Wollborn, “A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera,” Signal Processing, vol. 66, pp. 203–217, 1998.
[15] A. Smolic´, T. Sikora, and J.-R. Ohm, “Long-term global motion estimation and its application for sprite coding, content description and segmentation,” IEEE Trans. Circuits Syst. Video Technol., vol. 9, pp. 1227–1242, 1999.
[16] Engineering Statistics HandBook, http://www.itl.nist.gov/div898/handbook/eda/section3/eda3661.htm.
[17] D. Hepper, “Efficiency analysis and application of uncovered background prediction in a low bit rate image coder,” IEEE Transactions Commun., vol. 38, pp. 1578–1584, 1990.
[18] S.Y. Chien, S.Y. Ma, and L.G. Chen, “Efficient moving object segmentation algorithm using background registration technique,” IEEE Trans. Circuits Syst. Video Technol., vol.12, no.7, pp. 577-586, 2002.
[19] Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, “An efficient video segmentation algorithm for real-time MPEG-4 camera system,” in Proceedings of Visul Communication and Image Processing(VCIP2000), 2000.
[20] Tony C. T. Kuo, Y. B. Lin and Arbee L. P. Chen, “Efficient Shot Change Detection on Compressed Video Data,” in Proc. of IEEE Workshop on Multimedia Database Management Systems, pp. 101-108, 1996.
[21] Lu, C.S., “Block DCT-Based Robust Watermarking Using Side Information Extracted by Mean Filtering,” Int. Conf. Pattern Recognition, pp. 1001-1004, 2002.
[22] X. Lai and J. Massey, “A Proposal For A New Block Encryption Standard,” Proceeding, EUROCRYPT '90 (Springer-Verlag, Berlin) pp.389-404, 1990.