在影像處理和視訊應用中，影像切割佔有十分重要的地位。影像切割的目的是在圖像中簡化圖像的表現形式，使圖像能更方便進行分析及處理。考量到不同的影像類型，有各種不同的演算法來做為高效率的影像切割結果，這些方法通常會針對鄰近紋理、顏色或是亮度同值合併的特性來完成影像切割。考慮到演算效能的情況下，通常會使用區域成長的技術作為分割的初始結果，進而使用動態合併分割區域的方式來達到影像分割的目的。
雖然有很多研究提出了不同的切割技術，但在一個高準確的切割演算法使用的技術中，通常需要大量的記憶體做為分析影像類型或做為迭代區塊成長以及合併的儲存空間。在本論文中，我們提出了以內容感知(Content-aware)的影像分析，並在HSV色彩空間中使用低記憶體存取特性的系統架構完成影像動態切割技術。接著將所提出的影像切割演算法用於2D轉3D應用中，藉由切割結果及分析移動向量來模擬不同攝影機運動模型，根據我們前景移動向量較大的假設來完成深度估測的系統。實驗結果顯示與現有切割演算法比較，所提出的切割演算法具有爭力的效能，且複雜度與其他效能相近的演算法比較低上許多。

Image segmentation is an important field in video applications and image processing. The goal of segmentation is to simplify the image representation for further analysis. There are a variety of efficient algorithms, which usually segment an image concerning the adjacent texture, color, and brightness for different image patterns. In order to acquire better performance, region based algorithms utilize region growing techniques to split and merge the regions dynamically.

Recently, a variety of segmentation algorithms are developed. However, in order to obtaining high-accurate segmentation results, huge storage and computation are required for analyzing different image types or growing regions. In this thesis, a content-aware image analysis and dynamic segmentation algorithm are proposed based on the HSV color space and realized using a low-memory-access system architecture. Then, the segmentation algorithm is employed in a 2D to 3D conversion applications considering to motion cue of segmented objects. The experimental results reveal that the performance in proposed segmentation algorithm is with competition to related works and the complexity is relatively low compare to other algorithms with similar score.

[1] 賴文能、陳韋志, “淺談2D 至3D 視訊轉換技術” , 影像與識別(IPPR)2010, vol.16 no. 2, pp.61-75.
[2] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision, Vols. I and II, Addison-Wesley, Reading, Mass., 1992.
[3] W. Skarbek and A. Koschan, "Colour image segmentation - a survey -, " Tech. rep., Institute for Technical Informatics, Technical University of Berlin, 1994.
[4] N. R. Pal and S. K. Pal, ”A Review on Image Segmentation techniques,” Pattern Recognition, Vol. 26, pages 1277-1294, 1993.
[5] Y.-W. Tai , J. Jia and C.-K. Tang "Soft Color Segmentation and Its Applications," EEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 9, pp.1520 -1537, 2007.
[6] Wang, H., Suter, D., 2003. “Color image segmentation using global information and local homogeneity,” Proc. of Digital Image Computing: Techniques and Applications, pp. 89-98, Dec. 2003.
[7] L. Shafarenko, M. Petrou and ,J. Kittler, ”Automatic watershed segmentation of randomly textured color images,” IEEE Trans. Image Processing, vol. 6, no.11, pp.1530-1544, Nov. 1997.
[8] S. Chen, W. Lin and C. Chen , ”Split-and-merge image segmentation based on localized feature analysis and statistical tests,” CVGIP: Graph. Models Image Process, vol. 53, pp.457-475 ,Sept. 1991.
[9] Aldo v. Wangenheim , Rafael F. Bertoldi, Daniel D. Abdala , Michael M. Richter, “Color image segmentation guided by a color gradient network,” Pattern Recognition Letters, vol. 28, pp.1795-1803, Oct. 2007.
[10] Ping Li, Rene Klein Gunnewiek, “On Creating Depth Maps from Monoscopic Video using Structure from Motion,” Proc. of IEEE Workshop on Content Generation and Coding for 3D-television, pp.508-515, 2006.
[11] S. Battiato, S. Curti, M. La Cascia, E. Scordato, and M. Tortora, “Depth Map Generation By Image Classification,” Three-Dimensional Image Capture and Applications VI, vol. 5302, pp. 95-104, 2004.
[12] H.-Y. Lee , H.-K. Lee and Y.-H. Ha, “Spatial color descriptor for image retrieval and video segmentation,” IEEE Trans. Multimedia, vol. 5, no. 3, pp. 358-367, 2003.
[13] X. Song and G. Fan, “Joint key-frame extraction and object segmentation for content-based video analysis,” IEEE Trans. Circuits Syst. Video Technol, vol. 16, no. 7, pp.904-914 2006.
[14] W. Xiong and J. C. M. Lee, “Efficient scene change detection and camera motion annotation for video classification, ” Comput. Vis. Image Under-stand, vol. 71, no. 2, pp. 166-181, 1998.
[15] L.Y Duan, J. S. Jin, Q. Tian, and C. S. Xu, “Nonparametric Motion Characterization for Robust Classification of Camera Motion Patterns, ” IEEE Transctions on multimedia, vol. 8, no. 2, pp. 323-339, 2006.
[16] He, L. Chao, Y. Suzuki, K. “Two Efficient Label-Equivalence-Based Connected-Component Labeling Algorithms for 3-D Binary Images,” IEEE Transactions on Image Processing, vol. 20, no. 8. Aug. 2011.
[17] Varekamp, C., and Barenbrug, B.: “Improved depth propagation for 2D to 3D video conversion using key-frames,” Proc. 4th European Conf. on Visual Media Production (IETCVMP), London, UK, pp. 1-7, 2007.
[18] Y.-L. Chang, J.-Y. Chang, Y.-M. Tsai, C.-L. Lee, and L.-G. Chen, “Priority Depth Fusion for the 2D-to-3D Conversion System,” SPIE Proc. Three-Dimensional Image Capture Applicat., vol. 20, pp.1-8, 2008.
[19] Pablo Arbelaez , Michael Maire , Charless Fowlkes , Jitendra Malik, “Contour Detection and Hierarchical Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.33 no.5, pp.898-916, May. 2011.
[20] E. Sharon, M. Galun, D. Sharon, R. Basri, and A. Brandt,“Hierarchy and Adaptivity in Segmenting Visual Scenes,” Nature , vol. 442, pp. 810-813, June. 2006.
[21] P.F. Felzenszwalb and D.P. Huttenlocher, “Efficient Graph-Based Image Segmentation,” International Journal of Computer Vision(IJCV), vol. 59, pp.167-181, 2004.
[22] T. Cour, F. Benezit, and J. Shi, “Spectral Segmentation with Multiscale Graph Decomposition,” in Proc. Computer Vision and Pattern Recognition, vol. 2, pp. 1124-1131, 2005.
[23] D. Comaniciu and P. Meer, “Mean Shift: A Robust Approach Toward Feature Space Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, May 2002.
[24] T.-W. Chen, C.-H. Sun, J.-Y. Bai, H.-R. Chen, and S.-Y. Chien, “Architectural analyses of K-Means silicon intellectual property for image segmentation,” in Proc. International Symposium on Circuits and Systems, pp.2578-2581, May. 2008.
[25] T.-W. Chen and S.-Y. Chien "Flexible hardware architecture of hierarchical K-means clustering for large cluster number", IEEE Trans. Very Large Scale Integrat. (VLSI) Syst, vol. 19, no. 8, pp.1336-1345 .2011.