基于图论的图像分割及其嵌入式应用研究
|
摘要
图像分割是一种底层的图像处理技术,它根据特定的特征将图像分离为连通的有意义区域,可以广泛应用在图像及视频的高级处理任务中。图像分割技术经过几十年的发展,形成了众多的方法、繁杂的类别和海量的文献,但是与人眼视觉特征相一致的全局分割问题一直得不到解决。在这些方法中,基于图论最小生成树的方法利用区域比较准则和最小生成树算法分割图像,具有获取全局特征的能力,计算速度快,是一种可以作为应用研究的分割方法之一。本文的工作主要基于此算法。为了提高此算法应用的可能性,我们需要更改算法及优化程序,提高其全局分割效果和计算速度。本文在分析基于最小生成树分割算法概念、原理、数据结构和实现方式的基础上,发现其运算瓶颈为边的数目,也就是图中实际计算的节点数目。因此本文利用图像局部特征相似的特性,使用N×N, N=1,2,3大小的自适应像素块映射为单个计算节点,大大降低了实际计算的节点和边的数目,从而降低了核心算法的计算复杂度。
为了适应块结构,本文更改了邻域系统,提出了基本连接和超连接的层次。基本连接保证了相邻区域的邻近性,而超连接提供了区域之间的连续性。这种两层的连接方式提高了算法获取全局特征的能力,获得了既不过分割也不欠分割的效果,接近图像对象的数目,减少了原算法分割区域的数目。另外,为了分析基于最小生成树算法的结构,本文将其分为三个阶段:前处理、核心算法和后处理。原算法大部分的计算负担集中在核心算法上,算法结构极不均衡。因此,本文在保证三个阶段接口不变的基础上,将构造图的过程从核心算法阶段转移到前处理阶段,均衡了计算量,增加了算法并行处理的能力。
图像进行分层分析和表达由来已久,具有在不同分辨率下表现图像内容的优势。金字塔图像分割方法是一种分层的分析方法,其突出优点是可以累积局部特征,从而表现全局特征。金字塔分为规则金字塔和非规则金字塔,后者可以克服前者的刚性特点,与图像内容相适应,成为金字塔图像分割算法的主要实现形式。人们提出了不同的非规则金字塔数据结构和缩减方法,但是大多数比较复杂。本文利用基于最小生成树分割算法计算速度快、结构简单、有效进行区域比较的优势,将其作为缩减核应用到非规则金字塔结构中,形成一种快速有效的块嵌入非规则金字塔分割算法。为了将金字塔高度控制在合理范围内,提高缩减因子,本文在第零层使用块结构加快其收敛速度,并提出了一种快速的邻近区域搜索方法以有效地构造高一层的边。试验结果表明,新的算法具有良好的分割效果和计算速度。
块嵌入非规则金字塔分割算法使用区域的特征平均值代替父节点的特征值,降低了噪声对算法的影响,从而无需额外的去噪方法,消除了原算法的高斯滤波参数。本文使用权重的最大最小差值代替原算法抑制小区域的参数,可以在每层上自动适应图像的特征。另外,在构造块结构的过程中,本文使用图像的标准差作为比较准则,从而无需输入块构造参数。金字塔累积局部特征的本质可以去除合并小区域的步骤,从而消除了最小区域参数。本文的这些工作使块嵌入非规则金字塔分割算法成为一个参数独立的自动分割算法,有利于实际应用。
良好的分割效果与快速计算速度使分割算法进行实时应用成为可能。本文在高清数字电视解码器片上系统平台软硬件工作的基础上,分析了基于MIPS处理器的嵌入式平台在时间和空间上的运算资源优化,尝试将基于最小生成树的图像分割算法进行嵌入式移植。在回顾算法改进的基础上,本文对程序代码进行运行时间和空间上的优化,包括运行时间剖析、缓存优化、调用关系优化和动态内存分析等,以软件IP的形式移植到基于MIPS开发平台Malta板上。分割程序建立在一个嵌入式软件系统上,包括启动程序、Linux操作系统、API和库等,以主机控制目标板的方式运行,通过网络远程读写图像文件。
Image Segmentation is a low-level technique of image processing. It partitions images into meaningful connected regions by some specific image features. The high-level applications of it include image & video processing tasks, covering fields of broadcast, computer network, pattern recognition, and machine vision, etc. Research on image segmentation techniques has duration of several decades of years. Although there exist many methods, multiple classes, and a huge literature in this field, the problem of global segmentation having vision consistency with human eyes is not solved well.
Among all of these image segmentation methods, the one based on Minimum Spanning Tree (MST) and region comparison predicates has the capability of capturing global features. It also runs quickly, having computational complexity nearly linear to the pixel number. The two dominant advantages give it the possibility to application. Our work mainly bases on the MST-based algorithm.
In order to improve the segmentation results and computational speed, we concentrate the modification efforts on two sides: algorithm and program. The algorithm details of the concepts, theories, data structures, and implementation ways are studied.
We find that the bottle neck of the algorithm dues to the number of graph edges, i.e., the actual number of computed vertices in the mapped graph. Instead of mapping the image pixel by pixel, our work represents with one vertex a square block of image pixels with fixed size of N×N, N=1,2,3. This trick utilizes the similarity of local image features among neighboring pixels, significantly decreasing the number of graph edges. The fixed square blocks simplify the work of deciding whether one pixel belongs to some block. We change the neighboring system to adapt with the square blocks. It consists of two layers: the basic and super connection. The basic connection keeps the proximity of regions, and the super connection keeps the continuity of regions. They improve the capability of capturing global features. The segmentation produces neither over-segmented nor under-segmented regions. We classify the algorithm into three stages: preprocessor, kernel, and postprocessor. The structure facilitates the balance of computational loads. The original algorithm has a big portion of computation in the kernel. Therefore we move the procedure of graph building from kernel into the preprocessor by keeping the interfaces unchanged. The modification improves the ability of parallel processing.
Analyzing and representing images in a hierarchical way has a long history. It has advantages of showing image contents in different definitions. Graph pyramids in image segmentation can accumulate local features, representing in a coarse definition the global features. Pyramids have two classes: regular and irregular pyramid. Irregular pyramid is also called adaptive pyramid, which overcomes the rigidity of regular pyramid and is adaptive to the contents of images. The irregular pyramid structure is the main implementation in segmentation methods. Many data structure and decimation schemes about irregular pyramids have been presented, but most of them are too complex.
Our work use the MST-based segmentation algorithm as an irregular contraction kernel because of its advantages of global segmentation, high running speed, and simple algorithm structure. The blocks are used in level 0 to improve convergence speed. A new fast neighbor region searching method is given to efficiently construct the edges in higher level. These efforts limit the contraction factor and pyramid height, and show a new irregular pyramid segmentation algorithm with embedded blocks. More efficient segmentation and higher running speed are verified by the experimental results.
We use some modifications to form a parameter independent segmentation algorithm. Firstly, the feature of parent vertex is replaced by the mean value of its region in our irregular pyramid. It reduces the affect of noise without other methods, therefore removing the Gaussian filter parameter in the original algorithm. Secondly, the parameter of limiting small regions is replaced by the edge weight difference between maximum and minimum value. The modification adapts the algorithm to each level of the irregular pyramid. Thirdly, the deviation of the image feature is computed to replace a threshold parameter in constructing the blocks. Fourthly, the intrinsic contraction of the pyramid gets rid of the procedure of merging small components. Therefore it removes the corresponding parameter.
Good segmentation results and fast solution make our algorithm have a possibility to real-time applications. Based on the work of software/hardware designs on the decoder of High Definition Television System-on-a-Chip platform, we analyze the optimizations of temporal and spatial resources on embedded platform with MIPS processor. The optimization of the MST-based segmentation algorithm is firstly recalled. Then we concentrate the optimization work on program codes, including running time profiling, cache using, function call, and dynamic memory, etc. Finally our segmentation algorithm is ported to MIPS development platform Malta as software IP. It runs in a host-target way on an embedded software system, with components including boot loader, Linux kernel, API and lib. The segmentation program reads/writes image data files via network.
In a word, we study the MST-based image segmentation method and pyramid structures. At the same time, a series of efforts are given to improve the segmentation results and running speed. We also optimize the program in running time and space aspects, and present a porting to embedded platform. The experimental results show good values of our work on theory and application.
为了适应块结构,本文更改了邻域系统,提出了基本连接和超连接的层次。基本连接保证了相邻区域的邻近性,而超连接提供了区域之间的连续性。这种两层的连接方式提高了算法获取全局特征的能力,获得了既不过分割也不欠分割的效果,接近图像对象的数目,减少了原算法分割区域的数目。另外,为了分析基于最小生成树算法的结构,本文将其分为三个阶段:前处理、核心算法和后处理。原算法大部分的计算负担集中在核心算法上,算法结构极不均衡。因此,本文在保证三个阶段接口不变的基础上,将构造图的过程从核心算法阶段转移到前处理阶段,均衡了计算量,增加了算法并行处理的能力。
图像进行分层分析和表达由来已久,具有在不同分辨率下表现图像内容的优势。金字塔图像分割方法是一种分层的分析方法,其突出优点是可以累积局部特征,从而表现全局特征。金字塔分为规则金字塔和非规则金字塔,后者可以克服前者的刚性特点,与图像内容相适应,成为金字塔图像分割算法的主要实现形式。人们提出了不同的非规则金字塔数据结构和缩减方法,但是大多数比较复杂。本文利用基于最小生成树分割算法计算速度快、结构简单、有效进行区域比较的优势,将其作为缩减核应用到非规则金字塔结构中,形成一种快速有效的块嵌入非规则金字塔分割算法。为了将金字塔高度控制在合理范围内,提高缩减因子,本文在第零层使用块结构加快其收敛速度,并提出了一种快速的邻近区域搜索方法以有效地构造高一层的边。试验结果表明,新的算法具有良好的分割效果和计算速度。
块嵌入非规则金字塔分割算法使用区域的特征平均值代替父节点的特征值,降低了噪声对算法的影响,从而无需额外的去噪方法,消除了原算法的高斯滤波参数。本文使用权重的最大最小差值代替原算法抑制小区域的参数,可以在每层上自动适应图像的特征。另外,在构造块结构的过程中,本文使用图像的标准差作为比较准则,从而无需输入块构造参数。金字塔累积局部特征的本质可以去除合并小区域的步骤,从而消除了最小区域参数。本文的这些工作使块嵌入非规则金字塔分割算法成为一个参数独立的自动分割算法,有利于实际应用。
良好的分割效果与快速计算速度使分割算法进行实时应用成为可能。本文在高清数字电视解码器片上系统平台软硬件工作的基础上,分析了基于MIPS处理器的嵌入式平台在时间和空间上的运算资源优化,尝试将基于最小生成树的图像分割算法进行嵌入式移植。在回顾算法改进的基础上,本文对程序代码进行运行时间和空间上的优化,包括运行时间剖析、缓存优化、调用关系优化和动态内存分析等,以软件IP的形式移植到基于MIPS开发平台Malta板上。分割程序建立在一个嵌入式软件系统上,包括启动程序、Linux操作系统、API和库等,以主机控制目标板的方式运行,通过网络远程读写图像文件。
Image Segmentation is a low-level technique of image processing. It partitions images into meaningful connected regions by some specific image features. The high-level applications of it include image & video processing tasks, covering fields of broadcast, computer network, pattern recognition, and machine vision, etc. Research on image segmentation techniques has duration of several decades of years. Although there exist many methods, multiple classes, and a huge literature in this field, the problem of global segmentation having vision consistency with human eyes is not solved well.
Among all of these image segmentation methods, the one based on Minimum Spanning Tree (MST) and region comparison predicates has the capability of capturing global features. It also runs quickly, having computational complexity nearly linear to the pixel number. The two dominant advantages give it the possibility to application. Our work mainly bases on the MST-based algorithm.
In order to improve the segmentation results and computational speed, we concentrate the modification efforts on two sides: algorithm and program. The algorithm details of the concepts, theories, data structures, and implementation ways are studied.
We find that the bottle neck of the algorithm dues to the number of graph edges, i.e., the actual number of computed vertices in the mapped graph. Instead of mapping the image pixel by pixel, our work represents with one vertex a square block of image pixels with fixed size of N×N, N=1,2,3. This trick utilizes the similarity of local image features among neighboring pixels, significantly decreasing the number of graph edges. The fixed square blocks simplify the work of deciding whether one pixel belongs to some block. We change the neighboring system to adapt with the square blocks. It consists of two layers: the basic and super connection. The basic connection keeps the proximity of regions, and the super connection keeps the continuity of regions. They improve the capability of capturing global features. The segmentation produces neither over-segmented nor under-segmented regions. We classify the algorithm into three stages: preprocessor, kernel, and postprocessor. The structure facilitates the balance of computational loads. The original algorithm has a big portion of computation in the kernel. Therefore we move the procedure of graph building from kernel into the preprocessor by keeping the interfaces unchanged. The modification improves the ability of parallel processing.
Analyzing and representing images in a hierarchical way has a long history. It has advantages of showing image contents in different definitions. Graph pyramids in image segmentation can accumulate local features, representing in a coarse definition the global features. Pyramids have two classes: regular and irregular pyramid. Irregular pyramid is also called adaptive pyramid, which overcomes the rigidity of regular pyramid and is adaptive to the contents of images. The irregular pyramid structure is the main implementation in segmentation methods. Many data structure and decimation schemes about irregular pyramids have been presented, but most of them are too complex.
Our work use the MST-based segmentation algorithm as an irregular contraction kernel because of its advantages of global segmentation, high running speed, and simple algorithm structure. The blocks are used in level 0 to improve convergence speed. A new fast neighbor region searching method is given to efficiently construct the edges in higher level. These efforts limit the contraction factor and pyramid height, and show a new irregular pyramid segmentation algorithm with embedded blocks. More efficient segmentation and higher running speed are verified by the experimental results.
We use some modifications to form a parameter independent segmentation algorithm. Firstly, the feature of parent vertex is replaced by the mean value of its region in our irregular pyramid. It reduces the affect of noise without other methods, therefore removing the Gaussian filter parameter in the original algorithm. Secondly, the parameter of limiting small regions is replaced by the edge weight difference between maximum and minimum value. The modification adapts the algorithm to each level of the irregular pyramid. Thirdly, the deviation of the image feature is computed to replace a threshold parameter in constructing the blocks. Fourthly, the intrinsic contraction of the pyramid gets rid of the procedure of merging small components. Therefore it removes the corresponding parameter.
Good segmentation results and fast solution make our algorithm have a possibility to real-time applications. Based on the work of software/hardware designs on the decoder of High Definition Television System-on-a-Chip platform, we analyze the optimizations of temporal and spatial resources on embedded platform with MIPS processor. The optimization of the MST-based segmentation algorithm is firstly recalled. Then we concentrate the optimization work on program codes, including running time profiling, cache using, function call, and dynamic memory, etc. Finally our segmentation algorithm is ported to MIPS development platform Malta as software IP. It runs in a host-target way on an embedded software system, with components including boot loader, Linux kernel, API and lib. The segmentation program reads/writes image data files via network.
In a word, we study the MST-based image segmentation method and pyramid structures. At the same time, a series of efforts are given to improve the segmentation results and running speed. We also optimize the program in running time and space aspects, and present a porting to embedded platform. The experimental results show good values of our work on theory and application.
引文
[1] 余松煜,周源华,吴时光,“数字图像处理”,电子工业出版社,1987。
[2] Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, 2nd Edition, Publishing House of Electronics Industry, 2002.
[3] L. Luccheseyz and S.K. Mitray, “Image Segmentation: A State-of-the-art Survey”, Proceedings Of the Indian National Science Academy (INSA-A), Delhi, India, 207-221, 2001.
[4] Nils J. Nilsson, “Artificial Intelligence: A New Synthesis”, Morgan Kaufmann & China Machine Press, 1999.
[5] Ramesh Jain, Rangachar Kasturi, and Brian G. Schunck, “Machine Vision”, China Machine Press, 2003.
[6] P.F. Felzenszwalb, and D.P. Huttenlocher, “Efficient Graph-Based Image Segmentation”, International Journal of Computer Vision, Kluwer Academic Publishers, vol. 59, no. 2, pp. 167-181, 2004.
[7] 杨帆,廖庆敏,“基于图论的图像分割算法的分析与研究”,电视技术,No.7,pp. 80-83, 2006。
[8] Z. Wu, and R. Leahy, “An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 15, no. 11, pp. 1101-1113, 1993.
[9] J. Shi, and J. Malik, “Normalized Cuts and Image Segmentation,” IEEE Trans. Pattern Anal. And Machine Intell., vol. 22, no. 8, pp. 888-905, Aug. 2000.
[10] Y Weiss, “Segmentation Using Eigenvector: A Unifying View”, IEEE Intl Conf Computer Vision, 2:975～982, 1999.
[11] P. Perona, and W. T. Freeman, “A Factorization Approach to Grouping”, Lecture Notes in Computer Science, 1999.
[12] Jo?o Costeira, and Takeo Kanade, “A Multi-body Factorization Method for Motion Analysis”, ICCV, 1995.
[13] F.R.K. Chung, “Spectral Graph Theory”. Am. Math. Soc., 1997.
[14] Charless Fowlkes, Serge Belongie, Fan Chung, and Jitendra Malik, “Spectral Grouping Using The Nystrom Method”, IEEE Trans on PAMI, 2004; 26(2): 214～225.
[15] Laurent Guigues, Hervé Le Men, and Jean-Pierre Cocquerez, “The Hierarchy of The Cocoons of A Graph and Its Application to Image Segmentation”, Pattern Recognition Letters, Vol. 24, No. 8, pp. 1059-1066, 2003.
[16] R. Marfil, L. Molina-Tanco, A. Bandera, J. A. Rodríguez, and F. Sandoval “Pyramid Segmentation Algorithms Revisited”, Pattern Recognition, Vol. 39, No. 8, pp.1430-1451, 2006.
[17] A. Montanvert, P. Meer, and A. Rosenfield, “Hierarchical Image Analysis Using Irregular Tessellations”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 13, No. 4, pp. 307-316, 1991.
[18] Y. Haxhimusa, and W. Kropatsch, “Segmentation Graph Hierarchies,” Lecture Notes on Computer Science, Vol. 3138, pp. 343-351, Springer-Verlag Berlin Heidelberg, 2004.
[19] W.G. Kropatsch, “Building Irregular Pyramids by Dual Graph Contraction”, IEE Proc. Vision Image Signal Process, 142 (6) , 366–374, (1995).
[20] 闫成新, 桑农, 张天序, “基于图论的图像分割研究进展”, 计算机工程与应用, Vol.42 No.5 P.11-14, 2006.
[21] 闫成新, 桑农, 张天序,“基于图划分的图像直方图聚类分割”,计算机应用, Vol.25 No.3 P.570-572,2005。
[22] 曹建农,方丹霞,“基于图论的图像分割方法及其局限性研究”,测绘技术装备,02,2006。
[23] 牟涛,陈文斌,沈一帆,“一种融合区域生长与图论的图像分割方法”,计算机工程与应用,Vol.41 No.19 P.32-34,104,2005。
[24] Yueyun Shu, G.-A. Bilodeau, F. Cheriet, “Segmentation of Laparoscopic Images: Integrating Graph-based Segmentation and Multistage Region Merging”, Computer and Robot Vision, 2005. Proceedings. The 2nd Canadian Conference on, pp429-436, 2005.
[25] Ming Zhang, Reda Alhajj, “Improving the Graph-Based Image Segmentation Method”, Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence, pp. 617-624, 2006.
[26] Cheng H D, Jiang X H, Sun Y, et al., “Color Image Segmentation: Advances and Prospects”,Pattern Recognition, 2001, 34(12): 2259-2281.
[27] “Color Pixels Classification in an Hybrid Color Space”, Image Processing, Proceedings. 1998 International Conference on, Vol. 1, pp. 176-180, 1998.
[28] Yang Wang, K.-F.Loe, T.Tan, Jian-Kang Wu, “Spatiotemporal Video Segmentation Based on Graphical Models”, Image Processing, IEEE Transactions on, Vol. 14, No. 7, pp. 937-947, 2005
[29] Sanfeliu A.; Alquezar R.; Andrade J.; Climent J.; Serratosa F.; Verges J., “Graph-based Representations and Techniques for Image Processing and Image Analysis”, Pattern Recognition, Volume 35, Number 3, March 2002, pp. 639-650(12)
[30] Vlachos, T.; Constantinides, A.G.; “Graph-theoretical Approach to Colour Picture Segmentation and Contour Classification”, Communications, Speech and Vision, IEE Proceedings I, Volume 140, Issue 1, Feb. 1993 Page(s):36 – 45.
[31] T.H. Cormen, C.E. Leiserson, R.L. Rivest, and C. Stein, “Introduction to Algorithm”, 2nd Edition, The MIT Press, Higher Education Press, Beijing, China, 2002.
[32] Douglas B. West. “Introduction to Graph Theory”, China Machine Press, 2004.
[33] Yuri Boykov, Marie-Pierre Jolly, “Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images”, International Conference on Computer Vision (ICCV), vol. I, pp. 105-112, 2001.
[34] Yuri Boykov, Vladimir Kolmogorov, “An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1124-1137, Sept. 2004.
[35] Gupta, A. Prasad, V.S.N. Davis, L.S. “Extracting Regions of Symmetry”, Image Processing, 2005. ICIP 2005. IEEE International Conference on, Volume: 3, On page(s): III- 133-6, Sept. 2005.
[36] Chia, A. Zagorodnov, V. “Graph Cut Based Segmentation of Convoluted Objects”, Image Processing, 2005. ICIP 2005. IEEE International Conference on, Volume: 3, On page(s): III- 848-51, Sept. 2005
[37] Piali Das, Olga Veksler, Vyacheslav Zavadsky, Yuri Boykov, “Semiautomatic Segmentation with Compact Shape Prior”, Canadian Conference on Computer and Robot Vision (CRV), pp.28-36, June 2006.
[38] 张贤达,“矩阵分析与应用”,清华大学出版社,2004.
[39] Makrogiannis, S. Economou, G. Fotopoulos, S. “A Region Dissimilarity Relation That Combines Feature-Space and Spatial Information for Color Image Segmentation”, Systems, Man and Cybernetics, Part B, IEEE Transactions on, Volume: 35, Issue: 1, On page(s): 44- 53, Feb. 2005.
[40] P. Perona, and W. T. Freeman, “A Factorization Approach to Grouping”, Lecture Notes in Computer Science, 1999.
[41] Kolmogorov, V. Zabin, R. “What Energy Functions Can Be Minimized via Graph Cuts”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Volume: 26, Issue: 2, On page(s): 147- 159, Feb 2004.
[42] Michael Bleyer, Margrit Gelautz, “Graph-cut-based Stereo Matching Using Image Segmentation with Symmetrical Treatment of Occlusions”, Image Communication, Volume 22, Issue 2 (February 2007), Pages: 127-143.
[43] Slabaugh, G. Unal, G. “Graph Cuts Segmentation Using An Elliptical Shape Prior”, Image Processing, 2005. ICIP 2005. IEEE International Conference on, Volume: 2, On page(s): II- 1222-5, Sept. 2005
[44] Jens Gustedt “Efficient Union-Find for Planar Graphs and Other Sparse Graph Classes”, Proceedings of the 22nd International Workshop on Graph-Theoretic Concepts in Computer Science, Vol. 1197, Pages: 181 – 195, 1996.
[45] Robert Endre Tarjan, “Efficiency of a Good But Not Linear Set Union Algorithm”, Journal of the ACM (JACM), Volume 22 , Issue 2 (April 1975), Pages: 215 – 225, 1975.
[46] “Approximate Nearest Neighbor Searching”, http://www.cs.umd.edu/~mount/ANN/
[47] Wang A.-H.-H.; Chen M.-T.; Batlle J.; Casals A.; Freixenet J.; Mart J. “A Review on Strategies for Recognizing Natural Objects in Colour Images of Outdoor Scenes”, Image and Vision Computing, Volume 18, Number 6, 1 May 2000, pp. 515-530(16)
[48] Salvador, E. ; Cavallaro, A. ; Ebrahimi, T. “Cast Shadow Segmentation Using Invariant Colour Features”, Computer Vision and Image Understanding, vol. 95, num. 2 (2004), p. 238-259
[49] Walter G. Kropatsch, Yll Haxhimusa, “Hierarchical Grouping of Non-Connected Structures”, 2004.
[50] Walter G. Kropatsch, Yll Haxhimusa, Zygmunt Pizlo, Georg Langs, “Vision Pyramids That Do Not Grow Too High”, Pattern Recognition Letters 26(3): 319-337 (2005).
[51] Christophe E. Mathieu, Isabelle E. Magnin “On The Choice of The First Level on Graph Pyramids”, Journal of Mathematical Imaging and Vision, Volume 6 , Issue 1 (January 1996), Pages: 85 - 96
[52] Y. Ping, W. Runsheng, L. Diannong, “A New Image Segmentation Approach Based on Linked Pyramid”, International Conference on Signal Processing, 1996, pp. 1118–1121.
[53] F. Ziliani, B. Jensen, “Unsupervised Image Segmentation Using The Modified Pyramidal Linking Approach”, International Conference on Image Processing, vol. 3, 1998, pp. 303–307.
[54] P. Nacken “Image Segmentation by Connectivity Preserving Relinking in Hierarchical Graph Structures”, Pattern Recognition 28 (6) (1995) 907–920.
[55] L. Brun, W.G. Kropatsch, “Receptive Fields within The Combinatorial Pyramid Framework”, Graphical Models 65 (2003) 23–42.
[56] H. Ip, S. Lam, “Alternative Strategies for Irregular Pyramid Construction”, Image Vision Comput. 14 (4) (1996) 297–303.
[57] J.M. Jolion, “Stochastic Pyramid Revisited”, Pattern Recognition Lett. 24 (8) (2003) 1035–1042.
[58] Y. Haxhimusa, R. Glantz, M. Saib, G. Langs, W.G. Kropatsch, “Logarithmic Tapering Graph Pyramid”, L. van Gool (Ed.), Proceedings of the 24th German Association for Pattern Recognition Symposium, Lecture Notes in Computer Science, vol. 2449, Springer, Berlin, 2002, pp. 117–124.
[59] D. Willersinn, W.G. Kropatsch, “Dual Graph Contraction for Irregular Pyramids”, 12th IAPR International Conference on Pattern Recognition, vol. 3, 1994, pp. 251–256.
[60] L. Brun, W.G. Kropatsch, “Construction of combinatorial pyramids”, E. Hancock, M. Vent. (Eds.), Graph Based Representations in Pattern Recognition, Lecture Notes in Computer Science, vol. 2726, Springer, Berlin, 2003, pp. 1–12.
[61] Sunil Arya, David M. Mount, “Approximate Nearest Neighbor Queries in Fixed Dimensions”, ACM-SIAM Symposium on Discrete Algorithms, 1993.
[62] S. Lallich, F. Muhlenbach, J.M. Jolion, “A Test to Control A Region Growing Process within A Hierarchical Graph”, Pattern Recognition 36 (2003) 2201–2211.
[63] Asaduzzaman, A. Mahgoub, I. Sanigepalli, P. Kalva, H. Shankar, R. Furht, B. “Cache Optimization for Mobile Devices Running Multimedia Applications”, Multimedia Software Engineering, 2004. Proceedings. IEEE Sixth International Symposium on, page(s): 499- 506, Dec. 2004.
[64] Jorge Nocedal, Stephen J. Wright, “Numerical Optimization”, 科学出版社,影印版,2006。
[65] Z. Tan, S. Zheng, “Porting A Graph-based Image Segmentation Algorithm to Embedded System”, submitted.
[66] Pospiech, F. Olsen, S. “Embedded Software in The Soc World: How Hds Helps to Face The HW and SW Design Challenge”, Custom Integrated Circuits Conference, 2003. Proceedings of the IEEE 2003, On page(s): 653- 658, Sept. 2003.
[67] Zhiming Tan, Shibao Zheng, Jianling Hu, Yingqi Chen, Peilin Liu, “Design and Implementation of The Software System on MPSoC: An HDTV Decoder Case Study”, Consumer Electronics, IEEE Transactions on, Volume: 52, Issue: 4, On page(s): 1333-1339, 2006.
[68] Zhiming Tan, Shibao Zheng, Peilin Liu, Guixu Lin, Shimei Yu, “An Implementation of Open Source Operating System on Multi-processor System-On-a-Chip”, IEEE Transactions on Consumer Electronics, Vol. 52, No. 3, pp. 1118-1123, Aug. 2006.
[69] Daniel P. Bovet, Marco Cesati, “Understanding The Linux Kernel”, 3rd Edition, O’Reilly, 2006.
[70] Win-Bin See Pao-Ann Hsiung Sao-Jie Chen, “Framework Approach for System on Chip Software Development”, VLSI Technology, Systems, and Applications, 2003 International Symposium on, On page(s): 196- 199, Oct. 2003.
[71] 罗胜钦,“数字集成系统芯片(SoC)设计”,北京希望电子出版社,2002。
[72] Ralph E. Johnson, “Frameworks = (Components + Patterns)”, Communications of the ACM, Volume 40 , Issue 10 (October 1997), Pages: 39 – 42, 1997.
[73] Savage W, Chilton J, Camposano R., “IP Reuse in The System-on-a-Chip Era”, IEEE System Synthesis 2000 Proceedings. Madrid, Spain: IEEE Computer Society Press, 2000.2-7.
[74] R.A.Bergamaschi, J.Cohn, “The A to Z of SoCs,” Computer Aided Design, IEEE/ACM International Conf. on, pp. 791-798, Nov. 2002.
[75] MIPS Technologies Inc., MIPS32 4KTM Processor Core Family Software User’s Manual,Revision 01.17, http://www.mips.com/, Sept. 2002.
[76] Asaduzzaman, A. Mahgoub, I. “Cache Optimization for Embedded Systems Running H.264/AVC Video Decoder”, Computer Systems and Applications, 2006. IEEE International Conference on. On page(s): 665- 672, 2006
[77] Givargis, T. “Improved Indexing For Cache Miss Reduction In Embedded Systems”, Design Automation Conference, 2003. Proceedings, On page(s): 875- 880, June 2003.
[78] John L. Hennessy, and David A. Patterson, “Computer Architecture- A Quantitative Approach”, 3rd Edition, China Machine Press, 2002.
[79] Temam O.; Drach N. “Software Assistance for Data Caches”, Future Generation Computer Systems, Volume 11, Number 6, October 1995, pp. 519-536(18).
[80] D. Sweetman, “See MIPS Run”, Morgan Kaufmann Publishers, Academic Press, 2002.
[81] Ghosh, A. Givargis, T. “Cache Optimization for Embedded Processor Cores: An Analytical Approach”, Computer Aided Design, 2003. ICCAD-2003. International Conference on, On page(s): 342- 347, Nov. 2003.
[82] Alan Dain Samples and Paul N. Hilfinger, “Code Reorganization for Instruction Caches”, System Sciences, 1993, Proceeding of the Twenty-Sixth Hawaii International Conference on, On page(s): 214- 223 vol.1, Jan 1993.
[83] Bruce Eckel, “Thinking in C++”, Prentice Hall, 1998.
[84] Vera, X. Jingling Xue, “Efficient Compile-time Analysis of Cache Behaviour for Programs with IF Statements”, Algorithms and Architectures for Parallel Processing, 2002. Proceedings. Fifth International Conference on, On page(s): 396- 407, 2002.
[85] Zhang Y J. “A Survey on Evaluation Methods for Image Segmentation”, Pattern Recognition, 1996, 29(8): 1335- 1346.
[86] K. Cho, P. Meer, “Image segmentation from consensus information”, Comput. Vision Image Understanding 68 (1997) 72–89.
[87] W.G. Kropatsch, Y. Haxhimusa, “Grouping and segmentation in a hierarchy of graphs”, in: C.A. Bouman, E.L. Miller (Eds.), Computational Imaging II, SPIE, vol. 5299, 2004, pp. 193–204.
[88] Y. Haxhimusa, R. Glantz, W.G. Kropatsch, “Constructing stochastic pyramids by MIDES—maximal independent directed edge set”, in: E. Hancock, M. Vento (Eds.), FourthIAPR-RC15 Workshop on GbR in Pattern Recognition, Lecture Notes in Computer Science, vol. 2726, Springer, Berlin, 2003, pp. 35–46.
[89] J. Huart, P. Bertolino, “Similarity-based and perception-based image segmentation”, in: IEEE International Conference on Image Processing—ICIP 2005, 2005.
[90] R. Marfil, J.A. Rodriguez, A. Bandera, F. Sandoval, “Bounded irregular pyramid: a new structure for colour image segmentation”, Pattern Recognition 37 (3) (2004) 623–626.
[91] D. Prewer, L.J. Kitchen, “Soft image segmentation by weighted linkedpyramid”, Pattern Recognition Lett. 22 (2) (2001) 123–132.
[92] J. Liu, Y. Yang, “Multi-resolution color image segmentation”, IEEE Trans. Pattern Anal. Mach. Intell. 16 (7) (1994) 689–700.
[93] M. Borsotti, P. Campadelli, R. Schettini, “Quantitative evaluation of color image segmentation results”, Pattern Recognition Lett. 19 (1998) 741–747.
[94] B. Sabata, F. Arman, J. Aggarwal, “Convergence of fuzzy-pyramid algorithms”, J. Math. Imaging Vision 4 (1994) 291–302.
[95] H. Rom, S. Peleg, “Image representation using voronoi tessellation: adaptive and secure”, IEEE Comput. Vision Pattern Recognition (1988) 282–285.
[96] W.G. Kropatsch, “From equivalent weighting functions to equivalent contraction kernels”, in: E.Wenger, L.I. Dimitrov (Eds.), Digital Image Processing and Computer Graphics: Applications in Humanities and Natural Sciences, vol. 3346, SPIE, 1998, pp. 310–320.
[97] P. Bertolino, A. Montanvert, “Multiresolution segmentation using the irregular pyramid”, in: International Conference on Image Processing, vol. 1, 1996, pp. 257–260.
[98] B.V. Cherkassky and A.V. Goldberg, “On Implementing Push-Relabel Method for the Maximum Flow Problem,” Algorithmica, vol. 19, pp. 390-410, 1997.
[99] S Sarkar, K L Boyer.Quantitative “Measures of Change Based on Feature Organization: Eigenvalues and Eigenvectors”.In: Proc IEEE Conf Computer Vision and Pattern Recognition, 1996.
[100] Verges-Llahi, J. Climent, J. Sanfeliu, A., “Colour image segmentation solving hard-constraints on graphpartitioning greedy algorithms”, Pattern Recognition, 2000. Proceedings. 15th International Conference on, Volume: 3, On page(s): 625-628 vol.3.
[101] Ratan, A.L. Maron, O. Grimson, W.E.L. Lozano-Perez, T., “A framework for learning queryconcepts in image classification”, Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on, On page(s): 423-429 Vol. 1.
[102] 孙雷,“基于对象的视频编码技术研究”,上海交通大学博士学位论文,2005。
[103] 曾昭平,“基于内容的视频检索研究”,上海交通大学博士学位论文,2002。
[104] 宋利,“图像鲁棒匹配及相关技术的应用研究”,上海交通大学博士学位论文,2005。
[105] Ying X.1; Uberbacher E.C. “2D Image Segmentation Using Minimum Spanning Trees”, Image and Vision Computing, Volume 15, Number 1, January 1997, pp. 47-57(11).
[106] Richard Cole, Philip N. Klein, Robert E. Tarjan, “A Linear-Work Parallel Algorithm for Finding Minimum Spanning Trees”, Annual ACM Symposium on Parallel Algorithms and Architectures, 1994.
[107] Wang Song, Siskind J M. “Image segmentation with ratio cut”, IEEE Trans Pattern Analysis and Machine Intelligence, 2003; 25 (6):675-690.
[108] C Ding, X F Ren, H Zha et al. “Spectral Min- max Cut for Graph Partitioning and Data Clustering”, Proc of the IEEE Intl Conf on Data Mining, 2001: 107~114.
[109] O Veksler. “Image Segmentation by Nested Cuts”. In: Proc IEEE CS Conf Computer Vision and Pattern Recognition, 2000: 339~344。
[2] Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing”, 2nd Edition, Publishing House of Electronics Industry, 2002.
[3] L. Luccheseyz and S.K. Mitray, “Image Segmentation: A State-of-the-art Survey”, Proceedings Of the Indian National Science Academy (INSA-A), Delhi, India, 207-221, 2001.
[4] Nils J. Nilsson, “Artificial Intelligence: A New Synthesis”, Morgan Kaufmann & China Machine Press, 1999.
[5] Ramesh Jain, Rangachar Kasturi, and Brian G. Schunck, “Machine Vision”, China Machine Press, 2003.
[6] P.F. Felzenszwalb, and D.P. Huttenlocher, “Efficient Graph-Based Image Segmentation”, International Journal of Computer Vision, Kluwer Academic Publishers, vol. 59, no. 2, pp. 167-181, 2004.
[7] 杨帆,廖庆敏,“基于图论的图像分割算法的分析与研究”,电视技术,No.7,pp. 80-83, 2006。
[8] Z. Wu, and R. Leahy, “An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 15, no. 11, pp. 1101-1113, 1993.
[9] J. Shi, and J. Malik, “Normalized Cuts and Image Segmentation,” IEEE Trans. Pattern Anal. And Machine Intell., vol. 22, no. 8, pp. 888-905, Aug. 2000.
[10] Y Weiss, “Segmentation Using Eigenvector: A Unifying View”, IEEE Intl Conf Computer Vision, 2:975～982, 1999.
[11] P. Perona, and W. T. Freeman, “A Factorization Approach to Grouping”, Lecture Notes in Computer Science, 1999.
[12] Jo?o Costeira, and Takeo Kanade, “A Multi-body Factorization Method for Motion Analysis”, ICCV, 1995.
[13] F.R.K. Chung, “Spectral Graph Theory”. Am. Math. Soc., 1997.
[14] Charless Fowlkes, Serge Belongie, Fan Chung, and Jitendra Malik, “Spectral Grouping Using The Nystrom Method”, IEEE Trans on PAMI, 2004; 26(2): 214～225.
[15] Laurent Guigues, Hervé Le Men, and Jean-Pierre Cocquerez, “The Hierarchy of The Cocoons of A Graph and Its Application to Image Segmentation”, Pattern Recognition Letters, Vol. 24, No. 8, pp. 1059-1066, 2003.
[16] R. Marfil, L. Molina-Tanco, A. Bandera, J. A. Rodríguez, and F. Sandoval “Pyramid Segmentation Algorithms Revisited”, Pattern Recognition, Vol. 39, No. 8, pp.1430-1451, 2006.
[17] A. Montanvert, P. Meer, and A. Rosenfield, “Hierarchical Image Analysis Using Irregular Tessellations”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Vol. 13, No. 4, pp. 307-316, 1991.
[18] Y. Haxhimusa, and W. Kropatsch, “Segmentation Graph Hierarchies,” Lecture Notes on Computer Science, Vol. 3138, pp. 343-351, Springer-Verlag Berlin Heidelberg, 2004.
[19] W.G. Kropatsch, “Building Irregular Pyramids by Dual Graph Contraction”, IEE Proc. Vision Image Signal Process, 142 (6) , 366–374, (1995).
[20] 闫成新, 桑农, 张天序, “基于图论的图像分割研究进展”, 计算机工程与应用, Vol.42 No.5 P.11-14, 2006.
[21] 闫成新, 桑农, 张天序,“基于图划分的图像直方图聚类分割”,计算机应用, Vol.25 No.3 P.570-572,2005。
[22] 曹建农,方丹霞,“基于图论的图像分割方法及其局限性研究”,测绘技术装备,02,2006。
[23] 牟涛,陈文斌,沈一帆,“一种融合区域生长与图论的图像分割方法”,计算机工程与应用,Vol.41 No.19 P.32-34,104,2005。
[24] Yueyun Shu, G.-A. Bilodeau, F. Cheriet, “Segmentation of Laparoscopic Images: Integrating Graph-based Segmentation and Multistage Region Merging”, Computer and Robot Vision, 2005. Proceedings. The 2nd Canadian Conference on, pp429-436, 2005.
[25] Ming Zhang, Reda Alhajj, “Improving the Graph-Based Image Segmentation Method”, Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence, pp. 617-624, 2006.
[26] Cheng H D, Jiang X H, Sun Y, et al., “Color Image Segmentation: Advances and Prospects”,Pattern Recognition, 2001, 34(12): 2259-2281.
[27] “Color Pixels Classification in an Hybrid Color Space”, Image Processing, Proceedings. 1998 International Conference on, Vol. 1, pp. 176-180, 1998.
[28] Yang Wang, K.-F.Loe, T.Tan, Jian-Kang Wu, “Spatiotemporal Video Segmentation Based on Graphical Models”, Image Processing, IEEE Transactions on, Vol. 14, No. 7, pp. 937-947, 2005
[29] Sanfeliu A.; Alquezar R.; Andrade J.; Climent J.; Serratosa F.; Verges J., “Graph-based Representations and Techniques for Image Processing and Image Analysis”, Pattern Recognition, Volume 35, Number 3, March 2002, pp. 639-650(12)
[30] Vlachos, T.; Constantinides, A.G.; “Graph-theoretical Approach to Colour Picture Segmentation and Contour Classification”, Communications, Speech and Vision, IEE Proceedings I, Volume 140, Issue 1, Feb. 1993 Page(s):36 – 45.
[31] T.H. Cormen, C.E. Leiserson, R.L. Rivest, and C. Stein, “Introduction to Algorithm”, 2nd Edition, The MIT Press, Higher Education Press, Beijing, China, 2002.
[32] Douglas B. West. “Introduction to Graph Theory”, China Machine Press, 2004.
[33] Yuri Boykov, Marie-Pierre Jolly, “Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images”, International Conference on Computer Vision (ICCV), vol. I, pp. 105-112, 2001.
[34] Yuri Boykov, Vladimir Kolmogorov, “An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, pp. 1124-1137, Sept. 2004.
[35] Gupta, A. Prasad, V.S.N. Davis, L.S. “Extracting Regions of Symmetry”, Image Processing, 2005. ICIP 2005. IEEE International Conference on, Volume: 3, On page(s): III- 133-6, Sept. 2005.
[36] Chia, A. Zagorodnov, V. “Graph Cut Based Segmentation of Convoluted Objects”, Image Processing, 2005. ICIP 2005. IEEE International Conference on, Volume: 3, On page(s): III- 848-51, Sept. 2005
[37] Piali Das, Olga Veksler, Vyacheslav Zavadsky, Yuri Boykov, “Semiautomatic Segmentation with Compact Shape Prior”, Canadian Conference on Computer and Robot Vision (CRV), pp.28-36, June 2006.
[38] 张贤达,“矩阵分析与应用”,清华大学出版社,2004.
[39] Makrogiannis, S. Economou, G. Fotopoulos, S. “A Region Dissimilarity Relation That Combines Feature-Space and Spatial Information for Color Image Segmentation”, Systems, Man and Cybernetics, Part B, IEEE Transactions on, Volume: 35, Issue: 1, On page(s): 44- 53, Feb. 2005.
[40] P. Perona, and W. T. Freeman, “A Factorization Approach to Grouping”, Lecture Notes in Computer Science, 1999.
[41] Kolmogorov, V. Zabin, R. “What Energy Functions Can Be Minimized via Graph Cuts”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, Volume: 26, Issue: 2, On page(s): 147- 159, Feb 2004.
[42] Michael Bleyer, Margrit Gelautz, “Graph-cut-based Stereo Matching Using Image Segmentation with Symmetrical Treatment of Occlusions”, Image Communication, Volume 22, Issue 2 (February 2007), Pages: 127-143.
[43] Slabaugh, G. Unal, G. “Graph Cuts Segmentation Using An Elliptical Shape Prior”, Image Processing, 2005. ICIP 2005. IEEE International Conference on, Volume: 2, On page(s): II- 1222-5, Sept. 2005
[44] Jens Gustedt “Efficient Union-Find for Planar Graphs and Other Sparse Graph Classes”, Proceedings of the 22nd International Workshop on Graph-Theoretic Concepts in Computer Science, Vol. 1197, Pages: 181 – 195, 1996.
[45] Robert Endre Tarjan, “Efficiency of a Good But Not Linear Set Union Algorithm”, Journal of the ACM (JACM), Volume 22 , Issue 2 (April 1975), Pages: 215 – 225, 1975.
[46] “Approximate Nearest Neighbor Searching”, http://www.cs.umd.edu/~mount/ANN/
[47] Wang A.-H.-H.; Chen M.-T.; Batlle J.; Casals A.; Freixenet J.; Mart J. “A Review on Strategies for Recognizing Natural Objects in Colour Images of Outdoor Scenes”, Image and Vision Computing, Volume 18, Number 6, 1 May 2000, pp. 515-530(16)
[48] Salvador, E. ; Cavallaro, A. ; Ebrahimi, T. “Cast Shadow Segmentation Using Invariant Colour Features”, Computer Vision and Image Understanding, vol. 95, num. 2 (2004), p. 238-259
[49] Walter G. Kropatsch, Yll Haxhimusa, “Hierarchical Grouping of Non-Connected Structures”, 2004.
[50] Walter G. Kropatsch, Yll Haxhimusa, Zygmunt Pizlo, Georg Langs, “Vision Pyramids That Do Not Grow Too High”, Pattern Recognition Letters 26(3): 319-337 (2005).
[51] Christophe E. Mathieu, Isabelle E. Magnin “On The Choice of The First Level on Graph Pyramids”, Journal of Mathematical Imaging and Vision, Volume 6 , Issue 1 (January 1996), Pages: 85 - 96
[52] Y. Ping, W. Runsheng, L. Diannong, “A New Image Segmentation Approach Based on Linked Pyramid”, International Conference on Signal Processing, 1996, pp. 1118–1121.
[53] F. Ziliani, B. Jensen, “Unsupervised Image Segmentation Using The Modified Pyramidal Linking Approach”, International Conference on Image Processing, vol. 3, 1998, pp. 303–307.
[54] P. Nacken “Image Segmentation by Connectivity Preserving Relinking in Hierarchical Graph Structures”, Pattern Recognition 28 (6) (1995) 907–920.
[55] L. Brun, W.G. Kropatsch, “Receptive Fields within The Combinatorial Pyramid Framework”, Graphical Models 65 (2003) 23–42.
[56] H. Ip, S. Lam, “Alternative Strategies for Irregular Pyramid Construction”, Image Vision Comput. 14 (4) (1996) 297–303.
[57] J.M. Jolion, “Stochastic Pyramid Revisited”, Pattern Recognition Lett. 24 (8) (2003) 1035–1042.
[58] Y. Haxhimusa, R. Glantz, M. Saib, G. Langs, W.G. Kropatsch, “Logarithmic Tapering Graph Pyramid”, L. van Gool (Ed.), Proceedings of the 24th German Association for Pattern Recognition Symposium, Lecture Notes in Computer Science, vol. 2449, Springer, Berlin, 2002, pp. 117–124.
[59] D. Willersinn, W.G. Kropatsch, “Dual Graph Contraction for Irregular Pyramids”, 12th IAPR International Conference on Pattern Recognition, vol. 3, 1994, pp. 251–256.
[60] L. Brun, W.G. Kropatsch, “Construction of combinatorial pyramids”, E. Hancock, M. Vent. (Eds.), Graph Based Representations in Pattern Recognition, Lecture Notes in Computer Science, vol. 2726, Springer, Berlin, 2003, pp. 1–12.
[61] Sunil Arya, David M. Mount, “Approximate Nearest Neighbor Queries in Fixed Dimensions”, ACM-SIAM Symposium on Discrete Algorithms, 1993.
[62] S. Lallich, F. Muhlenbach, J.M. Jolion, “A Test to Control A Region Growing Process within A Hierarchical Graph”, Pattern Recognition 36 (2003) 2201–2211.
[63] Asaduzzaman, A. Mahgoub, I. Sanigepalli, P. Kalva, H. Shankar, R. Furht, B. “Cache Optimization for Mobile Devices Running Multimedia Applications”, Multimedia Software Engineering, 2004. Proceedings. IEEE Sixth International Symposium on, page(s): 499- 506, Dec. 2004.
[64] Jorge Nocedal, Stephen J. Wright, “Numerical Optimization”, 科学出版社,影印版,2006。
[65] Z. Tan, S. Zheng, “Porting A Graph-based Image Segmentation Algorithm to Embedded System”, submitted.
[66] Pospiech, F. Olsen, S. “Embedded Software in The Soc World: How Hds Helps to Face The HW and SW Design Challenge”, Custom Integrated Circuits Conference, 2003. Proceedings of the IEEE 2003, On page(s): 653- 658, Sept. 2003.
[67] Zhiming Tan, Shibao Zheng, Jianling Hu, Yingqi Chen, Peilin Liu, “Design and Implementation of The Software System on MPSoC: An HDTV Decoder Case Study”, Consumer Electronics, IEEE Transactions on, Volume: 52, Issue: 4, On page(s): 1333-1339, 2006.
[68] Zhiming Tan, Shibao Zheng, Peilin Liu, Guixu Lin, Shimei Yu, “An Implementation of Open Source Operating System on Multi-processor System-On-a-Chip”, IEEE Transactions on Consumer Electronics, Vol. 52, No. 3, pp. 1118-1123, Aug. 2006.
[69] Daniel P. Bovet, Marco Cesati, “Understanding The Linux Kernel”, 3rd Edition, O’Reilly, 2006.
[70] Win-Bin See Pao-Ann Hsiung Sao-Jie Chen, “Framework Approach for System on Chip Software Development”, VLSI Technology, Systems, and Applications, 2003 International Symposium on, On page(s): 196- 199, Oct. 2003.
[71] 罗胜钦,“数字集成系统芯片(SoC)设计”,北京希望电子出版社,2002。
[72] Ralph E. Johnson, “Frameworks = (Components + Patterns)”, Communications of the ACM, Volume 40 , Issue 10 (October 1997), Pages: 39 – 42, 1997.
[73] Savage W, Chilton J, Camposano R., “IP Reuse in The System-on-a-Chip Era”, IEEE System Synthesis 2000 Proceedings. Madrid, Spain: IEEE Computer Society Press, 2000.2-7.
[74] R.A.Bergamaschi, J.Cohn, “The A to Z of SoCs,” Computer Aided Design, IEEE/ACM International Conf. on, pp. 791-798, Nov. 2002.
[75] MIPS Technologies Inc., MIPS32 4KTM Processor Core Family Software User’s Manual,Revision 01.17, http://www.mips.com/, Sept. 2002.
[76] Asaduzzaman, A. Mahgoub, I. “Cache Optimization for Embedded Systems Running H.264/AVC Video Decoder”, Computer Systems and Applications, 2006. IEEE International Conference on. On page(s): 665- 672, 2006
[77] Givargis, T. “Improved Indexing For Cache Miss Reduction In Embedded Systems”, Design Automation Conference, 2003. Proceedings, On page(s): 875- 880, June 2003.
[78] John L. Hennessy, and David A. Patterson, “Computer Architecture- A Quantitative Approach”, 3rd Edition, China Machine Press, 2002.
[79] Temam O.; Drach N. “Software Assistance for Data Caches”, Future Generation Computer Systems, Volume 11, Number 6, October 1995, pp. 519-536(18).
[80] D. Sweetman, “See MIPS Run”, Morgan Kaufmann Publishers, Academic Press, 2002.
[81] Ghosh, A. Givargis, T. “Cache Optimization for Embedded Processor Cores: An Analytical Approach”, Computer Aided Design, 2003. ICCAD-2003. International Conference on, On page(s): 342- 347, Nov. 2003.
[82] Alan Dain Samples and Paul N. Hilfinger, “Code Reorganization for Instruction Caches”, System Sciences, 1993, Proceeding of the Twenty-Sixth Hawaii International Conference on, On page(s): 214- 223 vol.1, Jan 1993.
[83] Bruce Eckel, “Thinking in C++”, Prentice Hall, 1998.
[84] Vera, X. Jingling Xue, “Efficient Compile-time Analysis of Cache Behaviour for Programs with IF Statements”, Algorithms and Architectures for Parallel Processing, 2002. Proceedings. Fifth International Conference on, On page(s): 396- 407, 2002.
[85] Zhang Y J. “A Survey on Evaluation Methods for Image Segmentation”, Pattern Recognition, 1996, 29(8): 1335- 1346.
[86] K. Cho, P. Meer, “Image segmentation from consensus information”, Comput. Vision Image Understanding 68 (1997) 72–89.
[87] W.G. Kropatsch, Y. Haxhimusa, “Grouping and segmentation in a hierarchy of graphs”, in: C.A. Bouman, E.L. Miller (Eds.), Computational Imaging II, SPIE, vol. 5299, 2004, pp. 193–204.
[88] Y. Haxhimusa, R. Glantz, W.G. Kropatsch, “Constructing stochastic pyramids by MIDES—maximal independent directed edge set”, in: E. Hancock, M. Vento (Eds.), FourthIAPR-RC15 Workshop on GbR in Pattern Recognition, Lecture Notes in Computer Science, vol. 2726, Springer, Berlin, 2003, pp. 35–46.
[89] J. Huart, P. Bertolino, “Similarity-based and perception-based image segmentation”, in: IEEE International Conference on Image Processing—ICIP 2005, 2005.
[90] R. Marfil, J.A. Rodriguez, A. Bandera, F. Sandoval, “Bounded irregular pyramid: a new structure for colour image segmentation”, Pattern Recognition 37 (3) (2004) 623–626.
[91] D. Prewer, L.J. Kitchen, “Soft image segmentation by weighted linkedpyramid”, Pattern Recognition Lett. 22 (2) (2001) 123–132.
[92] J. Liu, Y. Yang, “Multi-resolution color image segmentation”, IEEE Trans. Pattern Anal. Mach. Intell. 16 (7) (1994) 689–700.
[93] M. Borsotti, P. Campadelli, R. Schettini, “Quantitative evaluation of color image segmentation results”, Pattern Recognition Lett. 19 (1998) 741–747.
[94] B. Sabata, F. Arman, J. Aggarwal, “Convergence of fuzzy-pyramid algorithms”, J. Math. Imaging Vision 4 (1994) 291–302.
[95] H. Rom, S. Peleg, “Image representation using voronoi tessellation: adaptive and secure”, IEEE Comput. Vision Pattern Recognition (1988) 282–285.
[96] W.G. Kropatsch, “From equivalent weighting functions to equivalent contraction kernels”, in: E.Wenger, L.I. Dimitrov (Eds.), Digital Image Processing and Computer Graphics: Applications in Humanities and Natural Sciences, vol. 3346, SPIE, 1998, pp. 310–320.
[97] P. Bertolino, A. Montanvert, “Multiresolution segmentation using the irregular pyramid”, in: International Conference on Image Processing, vol. 1, 1996, pp. 257–260.
[98] B.V. Cherkassky and A.V. Goldberg, “On Implementing Push-Relabel Method for the Maximum Flow Problem,” Algorithmica, vol. 19, pp. 390-410, 1997.
[99] S Sarkar, K L Boyer.Quantitative “Measures of Change Based on Feature Organization: Eigenvalues and Eigenvectors”.In: Proc IEEE Conf Computer Vision and Pattern Recognition, 1996.
[100] Verges-Llahi, J. Climent, J. Sanfeliu, A., “Colour image segmentation solving hard-constraints on graphpartitioning greedy algorithms”, Pattern Recognition, 2000. Proceedings. 15th International Conference on, Volume: 3, On page(s): 625-628 vol.3.
[101] Ratan, A.L. Maron, O. Grimson, W.E.L. Lozano-Perez, T., “A framework for learning queryconcepts in image classification”, Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on, On page(s): 423-429 Vol. 1.
[102] 孙雷,“基于对象的视频编码技术研究”,上海交通大学博士学位论文,2005。
[103] 曾昭平,“基于内容的视频检索研究”,上海交通大学博士学位论文,2002。
[104] 宋利,“图像鲁棒匹配及相关技术的应用研究”,上海交通大学博士学位论文,2005。
[105] Ying X.1; Uberbacher E.C. “2D Image Segmentation Using Minimum Spanning Trees”, Image and Vision Computing, Volume 15, Number 1, January 1997, pp. 47-57(11).
[106] Richard Cole, Philip N. Klein, Robert E. Tarjan, “A Linear-Work Parallel Algorithm for Finding Minimum Spanning Trees”, Annual ACM Symposium on Parallel Algorithms and Architectures, 1994.
[107] Wang Song, Siskind J M. “Image segmentation with ratio cut”, IEEE Trans Pattern Analysis and Machine Intelligence, 2003; 25 (6):675-690.
[108] C Ding, X F Ren, H Zha et al. “Spectral Min- max Cut for Graph Partitioning and Data Clustering”, Proc of the IEEE Intl Conf on Data Mining, 2001: 107~114.
[109] O Veksler. “Image Segmentation by Nested Cuts”. In: Proc IEEE CS Conf Computer Vision and Pattern Recognition, 2000: 339~344。