Slide 1Slide 2Slide 3Slide 4Slide 5Slide 6Slide 7Slide 8Slide 9Implementation on video object segmentation algorithm Kuo, Yi-Ting and Wu, Chia-PengMay 03. 2004OutlinesIntroductionAlgorithmArchitecture of hardware implementationSystolic array for texture feature extractionIntroductionOur project is focused on extracting moving objects from video.The algorithm of moving object segmentation can be applied to MPEG-4 standard which enable content-based functionality.Also can be used in traffic surveillance system.AlgorithmChange detectionPrevious frame In-1 CurrentFrame In Find moving object edgeSmooth edge Moving object-Mean and Variance Features1 ( , )1( , ) ( , )t k l W yWf m n f m k n lN�= - -��22 ( , ) 11( , ) ( ( , ) ( , ))t k l W y tWf m n f m k n l f m nN�= - - -��The two features (mean and variance),ft1(m,n) and ,ft2(m,n) are textural appearance of the area surrounding a pixel (m,n) in asmall window centered on this pixel, Nw is the number of pixelof Ws * Ws of window W .Systolic array for texture feature extractionSystolic array for extracting the two texture features ft1, ft2Systolic array for extracting the two texture features using 5x5 windowThe luminance component of a reference frame fy(m,n) are scanned Into 1+4Nc size FIFO. Nc = number of columns of reference frameBlock A: accumulates luminance components.Block M: generate a mean value by dividing the accumulated result by NwBlock V: calculate localvariance texture feature.DEMOReferences[1] Changick Kim and Jenq-Neng Hwang, “Fast and automatic video object segmentation and tracking for content-based application,” IEEE Trans. Circuits and Systems for Video Technology, vol. 12, No. 2, Feb. 2002, pp. 122-129.[2] J. F. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, pp. 679-698, Nov. 1996.[3] Jinsang Kim and Tom Chen, “Real-time video objects segmentation using a highly pipelined microarchitecture,” Proceedings of the IASTED International Conference, Visualization, Imaging, and Image Processing, Sep. 3-5, 2001, Marbella, Spain, pp. 483-488[4] Rafael C. Gonzalez and Richard E. Woods, Digital Image
View Full Document