Browse > Article

VLSI Architecture for Video Object Boundary Enhancement  

Kim, Jinsang- (경희대학교 전자공학과)
Publication Information
The Journal of Korean Institute of Communications and Information Sciences / v.30, no.11A, 2005 , pp. 1098-1103 More about this Journal
Abstract
The edge and contour information are very much appreciated by the human visual systems and are responsible for our perceptions and recognitions. Therefore, if edge information is integrated during extracting video objects, we can generate boundaries of oects closer to human visual systems for multimedia applications such as interaction between video objects, object-based coding, and representation. Most of object extraction methods are difficult to implement real-time systems due to their iterative and complex arithmetic operations. In this paper, we propose a VLSI architecture integrating edge information to extract video objects for precisely located object boundaries. The proposed architecture can be easily implemented into hardware due to simple arithmetic operations. Also, it can be applied to real-time object extraction for object-oriented multimedia applications.
Keywords
edge fusion; video object; segmentation; systolic architecture; VLSI;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Amjad and T. Chen, 'A VLSI Architecture for Real-Time Edge Linking,' IEEE Trans. PAMI, Vol. 21, no.1, pp. 89-94, 1999   DOI   ScienceOn
2 T. Kohonen, 'Self-organized formation of topologically correct feature maps,' Biological Cybernetics, vol. 4, pp.59-69, Jul. 1982
3 Y. J. Zhang, 'A Survey on Evaluation Methods for Image Segmentation,' Pattern Recognition, vol. 29, no.8, pp. 1335-1346, 1996   DOI   ScienceOn
4 Jinsang Kim and T. Chen, 'Low-Complexity Fusion of Intensity, Motion, Texture and Edge for Image Sequence Segmentation: A Neural Network Approach,' IEEE International Workshop on Neural Networks for Signal Processing, Sydney, Australia, pp.497-506, Dec. 2000
5 A.A.Alatan and et al. 'Image Sequence Analysis for Emerging Interactive Multimdia Services-The European C0ST211 framework' IEEE Trans. CSVT, vol 8. 802-813, Nov. 1998
6 C. D. Thompson, 'The VLSI Complexity of Sorting,' IEEE Trans. on Computers, vol 32, pp. 1171-1184, 1983   DOI   ScienceOn
7 Xue Dong Yang, 'Design of Fast Connected Components Hardware,' IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 937-944, 1996
8 Roberto Castagno and et al., 'Video Segmentation Based on Multiple Features for Interactive Multimedia Applications,' IEEE Trans. CSVT, vol 8, no. 5, pp. 562-571, Sep. 1998