Loading...

Fuzzy motion interpolation for mesh-based motion estimation

Eslami, A ; Sharif University of Technology | 2007

248 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/CIISP.2007.369301
  3. Publisher: 2007
  4. Abstract:
  5. Mesh-based motion estimation is an important tool for video coding especially with low bit rate. In this paper, a new method for interpolating pixel motion from adjacent mesh nodes with the ability of omitting independent nodes is proposed. By exploiting fuzzy rules to determine the association of pixel and neighboring nodes, the proposed interpolation can detach pixels from some nodes. Consequently, it can deal with those critical patches on objects boundary which their nodes do not belong to one object. Updating the membership functions of each rule with specified strategy makes the interpolation adaptive with non-stationary conditions of image sequences and decreases sensitivity to initial selection of parameters. Experimental results show that the proposed method, in comparison with the conventional methods, increases the motion interpolation accuracy while does not accompanies with massive time cost and complexity. © 2007 IEEE
  6. Keywords:
  7. Computational complexity ; Fuzzy rules ; Image coding ; Interpolation ; Membership functions ; Pixels ; Bit rate ; Fuzzy motion interpolation ; Motion estimation
  8. Source: 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007, Honolulu, HI, 1 April 2007 through 5 April 2007 ; 2007 , Pages 101-106 ; 1424407079 (ISBN); 9781424407071 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/4221402