.png){kind=icon}
Return
Motion vector correction based on the pattern-like image analysis
.png){kind=icon}
PRE
AI
DOI：10.1109/TCE.2003.1233758.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we propose a motion vector correction algorithm to correct the erroneous motion vectors due to the failure of conventional motion estimation (ME) based on block matching algorithm (BM,4). The proposed method is based on the pattern-like image analysis that consists of the periodic pattern detection and calculation of motion parameters for the motion vector correction. In addition, the proposed method corrects effectively the erroneous motion vectors using the relations between the periodic pattern and local/global minima depending on whether the periodic pattern is static or moving. Also, it does not significantly increase computational complexity since it uses the estimated motion vectors and the integral projection of the sum of absolute difference (SAD) previously obtained from the conventional ME. Experimental results indicate good performance of the proposed scheme with significant reduction the erroneous motion vectors.
Keywords:
block matching algorithm
motion estimation
motion vector correction
pattern-like image analysis
Journal
IF:
10.9
Papers:
5.3K
Citations:
6.8K
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSaveShareSaveShareSave
View more