Motion parameters estimation and error criteria in model based coding
Yun Liu · Journal of China Institute of Communications · 2000
Model based facial image coding has got extensive attention due to its high subject image quality and low bit rates.But the estimation of object motion parameters is still a difficult problem,and there are no proper error criteria for the quality assessment satisfied with visual properties.This paper presents a motion parameters estimation algorithm based on feature points.The feature points are automatically extracted from edge,brightness and end node points,and the numbers of feature point are adjusted adaptively.A method of estimation of motion parameter error based on the quality of reconstructed image is suggested.That area error and contour transition turn error is used to be quality criteria.The two functions reflect the image geometric distortion caused by motion parameter error properly.