K.U.Leuven > ESAT > PSI > Visics > Research > Topics > Item 4.2

Image compression using motion based segmentation

L. Van Eycken, S. Desmet, B. Deknuydt

Object based coding is a technique that is being investigated to achieve high compression ratios for video sequences. The classical approach to video coding is a four-step algorithm: segmentation, motion estimation and compensation, coding of the segmentation information and finally coding of the prediction errors. In order to reduce the number of bits needed for coding the objects, we propose another approach where we try to combine the first three steps: do the motion estimation and segmentation together and at the same time collect important information for the coding of the segmentation information. With this scheme a "fuzzy" segmentation is obtained, i.e. for every pixel we have a probability to belong to a certain object. Only at coding time the real boundaries between objects are defined by minimizing the global cost of both segmentation information and prediction errors.