H.264 compression domain real time video object division method based on motion feature

Abstract

The invention relates to an H.264 compressed domain realtime video object segmentation method based on motion feature. The method comprises the following steps: after spatial domain normalization of a motion vector field is completed, weighting median filtering of the normalized motion vector field is carried out; then, based on the three motion features of the motion vector field including amplitude, divergence and circuitation, the motion vector field is divided into a plurality of objects according to motion feature similarity through adopting an improved statistical region growing method. The experimental result of an MPEG-4 testing sequence shows that: when a CIF format video sequence is processed in a computer with a 2.0GHz dual-core CPU and 900M memory, the average processing time of each frame is 15 ms which meets the requirements of most real-time application at 30fps; moreover, excellent segmentation quality is obtained. Because the method only makes use of motion vector field information, the method can also be used in the motion object segmentation of an optic flow field.

Description

technical field [0001] The invention relates to a real-time video object segmentation method based on the H.264 compressed domain. Compressed domain segmentation can avoid complete decoding of compressed video, and only motion vectors extracted through entropy decoding are used as motion features required for segmentation. In addition, quite different from the existing methods, this method uses three motion features based on the motion vector field's magnitude, divergence and curl, combined with the improved statistical region growing method to segment different objects in the video sequence, comparable to The calculation amount of the existing video object segmentation method based on the H.264 compressed domain is further reduced. Since this method only uses motion vector field information, it is also applicable to moving object segmentation based on optical flow field. Background technique [0002] Previous studies on video object segmentation mostly focus on the pixel d...

AI Technical Summary

Problems solved by technology

However, in this method, there are two problems that have not been well resolved

One is that the effective filtering method cannot be used to filter out the singular motion vectors while retaining the main details of the motion vector field; the other is that the characteristics of the motion vector field cannot be fully utilized to segment video moving objects

Images