Video object segmentation method based on time domain fixed-interval memory compensation

Abstract

The invention discloses a video object segmentation method based on time domain fixed-interval memory compensation, which comprises the steps of: firstly, detecting an initial motion change domain by using a symmetrical frame frame-difference accumulation method and a four-order moment of a frame-difference image; secondly, compensating the detected initial motion change domain by using a time domain fixed interval memory compensation, and further integrating to form a global motion memory mother board; in a spatial domain, more accurately detecting by using a Sobel edge detection operator to obtain all edges in a current frame; thirdly, carrying out the temporal-spatial fusion, thereby extracting a complete and fine motion object outline; and finally, filling to obtain a video motion object template. The invention relates to a novel parallel spatial fusion automatic segmentation method which effectively solves the problems that serious loss inside a video object usually occurs in the spatial fusion and blocking (covering / exposing) can not be avoided when the motion domain is detected by using frame difference, and greatly improves the accuracy, the universality and the speed.

Description

technical field [0001] The invention relates to a processing method in video object extraction, in particular to a video object segmentation method based on time-domain fixed-interval memory compensation. Background technique [0002] The second-generation video coding standard represented by MPEG-4, its object-based coding and interactive functions make Semantic Video Object Segmentation (VOP), a challenging problem, gradually become a research hotspot in the field of video processing. As a key link in video processing and video analysis, video object segmentation technology is not only widely used in the fields of pattern recognition and computer vision, but also more and more important in emerging fields such as video retrieval, video coding, and multimedia interaction. [0003] At present, there are many video segmentation methods. According to whether manual participation in the segmentation process is required, it can be divided into automatic segmentation (see Huang ...

AI Technical Summary

Problems solved by technology

[0005] Obtain the changing area of ​​the moving object directly through the difference between frames. The method is simple but sensitive to noise and ambient light changes. Usually, the complete moving area cannot be obtained. In addition, if the frame difference is not selected properly, the occlusion area will also be enlarged.

Moreover, when the internal texture similarity of the video object is high, part of the motion temporarily stops or the motion range is small, the detected change area will be full of holes.

These will reduce the accuracy and completeness of the final video object extraction

Images