An interactive image processing method for video

Abstract

The invention provides an interactive image processing method used for a video. The method comprises the following steps of extracting key frames from a video sequence; overlaying frames between adjacent key frames one by one to form a key frame cluster used for interactive marking; distinguishing the images of the key frames into a foreground area, a background area and an unknown area; carrying out spectral clustering and alpha value estimation on the key frames to obtain the sectional drawing result of the key frames; and finally, transferring the sectional drawing result of the key frames to the whole video sequence to obtain a final sectional drawing result. Because the foreground points are interactively marked on each key frame cluster, spatiotemporal information contained in the video sequence is fully utilized, and the naturalness and the intuition of user interaction are guaranteed on the basis of the user interface of the key frame, thereby conforming to the observation habit of a human visual system. Marking on the key frame clusters replaces independently marking on the key frames, and therefore the method has strong robustness for the situation with the big foreground object local action.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an interactive image processing method based on image fuzzy connectivity. Background technique [0002] Digital matting technology is a technical process that accurately extracts foreground objects from images or video sequences with a small amount of user interaction. Digital matting is a key technology in the field of image processing such as photo editing or film and television production. It has received extensive attention and research since the beginning of computer image processing technology. [0003] In simple terms, the matting technology is to completely divide the image into the foreground area (F) and the background area (B), and what needs to be processed is the color vector C of the pixel p in the unknown area (C). p , the color vector C p By foreground pixel F p , background area pixel B p and the transparency parameter α p Linear composition: [0004] C p =...

AI Technical Summary

Problems solved by technology

But on the other hand, the matting of video sequences is more challenging than that of a single image: the large amount of data in video sequences, the smoothness of edge processing of each frame of images, and the adaptability to large-scale movements of objects, etc. Influencing factors do not need to be considered in the matting technology of a single image

The current video matting algorithms include Bayesian video matting system, Rotoscoping-based video matting system, Graphcut-based video clipping system, Snapcut, etc., but in these algorithms, or due to large errors in motion estimation itself, the matting The results are unsatisfactory, or the robustness to foreground object motion is not strong, or the calculation amount of the algorithm used is too large to meet the requirements of the large-scale data flow of the video sequence, or the information that needs to be input by the user is too complicated and not intuitive, the system needs Operated by trained professionals, not practical

Images