Depth map assisted active contour image matting method and system

Abstract

The invention discloses a depth map assisted active contour image matting method and system, and the method comprises the following steps: obtaining a depth map of a color target image, carrying out the processing of the depth map through employing a repair algorithm, and obtaining a repaired depth map; carrying out confidence calculation on the repaired depth map and the target image to obtain adepth confidence map and a color confidence map; carrying out level set segmentation by utilizing the depth confidence map and the color confidence map, obtaining a final target contour, and obtaininga required tripartite graph; and respectively obtaining a matting result of the color image and a matting result obtained by the depth image, setting a color difference degree to measure a distance value between the foreground and the background, when the distance value is smaller than a given threshold T, adopting the color matting result, and otherwise, adopting the depth matting result. The method can better solve the problem of background similarity before and after the image, and is closer to the boundary of the to-be-segmented object in the segmentation process, so that the geometric topology of the object is better maintained, and the required binary segmentation result is obtained.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional reconstruction, and relates to performing foreground estimation on a target object to realize the separation (matching) of background information before and after, in particular to a depth map-assisted active contour matting method and system. Background technique [0002] 2017 is called the first year of artificial intelligence, thanks to the rapid development of computing power. At the same time, the constantly updated and iterative computing power has promoted the development of computer vision, and 3D reconstruction technology has received unprecedented attention. In 3D reconstruction, the object of concern is not only the objects in real life, but also the use of virtual models to represent real objects in life. [0003] So, how to realize the use of virtual models to describe real objects? At present, there are mainly two methods that are popular in the industry: the first is to ...

AI Technical Summary

Problems solved by technology

But only using trimaps and traditional color images can not solve the problems in the following two scenarios: one is when the foreground and background are similar; the other is that trimaps are not as accurate as expected

[0012] However, at present, when the depth image is used to assist image segmentation or matting, most of the relatively complete depth images are used.

In practice, in the process of acquiring depth images, due to the limitation of the equipment itself and the interference of external environmental factors, there are many problems in the acquired depth images, mainly including image holes caused by lack of depth information, and the accuracy of depth values ​​is not high. And the image noise problem, which leads to the poor effect of the current segmentation method using the depth image

Images