Method and system for automatically converting 2D to 3D

Abstract

The invention discloses a method and system for automatically converting 2D to 3D. The method comprises the steps of evaluating the total depth value, and determining the total depth value and the display position; segmenting an image to be converted into a specific number of independent image segmentation planes according to a grayscale threshold segmentation method; automatically creating a depth map for each independent image segmentation plane, automatically tracking image frames of a video object and the background when conversion is performed on a video, and associating the depth maps; generating a 3D stereoscopic image or video through iteration rendering; and performing adjustment on parameters of the generated 3D stereoscopic image by using an adjustment device so as to enable the3D stereoscopic image to reach a desired effect. The system comprises devices (A, B, C, D, E, F) corresponding to the steps of the method and an adjustment device. The implementation of the inventionsimplifies depth level and dynamic change steps, can obtain a good 3D stereoscopic effect and realizes automatic conversion of the 3D stereoscopic image or video.

Description

technical field [0001] The invention relates to the technical field of 3D image conversion, in particular to a method and system for automatically converting a 2D image into a 3D image by using a depth map. Background technique [0002] In 3D computer graphics, a depth image refers to an image or an image channel in which the information contained in the image is related to the distance from the surface of the scene object from the perspective of observation. Assuming that the change direction of the image depth value, that is, the shooting direction of the camera is the same as the Z direction of the field of view of the 3D scene to be described, then the entire 3D scene can be easily described, so the depth image is also called a distance image. Compared with color images, depth images can directly reflect the three-dimensional features of the object surface and are not affected by factors such as illumination, shadow, and chromaticity. Depth images can replace binocular ...

AI Technical Summary

Problems solved by technology

[0006] In view of the existing 2D to 3D technology, the accuracy of the depth map is not high, and a lot of depth information is missing, resulting in a "flat image" in the converted 3D image, and the problem of low automation and high human cost during conversion. , by extracting the depth information of the 2D image or video to be converted, according to the gray threshold segmentation method, the image to be converted is automatically segmented into individual image segmentation planes according to a certain threshold and segmentation accuracy, and for each discrete image segmentation Automatically create a depth map, automatically track the image frames in the video and associate the depth map, and finally obtain a stereoscopic image or 3D video after iterative rendering. During the whole process, the original 2D image is automatically segmented with high precision and the depth map is automatically assigned. , simplifies the depth level and dynamic change steps, you can get a better 3D stereoscopic effect, and realize the automatic conversion of 3D images or videos

Images