Method and device for image stacking for augmented reality

Abstract

The present invention discloses a method and device for image stacking for augmented reality. The method comprises: obtaining point cloud data of a preset scene; determining N planes in the point cloud data and N data point sets being in one-to-one correspondence with the N planes; determining the edge straight lines of the planes corresponding to each data point set; and when a virtual image is stacked on a first plane in the N planes, pasting the pasting surface of a main feature object in the virtual image with the first plane, and arranging the positive side of the main feature object to be in parallel with or perpendicular to the edge straight line of the first plane, wherein the positive side is an intersection line between the preset orientation surface and a preset bottom surface of the main feature object. In the process of stacking the virtual image to a real environment, the real edges of the planes in the real environment are combined to obviously improve the reality of the main feature object in the virtual image so as to reduce or avoid the possibility that users perceive that the main feature object is virtual and continuously provide immersion experience for users.

Description

technical field [0001] The invention relates to the field of augmented reality, in particular to an image superposition method and device for augmented reality. Background technique [0002] Augmented reality (English: Augmented Reality; abbreviation: AR) is one of the hot research topics in the field of machine vision in recent years. Computer image and video processing algorithms superimpose virtual image information or virtual objects displayed by video information into the same picture or space at the same time, and users can obtain a new sensory experience beyond reality. [0003] In order to provide users with an immersive experience, it is necessary to make the displayed virtual objects as close as possible to the user's real environment. In the existing technology, the point cloud data corresponding to the real environment is directly detected, and then the virtual objects are superimposed on the detected on the plane, but does not combine the actual edge of the cur...

AI Technical Summary

Problems solved by technology

[0003] In order to provide users with an immersive experience, it is necessary to make the displayed virtual objects as close as possible to the user's real environment. In the existing technology, the point cloud data corresponding to the real environment is directly detected, and then the virtual objects are superimposed on the detected on the plane, but does not combine the actual edge of the current real environment, so it may cause the following distortion: the position of superimposing the doll on the plane is chosen arbitrarily, resulting in the reduction of the reality of the doll, for example, to superimpose a virtual doll on the Take the wall in the real environment and the user standing on the ground as an example. In the prior art, after superimposing, the bottom of the doll is parallel to the ground and the face is facing the user. Although this can better show the doll to the user , but it will make the doll appear to be suspended in the air close to the wall, which can easily make the user perceive that the doll is a virtual doll, thus failing to provide users with an immersive experience

[0004] Therefore, in the prior art, there is a technical problem that the authenticity of virtual objects is reduced due to the fact that images are not combined with the actual edges of the real environment for image superposition.

Images