Method for realizing three-dimensional augmented reality

Abstract

The invention discloses a method for realizing a three-dimensional augmented reality. The bottleneck that the number of bi-dimensional read pictures of the conventional augmented reality is broken; graphical picture pixels and color information of a marker are respectively read twice, so that a mapping relation between a virtual object and a real object is quickly and accurately constructed; patterns on the marker are attractive; and under any lighting condition, the information of the marker can be normally read. The method comprises the following steps of: initializing multimedia equipment and a photography device, and connecting the multimedia equipment and the photography device with a relevant three-dimensional model; acquiring a video frame of the marker through the photography device, wherein the marker is a picture or a card, and the patterns on the marker are fully colored; reading the video frame, and retrieving a corresponding virtual three-dimensional model in a three-dimensional database; positioning the virtual three-dimensional model and a coordinate axis of the video frame; and calling the retrieved virtual three-dimensional model, synthesizing the virtual three-dimensional model and the video frame, and outputting the video frame to a display for displaying.

Description

technical field [0001] The invention relates to the technical field of three-dimensional modeling and augmented reality, in particular to a method for realizing three-dimensional augmented reality. Background technique [0002] Augmented reality technology is a technology that integrates computer science such as image recognition and tracking, motion capture, and virtual reality. It superimposes and displays digital information such as virtual 3D model animations, videos, texts, and pictures in real time on real scenes, and integrates them with real objects. Or the innovative human-computer interaction technology for users to achieve natural interaction, which is widely used in various fields. For example, the user holds a color card, reads it through the camera, and the display shows a three-dimensional image corresponding to the pattern on the card and The virtual and real combination of color pictures is presented. [0003] In the prior art, the pattern on the two-dimens...

AI Technical Summary

Problems solved by technology

[0007] Augmented reality technology realizes the most basic image recognition based on simple pixel graphics reading of QR codes. Although this method is fast in recognition, when the number of pictures to be read is large (generally about 200), such as game cards, Reading such a large amount of graphics will lead to confusion in reading images, slow response and errors. The reasons for the errors are:

[0008] The two-dimensional code is a dot matrix image information in units of pixels. The array mode is relatively single, and the two-dimensional code is distinguished by a combination of multiple digits, which has higher requirements for the recognition ability of the recognition device. In addition, due to the limitation of the size of the card itself (8.3x6.3cm), the size of the QR code should not be too large, so it will cause confusion or cannot be read in the case of long-distance recognition by the camera. At this time, the QR code is not suitable Development and application of augmented reality;

[0009] In addition, the traditional two-dimensional code adopts black and white recognition. Although the color value contrast is the largest (white R: 255B: 255G: 255 black R: 0G: 0B: 0), the recognition speed is fast under normal circumstances, but the printing paper and The environmental requirements are relatively high. If the color value is changed under the influence of strong light first (the change of black under high light), it will cause problems that cannot be recognized

Images