An automatic hollowing out method for augmented reality logo

Abstract

Identifiers are camera calibration aiding tools widely used in reinforced reality, while the presence of identifiers in reinforced reality images affects the realistic sense and beauty of virtual-real fusion. The invention provides an automatic hollowing method of a reinforced reality identifier. According to the method, important areas such as edges and corner points are reserved, areas useless to camera calibration are removed, and therefore, area required to be repaired after an identifier is removed can be decreased, and the visual effect of identifier hiding can be improved. The hollowing method includes the following steps that: 4-neighborhood color comparison is adopted to obtain the edge features of a traditional identifier image; morphological expansion operation is performed on the pixels of an edge feature image, so that an expanded edge image can be obtained; connecting bands are added onto a vertical axis, so that the overall communication of the reserved areas can be ensured, so that a communicated reserved image can be obtained; all right-angled boundaries are converted to smooth rounded edges, so that a hollowed area mask can be obtained; and pixels in the traditional identifier image which are corresponding to hollowed areas are set to be red, so that a final hollowed identifier can be obtained.

Description

technical field [0001] The invention relates to an automatic hollowing-out method for an augmented reality mark, in particular to an automatic hollowing-out processing method based on an augmented reality template-like mark. Background technique [0002] Augmented reality is a technology that enhances the observer's visual perception of the real world through the virtual information provided by the computer system. It uses related computer technology to superimpose the virtual scene into the video screen of the real environment in real time with the help of signs or feature points. In order to ensure the spatial consistency between the superimposed virtual scene and the real environment, it is necessary to use the camera calibration method to calculate the internal and external parameters of the camera in real time. [0003] Considering the production cost, ease of use and stability, the logo has become the most important and general camera calibration aid. The user only ne...

AI Technical Summary

Problems solved by technology

However, in order to ensure the accuracy of camera calibration, the imaging area of ​​the template type and coding type logo in the video screen is usually large, and the large-area image restoration required after removal not only consumes a huge amount of calculation, but also often leads to hidden results of the logo Distortions such as repair marks and gaps appear

Images