Virtual view generating method based on shielding region detection

Abstract

The invention provides a virtual view generating method based on shielding region detection. The virtual view generating method comprises the following steps of performing edge detection on a left view and a right view of a left reference viewpoint and a right reference viewpoint and extracting edge information; respectively dividing pixel sections of the left view and the right view according to the edge information and performing matching on the pixel sections; checking matching results of the pixel sections so as to perform secondary matching according to the shielding situation and detecting shielding regions of the left view and the right view; generating a virtual view according to the matching result of the pixel sections and detection results of the shielding regions. The virtual view generating method can fully utilize information of two reference viewpoints and avoid large-area void rendering. In addition, calculation redundancy can be further decreased and the calculation efficiency can be improved by adopting the method. Furthermore, virtual view rendering is achieved based on a shielding region and non-shielding region local change method without pixel calculation according to parallax values, and accordingly the drawing speed can be improved.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a virtual view generation method based on occlusion region detection. Background technique [0002] Currently, television has developed from analog television, digital television, and high-definition television to stereoscopic television (3DTV) and free viewpoint television (FTV). Stereoscopic display technology has a good application prospect. However, the lack of sources of 3D films and the difficulty of obtaining them are bottlenecks restricting the development of the 3D industry. [0003] There are mainly two types of current stereoscopic displays: displays based on binocular stereoscopic imaging and naked-eye multi-viewpoint stereoscopic displays. Multi-view glasses-free display technology can be divided into three types: projection type, stereoscopic type and parallax type, among which parallax type is the most common. The parallax-type naked-eye stereos...

AI Technical Summary

Problems solved by technology

[0008] Since the occluded area has no matching area in the target view, in the disparity map based on the reference view and the target view, this part of the area has no depth value, resulting in a lack of corresponding information in the virtual view, which appears as a rendering hole

At present, hole filling is usually used as a post-processing operation, or a certain background filling is used, or only information from a certain perspective is used, and information from two perspectives is not fully utilized.

At the same time, methods based on depth estimation have a lot of computational redundancy

Depth estimation takes up most of the calculation time, but the obtained disparity information is not completely necessary, and the depths of adjacent pixels belonging to the same scene level are basically the same, and the algorithm efficiency is not high

Images