A multi-view depth video preprocessing method

Abstract

The invention discloses a preprocessing method of a multi-view deep video. The preprocessing method of the multi-view deep video divides a deep video frames into a continuous region and discontinuous regions, then divides the continuous region into a foreground region and a background region, and then extracts the edge portions of all the regions to protect, carries out Gaussian filter processing to non-edge portions of the discontinuous regions, respectively carries out self-adaptive window filtering processing to the non-edge portions of the foreground region and the background region of the continuous region, enables all the pixel points inside a self-adaptive window to belong to a same region or an identical type, reduces errors as far as possible, and greatly improves compressed encoding efficiency of a deep video sequence, and saved code flow is up to 8.33% to 34.39%, and meanwhile a peak signal to noise ratio of drawn dummy viewpoints is averagely improved by 0.21 dB.

Description

technical field [0001] The invention relates to a video signal processing method, in particular to a multi-viewpoint depth video preprocessing method. Background technique [0002] Free Viewpoint Video (FVV, FreeViewpointVideo) can provide information on a certain scene or object at any angle and orientation, allowing the audience to experience a more realistic three-dimensional sense. The application prospect is the development direction of the new generation multimedia video system. In the free-viewpoint video system based on multi-viewpoint color video plus depth video (MVD, Multi-viewplusDepth), the multi-viewpoint video signal is mainly composed of multi-viewpoint color video sequence signal and multi-viewpoint depth video sequence corresponding to the multi-viewpoint color video sequence signal Signal composition, but the MVD data volume is more than ten times or even dozens of times that of ordinary single-channel video. The depth video sequence reflects the distanc...

AI Technical Summary

Problems solved by technology

[0003] There are two main ways to acquire depth video. The first method is to use the depth camera based on the time-of-flight principle to directly acquire it. However, building a multi-view depth video acquisition system is expensive and the acquisition distance is limited. These factors greatly restrict The popularity of depth cameras; the second method is to use the captured multi-viewpoint color video to obtain depth video through depth estimation software (DERS, DepthEstimationReferenceSoftware), which is more and more widely used

However, the depth video obtained by the depth camera or by the depth estimation software is not very accurate, which greatly reduces the temporal and spatial correlation of the depth video, thereby affecting its compression efficiency, and the sudden change of the depth value is easy to cause holes in the virtual viewpoint drawing , affecting the drawing quality

Images