Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for performing hole filling on destination image generated by depth-image-based rendering (DIBR) technology

A target image and hollow technology, applied in the direction of image communication, stereo system, electrical components, etc., can solve the problems of complex hardware implementation and achieve the effect of easy realization

Inactive Publication Date: 2013-06-05
SICHUAN PANOVASIC TECH +1
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the hardware implementation of this method is more complex

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for performing hole filling on destination image generated by depth-image-based rendering (DIBR) technology
  • Method for performing hole filling on destination image generated by depth-image-based rendering (DIBR) technology
  • Method for performing hole filling on destination image generated by depth-image-based rendering (DIBR) technology

Examples

Experimental program
Comparison scheme
Effect test

example

[0060] In this example, the "ballet" sequence test pattern and its accompanying calibration parameters are used for experiments, and the image resolution is 1024×768. The 0th frame captured by the camera 4 is used as the left view, that is, the reference image to synthesize the right view target image. Frame 0 captured by camera 4 I 4 like Figure 4 shown.

[0061] In this example, the baseline length is 0.65 (measured in the length unit in the camera space of the "ballet" sequence test pattern), the internal parameter matrix and rotation transformation matrix of the virtual camera are the same as those of camera 4, and the translation transformation matrix differs by 0.65 in the horizontal direction , the right view can be obtained from the reference image and the corresponding depth image through three-dimensional image transformation, that is, the target image I 1,like Figure 5 shown. from Figure 5 We can see that in the target image I 1 A large void is created on ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for performing hole filling on a destination image generated by a depth-image-based rendering (DIBR) technology. The method comprises the following steps of: traversing a parallax image in rows, and detecting relatively larger holes; distinguishing foreground pixels and background pixels of marginal areas of the holes by utilizing depth values, determining area with matching errors, and expanding the relatively larger holes to remove pixels with the matching errors on the edges of the relatively larger holes; and copying hole areas to be filled in a corresponding destination image, namely the hole areas to be filled from the background pixels to the destination image from a reference image to finish the hole filling. By the method, a depth image is not required to be preprocessed, the realness of relatively larger hole areas is maximally ensured, and a high-quality destination image is obtained. In addition, complex arithmetic operations are avoided, and convenience is brought to hardware implementation. Simultaneously, a foreground and a background are distinguished by utilizing the depth values, and the areas with the matching errors are determined and eliminated / reduced by expanding the edges of the holes to correct the matching errors.

Description

technical field [0001] The invention belongs to the technical field of Depth-Image-Based Rendering (DIBR for short) in a 3D television system, and more specifically relates to a method for filling holes in a target image generated by DIBR technology. Background technique [0002] The depth-based image rendering technology is to generate a new virtual viewpoint image (destination image) based on a reference image (reference image) and its corresponding depth image (depth image). Compared with the traditional 3D video format that uses two channels of plane video to synthesize 3D images, after adopting DIBR technology, only one channel of video and its depth image sequence are needed to synthesize 3D images, and the switching between 2D and 3D can be realized conveniently. , while avoiding the computational complexity of 3D space transformation brought by traditional view generation methods. Because of this, DIBR technology has been widely used in 3D TV synthesis of 3D images,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N13/00
Inventor 刘然田逢春刘阳鲁国宁黄扬帆甘平谢辉邰国钦谭迎春郭瑞丽罗雯怡许小艳
Owner SICHUAN PANOVASIC TECH