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

Image processing device, image processing method, program, integrated circuit

An image processing device and image data technology, applied in the field of image processing, can solve problems such as unnatural images of stereoscopic images, and achieve the effect of preventing blur and deformation

Inactive Publication Date: 2016-02-10
SOVEREIGN PEAK VENTURES LLC
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] However, in the above-mentioned prior art, there are cases where the stereoscopic image after DIBR processing becomes an unnatural image.

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
  • Image processing device, image processing method, program, integrated circuit
  • Image processing device, image processing method, program, integrated circuit
  • Image processing device, image processing method, program, integrated circuit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0085] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0086] [summary]

[0087] The image processing device according to Embodiment 1 shifts the coordinates of each pixel constituting the image data in a predetermined direction based on the depth image, and generates image data having a different starting point from the original image data. , the edge position of the depth image is shifted to the background side, pixel shift processing is performed using the depth image after the edge position has been shifted, and then the missing region where the pixel value generated by the pixel shift does not exist is interpolated. When performing pixel shift processing, the edge position of the depth image is moved to the background side, so the pixels at both ends of the pixel missing area become the pixels of the background object, and the foreground object formed due to the interpolation of the pixel missing area can be prevented....

Embodiment approach 2

[0132] Like the image processing device 100 of Embodiment 1, the image processing device according to Embodiment 2 moves the edge position of the depth image toward the background side, performs pixel shift processing using the depth image after the edge position has been shifted, and then performs pixel shift processing on the depth image obtained by the pixel shift. However, the difference from the image processing device 100 of Embodiment 1 is that the complexity of pixels on the background side is calculated when performing edge position shift processing, and the background Edge movement processing is performed on the condition that the complexity of pixels on the side is equal to or less than a predetermined threshold. Since the edge movement processing is only performed when the background objects are not complicated and the pixel changes are relatively monotonous, it is possible to prevent complex background objects from being stretched and causing deterioration of the o...

Embodiment approach 3

[0146] Like the image processing device 100 of Embodiment 1, the image processing device according to Embodiment 3 moves the edge position of the depth image toward the background side, performs pixel shift processing using the depth image after the edge position has been shifted, and then performs pixel shift processing on the depth image obtained by the pixel shift. However, when performing edge position shift processing, the complexity of pixels on the foreground side and the complexity of pixels on the background side are calculated, and the calculated pixels on the foreground side are The complexity is compared with the complexity of pixels on the background side. In addition, the edge shift processing is performed on the condition that the complexity of pixels on the foreground side is higher than the complexity of pixels on the background side. Since the edge position is shifted toward the background only when the foreground object is more complex than the background ob...

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

An image processing device in which a depth image conversion unit (101) shifts an edge position of an input depth image toward a background side. A pixel shifting unit (102) generates an image of another viewpoint by horizontally shifting the coordinates of each pixel constituting the image data based on the converted depth image. A pixel interpolation unit (103) interpolates a pixel-missing region generated by pixel shifting.

Description

technical field [0001] The present invention relates to image processing technology, in particular to generation technology of stereoscopic vision image. Background technique [0002] Such a DIBR (Depth-image-based Rendering: rendering based on a depth image) technique is known (see Non-Patent Document 1). By shifting the coordinates of each pixel constituting the image data in the horizontal direction, the original image data is generated. images from different viewpoints, and generate a stereoscopic image composed of images from multiple viewpoints. [0003] In the DIBR technique, the amount of displacement in the horizontal direction is determined from a depth image representing the position in the depth direction of each object captured in image data. At this time, the displacement of the object in the front (foreground object) and the object in the back (background object) are different, so in the pixel-shifted image, the boundary between the foreground object and the ...

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): H04N13/04G06T19/00
CPCG06T15/205H04N13/111H04N13/128G06T15/08
Inventor 前田昌树大谷尚毅野村和博
Owner SOVEREIGN PEAK VENTURES LLC