Cross-validation depth map quality evaluation method combined with jnd model

A quality evaluation and cross-validation technology, applied in image communication, television, electrical components, etc., can solve problems such as large performance impact and neglect, and achieve consistent objective results.

A quality evaluation and cross-validation technology, applied in image communication, television, electrical components, etc., can solve problems such as large performance impact and neglect, and achieve consistent objective results.

CN106803952BActive Publication Date: 2018-09-14NINGBO UNIV
9 Cites 0 Cited by

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cross-validation depth map quality evaluation method combined with jnd model
  • Cross-validation depth map quality evaluation method combined with jnd model
  • Cross-validation depth map quality evaluation method combined with jnd model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0042] A cross-validation depth map quality evaluation method combined with JND model proposed by the present invention, its overall realization block diagram is as follows figure 1 As shown, it includes the following steps:

[0043] ① Mark the depth map to be evaluated as D tar , the D tar The corresponding color map is marked as Τ tar , will divide D tar and T tar Another known viewpoint outside the viewpoint is defined as an auxiliary viewpoint, and the color map on the auxiliary viewpoint is marked as T ref ; then pass the D tar The pixel values ​​of all pixels in are transformed into disparity values, and Τ tar All pixels in are mapped to T by 3D-Warping ref in; among them, D tar , T tar and T ref The total number of pixels in the vertical direction is M, D tar , T tar and T ref The total number of pixels in the horizontal d...

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 cross validation depth map quality evaluation method combined with a JND model. According to the method, a color map corresponding to a depth map and a color map on an auxiliary viewpoint are utilized to obtain a difference image; the number of pixels at each coordinate in the color map on the auxiliary viewpoint to which the depth map and the color map corresponding to the depth map are mapped is utilized to obtain a shielding mask; then the shielding mask is utilized to remove pixel points shielded in the difference image to obtain a difference image after deshielding; then the color map on the auxiliary viewpoint is divided into a flat region, an edge region and a texture region to obtain a region marking map; a JND model is introduced, combined with the region marking map, an error visual threshold of each pixel point in the color map on the auxiliary viewpoint is obtained; and finally, according to the deshielded difference image and the error visual threshold, a depth error map is obtained, and the rate of error pixel points in the depth map is further obtained as a quality evaluation value. The advantage is that the method can effectively improve consistency of an evaluation result and the quality of virtual viewpoints obtained by drawing.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a cross-validation depth map quality evaluation method combined with a JND (Just-noticeable-distortion, just noticeable distortion) model. Background technique [0002] In recent years, video technology has developed rapidly, and many new applications have emerged, such as 3D video and Free Viewpoint Video (FVV, Free Viewpoint Video). Compared with traditional two-dimensional video, 3D video provides depth information, resulting in a more realistic visual experience. Depth maps play a fundamental role in many 3D video applications, for example, depth maps can be used to generate arbitrary new viewpoint images by interpolating or extrapolating images at available viewpoints; moreover, a high-quality depth map is an important tool for solving problems in computer vision. provided assistance with challenging problems. The performance of many 3D video applications benefits from...

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
14 Sep 2018
Publication
CN106803952B
IPC
H04N17/00; H04N13/106
CPC
H04N13/106; H04N17/00; H04N2013/0074
Inventors
陈芬; 陈嘉丽