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

Disparity map quality evaluation method

A technology of quality assessment and disparity map, applied in the fields of binocular vision and computer vision, which can solve problems such as quality prediction errors

Pending Publication Date: 2019-12-24
南京美基森信息技术有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There will be a large error in the process of fusing monocular images. Due to the problem of accurate pre-evaluation, there is a certain degree of error in the final quality prediction

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
  • Disparity map quality evaluation method
  • Disparity map quality evaluation method
  • Disparity map quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0007] specific implementation

[0008] In order to solve the above-mentioned main difficulties, the self-judgment of the depth image is firstly carried out by using the no-reference method, and the corresponding depth of each pixel is obtained according to the results of binocular matching and cost aggregation. , you can judge by yourself according to the following formula

[0009]

[0010] where i is , D is the parallax range, and Respectively in the pixel point p The minimum and maximum value of the cost value, T is the maximum and minimum value threshold. When an object approaches or an occluder appears, Costs with values ​​in all disparity ranges will have very small mutations, and their minimum values ​​will be much smaller than other disparity ranges, at which point their disparity will become very unreliable. When there is no obvious texture or white area in the grayscale image, when the cost value in all parallax ranges fluctuates up and down, and T...

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 binocular stereo matching disparity map quality evaluation method which can be used in the field of computer stereo matching. The method is mainly used for a camera to receive light, and when an object is close to a binocular, a traditional parallax result has many errors, and the parallax result is not reliable. By combining partial reference and no-reference methods, afeedback system is established for the depth map and the grey-scale map, and a feature geometry in the grey-scale map is used for judging a depth map error area to serve as a basis for judging the quality of the depth map.

Description

technical field [0001] The invention relates to a method for evaluating the quality of binocular stereo matching disparity maps, which belongs to the field of computer vision, especially the field of binocular vision. Background technique [0002] Image quality assessment (Image Quality Assessment, IQA) has always been the main hot research field of research. In the entire image quality assessment system, it is generally divided into objective image assessment and subjective image assessment. Subjective assessment needs to be judged by people or other third-party tools , which is relatively dependent on tools and has high cost. There are mainly Mean Subjective Score (MOS) and Difference Subjective Score (DMOS). Subjective evaluation requires the organization of corresponding manpower to judge the image quality, and the results are easily influenced by personal subjective factors. As the number of images increases geometrically, this method is extremely time-consuming, which ...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/10028G06T2207/30168G06T7/593
Inventor 霍志坤丁鹏飞李行蒋桐古峥
Owner 南京美基森信息技术有限公司