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

Method, device and terminal for judging disparity map

A disparity map and parallax technology, applied in the field of image processing, can solve the problems of poor quality of disparity map, low accuracy, and affecting the working effect of ADAS system

Active Publication Date: 2022-02-01
HISENSE
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current binocular stereo matching algorithms are derived on the basis of the high image quality of the binocular source images. The image quality of the target source image is also easily affected by the light, so it is easy to cause the image quality of the binocular source image to be poor. and the contrast will drop sharply. Therefore, using the binocular stereo matching algorithm to perform stereo matching on binocular source images with poor image quality, the obtained disparity map has more noise points, and the proportion of effective disparity points is small, that is, the disparity map. The quality is poor and the accuracy is low. Further, it will directly affect the working effect of the ADAS system

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, device and terminal for judging disparity map
  • Method, device and terminal for judging disparity map
  • Method, device and terminal for judging disparity map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0112] See image 3 , is a flow chart of an embodiment of a disparity map judging method shown in an exemplary embodiment of the present application, and the method may include the following steps:

[0113] Step 301: Obtain a gradient map and a disparity map according to the binocular source image collected by the binocular camera.

[0114] In the embodiment of the present application, a binocular camera can be arranged on the vehicle. The binocular camera has two cameras on the left and right. During an image collection process, the two cameras on the left and right can respectively collect an image. For the convenience of description, In the embodiment of the present application, the two images collected by the two cameras of the binocular camera are collectively referred to as a binocular source image, and at the same time, one of them can be designated as a target image and the other as a reference image.

[0115] In the embodiment of the present application, preprocessin...

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 present application provides a method, device and terminal for judging a disparity map, which relate to the field of image processing technology. The method includes: obtaining a gradient map and a disparity map based on a binocular source image collected by a binocular camera; obtaining a texture distribution map according to the gradient map , and obtain the disparity change distribution map according to the disparity map; according to the texture distribution map and the disparity change distribution map, determine the region in the disparity map that meets the preset conditions as an invalid parallax region; determine the disparity map according to the proportion of the invalid disparity region in the disparity map effectiveness. By applying this method, the validity and accuracy of the disparity map can be judged, so that when multiple invalid or poorly valid disparity maps are continuously judged, the driver can be reminded in time that there may be an abnormality in the working effect of the ADAS system, so as to remind the driver Drive carefully.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a disparity map evaluation method, device and terminal. Background technique [0002] Vehicle ranging based on binocular stereo vision technology, or detection of obstacles on the road is a popular research topic in the field of advanced driver assistant systems (Advanced Driver Assistant Systems, referred to as ADAS systems), and binocular stereo vision technology The core is binocular stereo matching. [0003] The current binocular stereo matching algorithms are derived on the basis of the high image quality of the binocular source images. The image quality of the target source image is also easily affected by the light, so it is easy to cause the image quality of the binocular source image to be poor. and the contrast will drop sharply. Therefore, using the binocular stereo matching algorithm to perform stereo matching on binocular source images with p...

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): G06T7/00G06T7/41
CPCG06T7/0002G06T7/41G06T2207/10012G06T2207/30252G06T2207/20228
Inventor 赵启东
Owner HISENSE