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

Method, device, storage medium and processor for locating image feature points

A technology of image feature points and positioning methods, applied in the field of image processing, can solve the problem of low positioning accuracy

Active Publication Date: 2020-12-18
NEUSOFT CORP
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, although there are some detection techniques for image key points, these methods can only locate the feature points near the real feature points, and the accuracy of positioning is low.

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, storage medium and processor for locating image feature points
  • Method, device, storage medium and processor for locating image feature points
  • Method, device, storage medium and processor for locating image feature points

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0069] see figure 1 , which is a flowchart of a method for locating image feature points provided in an embodiment of the present application.

[0070] Such as figure 1 As shown, the positioning method of the image feature point provided by the embodiment of the present application includes:

[0071] Step 101: Determine all the pixels in the neighborhood of the feature point; each pixel in the neighborhood has an adsorption effect on the feature point.

[0072] It should be noted that, in this embodiment, an image in which feature points are located using the prior art is obtained in advance. Due to the limited positioning accuracy, there is a deviation between the position of the feature point located in the image and the exact position. In this embodiment, the feature points in the pre-acquired image are relocated.

[0073] According to the inventor's research, it is found that there is an adsorption effect between pixels in the image. In this embodiment, feature points...

no. 2 example

[0092] see image 3 , which is a flow chart of another method for locating image feature points provided by an embodiment of the present application.

[0093] Such as image 3 As shown, the positioning method of the image feature point provided by the embodiment of the present application includes:

[0094] In this embodiment, step 301 is the same as step 101 in the first embodiment, and the specific implementation of step 301 may refer to the description in the first embodiment, and details are not repeated here.

[0095] Step 302: According to the gradient vector of the pixel point, and the position of the pixel point and the position of the feature point, the adsorption force of the pixel point to the feature point is obtained.

[0096] The current inaccurately positioned feature point, the adsorption force of any pixel point in its neighborhood is related to the gradient vector of the pixel point and the positions of the two points.

[0097] The image is stored as a dis...

no. 3 example

[0137] see Figure 5 , which is a schematic structural diagram of an image feature point positioning device provided in an embodiment of the present application.

[0138] Such as Figure 5 As shown, the image feature point positioning device provided by the embodiment of the present application includes: a determination unit 51 , an adsorption force acquisition unit 52 , a comprehensive adsorption force acquisition unit 53 and a positioning unit 54 .

[0139] Wherein, the determination unit 51 is used to determine all the pixels in the neighborhood of the feature point; each pixel in the neighborhood has an adsorption effect on the feature point;

[0140] An adsorption force acquisition unit 52, configured to obtain the adsorption force of each pixel point to the feature point;

[0141] A comprehensive adsorption force acquisition unit 53, configured to use the adsorption force of each pixel point to the feature point to obtain the comprehensive adsorption force of all the p...

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 application discloses a positioning method, device, storage medium and processor for image feature points. This application utilizes the adsorption effect between pixels in the image to correct the position of the currently inaccurate feature point. First, determine all the pixels in the neighborhood of the feature point; then, obtain the adsorption force of each pixel point in the neighborhood to the feature point; then, use the adsorption force of each pixel point to the feature point in the neighborhood to obtain all The comprehensive adsorption force of pixels to feature points. Finally, according to the magnitude and direction of the comprehensive adsorption force, the position of the feature point with inaccurate positioning is corrected to obtain the corrected position of the feature point. The present application can perform position correction on feature points with inaccurate positioning, and compared with the prior art, the accuracy of feature point positioning is significantly improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a method, device, storage medium and processor for locating image feature points. Background technique [0002] In the field of image processing technology, feature points refer to representative points in the image, such as image corner points, edge points, etc. Feature points are also called key points, or interest points. The identification and location of feature points play an important role in image recognition, image matching, image deformation and 3D modeling. For example, face recognition in image recognition. The precise location of feature points is the key to post-processing of image recognition. The more accurate the location of the feature points in the image, the higher the image recognition rate. [0003] Although there are some detection techniques for image key points at present, these methods can only locate the feature points near th...

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): G06K9/00G06K9/62
CPCG06V40/168G06V10/757
Inventor 罗子懿
Owner NEUSOFT CORP