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

Image recognition method, device, equipment and storage medium

An image recognition and image technology, applied in the field of image recognition, can solve the problems of adhesion and fusion of dense parts, inability to accurately segment adjacent houses, and inability to accurately identify buildings.

Active Publication Date: 2021-08-03
图兮数字科技(北京)有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous development of remote sensing image intelligent interpretation technology, the application of AI intelligent interpretation represented by the precise contour extraction of buildings is becoming more and more popular. However, for a long time, the identification and extraction of dense areas has always been a problem
In the process of generating the extracted black-and-white mask, the current interpretation technology will inevitably have serious problems such as adhesion and fusion in the dense parts, and cannot accurately realize the segmentation between adjacent houses, so that the buildings in the remote sensing image cannot be analyzed. for precise identification

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 recognition method, device, equipment and storage medium
  • Image recognition method, device, equipment and storage medium
  • Image recognition method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In the following, only some exemplary embodiments are briefly described. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present application. Accordingly, the drawings and descriptions are to be regarded as illustrative in nature and not restrictive.

[0063] figure 1 A flowchart showing an image recognition method according to an embodiment of the present application. Such as figure 1 As shown, the image recognition method may include:

[0064] S11. Acquiring an image to be recognized.

[0065] S12. Process the image to be recognized according to the patch model to obtain a patch vector.

[0066] S13. Process the image to be recognized according to the dense region segmentation line model to obtain a common segmentation line vector between regions.

[0067] S14. Obtain a segmented patch vector according to the patch vector and the common dividing ...

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

This application proposes an image recognition method, including: obtaining the image to be recognized; processing the image to be recognized according to the patch model to obtain a patch vector; processing the image to be recognized according to the dense area segmentation line model to obtain the common segmentation line between regions vector; obtain the segmented speckle vector according to the speckle vector and the shared dividing line vector between regions; correct the segmented speckle vector to identify each region in the image to be recognized. The embodiments of the present disclosure can solve the problem that the segmentation between adjacent houses cannot be accurately realized, so as to accurately identify the buildings in the remote sensing image.

Description

technical field [0001] The present application relates to the technical field of image recognition, and in particular to an image recognition method, device, equipment and storage medium. Background technique [0002] With the continuous development of remote sensing image intelligent interpretation technology, the application of AI intelligent interpretation represented by the precise contour extraction of buildings is becoming more and more popular. However, for a long time, the identification and extraction of dense areas has always been a problem. In the process of generating the extracted black-and-white mask, the current interpretation technology will inevitably have serious problems such as adhesion and fusion in the dense parts, and cannot accurately realize the segmentation between adjacent houses, so that the buildings in the remote sensing image cannot be analyzed. for precise identification. Contents of the invention [0003] The embodiment of the present appl...

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): G06K9/00G06K9/34G06K9/62G06N3/04
CPCG06V20/176G06V10/267G06N3/045G06F18/214
Inventor 郑李辉曾宇
Owner 图兮数字科技(北京)有限公司