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

Image processing method and device, computer equipment and storage medium

An image processing and image technology, applied in the field of image processing, can solve the problems of too many missing images, unsatisfactory number of changed areas, and unreal application, etc., to achieve the effect of improving accuracy and efficiency

Inactive Publication Date: 2021-03-02
ALIBABA GRP HLDG LTD
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The applicant found through research that most of the changed areas need to be manually extracted, which not only has the problem of missing more mentions, but also has low efficiency, and the general computer detection method is not ideal due to the unsatisfactory number of found and corrected changed areas. really applied to the actual scene

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 processing method and device, computer equipment and storage medium
  • Image processing method and device, computer equipment and storage medium
  • Image processing method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0190] The embodiment of the present application discloses an image processing method and device. Example 1 includes an image processing method, including:

[0191] Inputting the first image and the second image into the corresponding encoding network for feature extraction to obtain feature data of different encoding levels;

[0192] Merge the feature data of the same coding level to obtain the target feature data of different coding levels;

[0193] performing superposition and decoding operations on the target feature data of different coding levels in sequence to obtain decoded data;

[0194] Difference data between the first image and the second image are determined based on the decoded data.

example 2

[0195] Example 2 may include the method described in Example 1, wherein, before inputting the first image and the second image into the corresponding encoding network for feature extraction to obtain feature data of different encoding levels, the method further includes:

[0196] Two remote sensing images at different times for the same area are received as the first image and the second image.

example 3

[0197] Example 3 may include the method described in Example 1 and / or Example 2, wherein said inputting the first image and the second image into the corresponding encoding network for feature extraction, and obtaining feature data of different encoding levels includes:

[0198] performing feature extraction on the first image and the second image in the corresponding encoding network to obtain the feature data of the first encoding level;

[0199] Feature extraction is performed on the feature data of the N-1th encoding level in the encoding network to obtain the feature data of the Nth encoding level.

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 embodiment of the invention discloses an image processing method and device. The method comprises the following steps: respectively inputting a first image and a second image into corresponding coding networks for feature extraction to obtain feature data of different coding levels, and then combining the feature data of the same coding level to obtain target feature data of different coding levels, the target feature data of different coding levels are sequentially subjected to superposition operation and decoding operation to obtain the decoded data, and the difference data between the first image and the second image is determined according to the decoded data, so that two input images can be better distinguished during coding, and the features of multiple coding levels are fused during decoding to obtain the target feature data of different coding levels. According to the method, the abstract high-level features, the concrete low-level features and the features of all the middle levels between the abstract high-level features and the concrete low-level features can be utilized, the difference is efficiently extracted from the two images, and the accuracy and efficiency of discovering the difference between the images are improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an image processing method, an image processing device, a computer device, and a computer-readable storage medium. Background technique [0002] With the development of computer technology, computer detection has begun to be applied to the comparison task of two phases of remote sensing images. For example, new building detection is the most common one, which is mostly used in land management and law enforcement. [0003] Compared with the new construction inspection, the ground-breaking construction inspection covers a wider range. It not only includes the detection of new buildings, but also includes the detection of building demolition, building reconstruction, agricultural land, cultivated land, forest land, construction site, new roads, coastline changes, etc. The application scenarios have also expanded from a single land management law enforcement t...

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): G06K9/46G06K9/62G06N3/04
CPCG06V10/462G06N3/045G06F18/214
Inventor 陈伟涛王洪彬李昊
Owner ALIBABA GRP HLDG LTD