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

An object-based change detection method for multi-scale hierarchical representation learning

A multi-scale and hierarchical technology, applied in the field of image processing, can solve the problems of low robustness and one-sidedness, and achieve the effect of improving robustness and change detection accuracy.

Active Publication Date: 2020-09-22
XIDIAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing feature learning methods only learn abstract feature representation directly through a single learning model, which makes the learned features one-sided and less robust

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
  • An object-based change detection method for multi-scale hierarchical representation learning
  • An object-based change detection method for multi-scale hierarchical representation learning
  • An object-based change detection method for multi-scale hierarchical representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] See figure 1 , figure 1 It is a schematic flowchart of a change detection method based on object-based multi-scale hierarchical expression learning provided by an embodiment of the present invention. An embodiment of the present invention provides a change detection method based on object-based multi-scale hierarchical expression learning, including:

[0043] Acquiring a fusion image and a multi-scale image according to the first remote sensing image to be detected;

[0044] Obtaining a superpixel map according to the fused image;

[0045] Acquiring multi-scale hierarchical features according to the multi-scale image, the superpixel map and the multi-scale hierarchical learning model;

[0046] A detection result map is obtained according to the multi-scale hierarchical features.

[0047] The object-based multi-scale hierarchical expression learning change detection method proposed in the embodiment of the present invention uses multiple depth models to perform featu...

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 relates to an object-based change detection method for multi-scale hierarchical expression learning. The method comprises the steps of obtaining a fusion image and a multi-scale image according to a first to-be-detected remote sensing image; Obtaining a superpixel mapping graph according to the fused image; Obtaining multi-scale hierarchical characteristics according to the multi-scale image, the super-pixel mapping graph and a multi-scale hierarchical learning model; And obtaining a detection result graph according to the multi-scale hierarchical characteristics. According to the object-based multi-scale hierarchical expression learning change detection method provided by the invention, a plurality of depth models are used for carrying out feature learning on a multi-scale image to extract a plurality of groups of hierarchical features, and the plurality of groups of depth features are used for effectively completing hierarchical change region recognition from coarse tofine, so that the change detection precision is improved, and the robustness is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a change detection method based on object-based multi-scale hierarchical expression learning. Background technique [0002] Remote sensing images use computers to analyze the spectral information and spatial information of various ground objects in remote sensing images, select features, and use certain means to divide the feature space into complementary and overlapping subspaces, and then group each pixel in the image into into the subspace. Remote sensing images with high temporal resolution and high spatial resolution play an important role in applications such as land use change detection, dynamic monitoring, and rapid land surface change detection. [0003] The existing detection methods for changes in remote sensing images are divided into pixel-based change detection methods and object-based change detection methods. The pixel-based change detection ...

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): G06K9/00G06K9/62G06K9/52
Inventor 殷廷瑞陈晨胡少哲万春曼刘佳凤张涛
Owner XIDIAN UNIV