Object-level remote sensing change detection method and system based on dual related attention

A technology of change detection and attention, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of lack of semantic integrity and inability to truly simulate geographic entity targets, and achieve rapid convergence and avoid false positives. The effect of change interference and fast convergence

Active Publication Date: 2021-11-05
WUHAN UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitations of traditional hand-designed feature extraction methods, these segmented regions are usually threshold-dependent, making "objects" prone to over-segmentation and boundary fragmentation, without semantic integrity, and unable to truly simulate actual geographic entities Target

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
  • Object-level remote sensing change detection method and system based on dual related attention
  • Object-level remote sensing change detection method and system based on dual related attention
  • Object-level remote sensing change detection method and system based on dual related attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0036] At the data level, the framework designs a data augmentation method dedicated to change detection, which can effectively speed up the training speed of the model and improve the performance of the model. At the model level, the framework constructs a dual-related attention-guided change detection network, which can effectively extract the overall features and contextual associations of changing objects. The framework finally represents the detected changing geographic entities (such as newly added buildings, artificial structures, etc.) in the form of bounding boxes.

[0037] The embodiment of the present invention provides an object-level remote sensing change detection method based on dual correlation attention, including a data enhancement process dedicated to change detection (such as figure 1 shown) and a dual-rela...

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 provides an object-level remote sensing change detection method and system based on dual related attention, and the method comprises the steps: carrying out the data enhancement for change detection, and generating a dual-input stream; setting a backbone network sharing weight for receiving double input streams and extracting different scale characteristics of a double-time-phase image; setting a feature fusion neck guided by dual-correlation attention, paying attention to the correlation of dual-time-phase features of the same scale in a spatial level and a channel level to obtain refined difference features, and setting a refined path aggregation pyramid module to fuse the features of different scale layers; and finally, sending the difference features of different scales into a change detection head, and predicting the position, size and change confidence of the changed ground feature in a bounding box form. According to the data enhancement method special for change detection, model training can be accelerated, model performance can be improved, pseudo change interference in image pairs can be effectively resisted through guidance of a dual related attention mechanism, and the method and system have high accuracy and robustness.

Description

technical field [0001] The invention belongs to the field of automatic change detection of remote sensing images, in particular to an object-level remote sensing change detection method and system based on dual correlation attention. Background technique [0002] Change detection is the process of detecting differences by observing and recognizing the state of an object or phenomenon at different times. More precisely, the purpose of change detection is to find the change information of a specific semantic category of interest while filtering out the interference of irrelevant change information. It has always been one of the most important problems in the field of remote sensing. At present, change detection has been widely used in various applications, such as urban planning, land resource management, environmental monitoring, agricultural survey, disaster assessment and other applications, which has great research value. [0003] Currently, change detection methods can ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/253
Inventor 胡翔云张琳张觅
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap