High-resolution remote sensing image change detection method based on multi-scale segmentation and fusion

A multi-scale segmentation and remote sensing image technology, applied in the field of hyperspectral remote sensing images, can solve the problems of inability to guarantee the integrity of detection results, low detection accuracy of high-resolution remote sensing images, etc., to improve accuracy, ensure integrity, and improve detection accuracy Effect

Active Publication Date: 2017-08-22
HARBIN INST OF TECH
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing remote sensing image change detection technology has low detection accuracy for high-resolution remote sens

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
  • High-resolution remote sensing image change detection method based on multi-scale segmentation and fusion
  • High-resolution remote sensing image change detection method based on multi-scale segmentation and fusion
  • High-resolution remote sensing image change detection method based on multi-scale segmentation and fusion

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0012] Specific implementation manner 1: The method for detecting changes in high-resolution remote sensing images based on multi-scale segmentation and fusion described in this embodiment, the specific process of the detection method is:

[0013] Step 1. Use a multi-scale segmentation algorithm to segment the multi-temporal high-resolution remote sensing image at a spatial scale. The spatial scale is divided into two parts: coarse scale and fine scale, and appropriate shape factors are selected to use top-down regional heterogeneity Gender guidelines to merge;

[0014] Step 2. Perform feature extraction on the object angle of the target in each scale image segmented in Step 1, use the object feature to describe the object itself, and then perform vector analysis relative to remote sensing images in other phases to obtain object difference maps of multiple scales ;

[0015] Step 3. Perform change information extraction and fusion on the object difference map of multiple scales obtai...

specific Embodiment approach 2

[0021] Specific implementation manner 2: This implementation manner further illustrates the implementation manner 1. The specific method of using a multi-scale segmentation algorithm to perform spatial scale segmentation on multi-temporal high-resolution remote sensing images is:

[0022] Multi-scale segmentation uses a top-down region merging algorithm based on minimum heterogeneity to obtain image segmentation sequences of different scales of the input image, and combines shape heterogeneity to obtain merged regions. The representation of heterogeneity is:

[0023]

[0024] Where h total Represents overall heterogeneity, Indicates the weight of spectral heterogeneity, satisfying h c And h s Represents spectral heterogeneity and shape heterogeneity respectively, and satisfies:

[0025]

[0026]

[0027] among them, Indicates the weight of each band, the number of bands is c, σ c Indicates the standard deviation of each spectral band; Represents the smoothness weight, h sm And h...

specific Embodiment approach 3

[0038] Specific embodiment 3: This embodiment further explains the first or second embodiment. The multi-scale is divided into coarse scale and fine scale, the scale parameter of the fine scale is 10-50, and the scale parameter of the coarse scale is 50-100.

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 a high-resolution remote sensing image change detection method based on multi-scale segmentation and fusion, belongs to the technical field of hyperspectral remote sensing images, and solves the problems that the present remote sensing image change detection technology has low detection accuracy on the high-resolution remote sensing image and cannot guarantee the integrity of the detection result. The concrete process of the method comprises the steps that spatial scale segmentation is performed on the multi-temporal high-resolution remote sensing image by using a multi-scale segmentation algorithm; feature extraction is performed on the target in each scale of image after segmentation on the object perspective, and the object is described by using the object features so that vector analysis is performed relative to the remote sensing image of other temporal and object difference images of multiple scales are obtained; and change information extraction and fusion are performed on the obtained object difference images of multiple scales so that the final total change result image is obtained. The high-resolution remote sensing image change detection method is used for high-resolution remote sensing image change detection.

Description

Technical field [0001] The invention relates to a high-resolution remote sensing image change detection method, belonging to the technical field of hyperspectral remote sensing images. Background technique [0002] With the increase of satellite resolution, the detailed information of high-resolution remote sensing satellite data is rich, and the amount of data has increased sharply. The increase in image data volume and complexity has made it more difficult to automatically identify changing areas in multi-temporal remote sensing images. The corresponding data processing technology has also increased. It is difficult to meet the accuracy requirements; and the high-resolution remote sensing images are rich in detailed information, the edges of various objects are obvious, and the noise is greatly increased. At this stage, most change detection methods based on feature domains and pixel levels cannot overcome the problem of insufficient detection accuracy. Target-level detection m...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V20/13G06V10/462G06F18/253
Inventor 张钧萍郭庆乐李彤
Owner HARBIN INST OF TECH
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