Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-temporal remote sensing image feature extraction method based on difference temporal index features

A remote sensing image and feature extraction technology, which is applied to instruments, character and pattern recognition, computer components, etc., can solve the problems that cannot reflect the correlation degree of time series index features

Inactive Publication Date: 2016-01-27
HARBIN INST OF TECH
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims to solve the problem that the existing multi-temporal remote sensing image feature extraction method cannot reflect the correlation degree of time series index features between different time phases, thereby providing a multi-temporal remote sensing image feature extraction method based on differential time series index features

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
  • Multi-temporal remote sensing image feature extraction method based on difference temporal index features
  • Multi-temporal remote sensing image feature extraction method based on difference temporal index features
  • Multi-temporal remote sensing image feature extraction method based on difference temporal index features

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0022] The specific embodiment one, a kind of multi-temporal remote sensing image feature extraction method based on difference time series index feature, it is realized by the following steps:

[0023] Step 1. Arrange all the remote sensing image data obtained in different periods in chronological order to form a multi-temporal remote sensing image, and extract the index features under each phase;

[0024] Step 2. Using the exponential features obtained in step 1, perform differential operations using the exponential features of adjacent time phases to generate first-order difference time series exponential features;

[0025] Step 3. The first-order difference time-series index feature obtained in step 2 is subjected to the differential operation of adjacent first-order difference time-series features to generate the second-order difference time-series index feature, and the multi-temporal remote sensing image feature extraction based on the difference time-series index featur...

specific Embodiment approach 2

[0026] Specific embodiment 2. The further limitation of this specific embodiment and the multi-temporal remote sensing image feature extraction method based on differential time series index features described in specific embodiment 1, in step 1, the index feature under each phase is extracted The method is to use the formula:

[0027] M N D W I = G r e e n - M I R G r e e n + M I R

[0028] achieved;

[0029] Among them, MNDWI is the improved normalized difference water index, Green is the green band, and MIR is the mid-infrared band.

specific Embodiment approach 3

[0030] Specific embodiment three, this specific embodiment and the further limitation of a multi-temporal remote sensing image feature extraction method based on differential time-series index features described in specific embodiment two, the index feature obtained in step one described in step two, using The exponential features of adjacent time phases are differentially calculated to generate the first-order differential time series index features by using the formula:

[0031] dMNDWI=MNDWI t+1 -MNDWI t

[0032] achieved;

[0033] Among them, dMNDWI represents the first-order difference timing MNDWI feature, MNDWI t+1 and MNDWI t are the improved normalized normalized water index under the t+1th time series and the tth time series respectively.

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 multi-temporal remote sensing image feature extraction method based on difference temporal index features, relating to the field of multi-temporal remote sensing image feature extraction. Aiming to solve the problem that a multi-temporal remote sensing image feature extraction method in the prior art cannot reflect the associated degree of the temporal index features of different time phases, through the extraction of the index features of each time phase, the method performs difference operation on the index features of adjacent time phases based on the principle of discrete function differences to generate a first order difference temporal index feature, and performs difference operation on the basis of the first order difference temporal index feature to generate a second order difference temporal index feature. By means of the difference temporal index features, the method further describes the sensitivity degree of different natural objects along with time change. The method is suitable for the extraction of multi-temporal remote sensing image features.

Description

technical field [0001] The invention relates to the field of multi-temporal remote sensing image feature extraction. Background technique [0002] To a certain extent, multi-temporal remote sensing images reflect the state changes of various features at different times or locations, and time-series features are a series of feature extractions based on multi-temporal remote sensing images. Time-series index features are the most commonly used features in multi-temporal remote sensing images. Different indices have different sensitivities to different ground features. Among them, the modified normalized difference water index (MNDWI) is more sensitive to the moisture content of each ground feature. The common time-series index features only use the respective index features in their respective phases, which cannot reflect the degree of correlation of the time-series index features between different time phases. Contents of the invention [0003] The present invention aims 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
IPC IPC(8): G06K9/46
CPCG06V10/48
Inventor 谷延锋刘欢
Owner HARBIN INST OF TECH
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com