Gaussian mixture model-based remote sensing time sequence data fitting method

A Gaussian mixture model and time series data technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems that affect the extraction accuracy of vegetation parameter information, the seasonal change trend is not obvious, and achieve the effect of facilitating vegetation trend analysis.

Active Publication Date: 2019-07-19
ZHEJIANG UNIV OF TECH
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The directly acquired remote sensing NDVI time series data is a discrete data sequence, and is affected by noise factors such as clouds a...

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
  • Gaussian mixture model-based remote sensing time sequence data fitting method
  • Gaussian mixture model-based remote sensing time sequence data fitting method
  • Gaussian mixture model-based remote sensing time sequence data fitting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0027] A kind of remote sensing time series data fitting method based on Gaussian mixture model of the present invention, such as figure 1 shown, including the following steps:

[0028] Step 1: Obtain remote sensing time series data;

[0029] Prepare multiple remote sensing images of the same area, such as MODIS remote sensing images of 45 scenes with a two-year span at an interval of 16 days. Sure figure 2 The central mark point in the central box is the forest sampling point of this embodiment, and its geographical location is: N30°15′18.95″ north latitude, E120°06′54.32″ east longitude. Read the NDVI values ​​of the 45 remote sensing images in sequence, and organize them into NDVI time-series data in chronological order, as shown in Table 1.

[0030] Table 1

[0031]

[0032]

[0033] Step 2: Estimate the probability value;

[...

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 discloses a Gaussian mixture model-based remote sensing time sequence data fitting method. The method comprises the steps of 1, obtaining the remote sensing time sequence data; determining sampling points for the multi-scene remote sensing images in the same region, sequentially reading the NDVI values of the remote sensing images at the sampling points, and organizing the NDVI values into the NDVI time sequence data according to a time sequence; 2, estimating a probability value; drawing an NDVI time sequence data scatter diagram by taking the time as a horizontal axis and the NDVI value as a longitudinal axis; respectively calculating the trapezoidal area formed by the adjacent time sequence points and the transverse axis, and then solving the percentage of the trapezoidalarea of each interval in the total area to serve as the probability value of the current interval for subsequent calculation; step 3, carrying out probability value conversion; defining an amplification ratio M, multiplying the probability value of each interval by M to obtain A = {a1, a2,..., aN}, sequentially segmenting each corresponding interval into equal interval subintervals t, constructinga new time sequence t sequence, and step 4, solving the Gaussian mixture model parameters; and taking the new time sequence t sequence as the observation data, and solving the Gaussian mixture model,namely a probability distribution model.

Description

technical field [0001] The invention relates to a method for fitting remote sensing time series data based on a Gaussian mixture model. Background technique [0002] Remote sensing satellite images are widely used in forest succession, phenological changes, agricultural growth monitoring, crop yield estimation, urban expansion, etc. Among them, the normalized difference vegetation index NDVI (Normalized Difference Vegetation Index) is a measure of vegetation growth status and vegetation coverage. indicator factor. NDVI time series data analysis has great application potential. [0003] The directly acquired remote sensing NDVI time series data is a discrete data sequence, and is affected by noise factors such as clouds and the atmosphere, and the seasonal variation trend is not obvious, which greatly affects the accuracy of vegetation parameter information extraction. Remote sensing time series data fitting fits discrete data points obtained at different times into a curve...

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): G06K9/00
CPCG06V20/188
Inventor 沈瑛孙夏吴炜董天阳范菁
Owner ZHEJIANG UNIV 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