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

Feature extraction method of night light remote sensing image based on two-dimensional Gaussian surface fitting

A Gaussian surface, remote sensing image technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problem of limited development and application of luminous images

Active Publication Date: 2022-07-12
CHANGGUANG SATELLITE TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of relatively limited development and application of night light images in the prior art, the present invention provides a night light remote sensing image feature extraction method based on two-dimensional Gaussian surface fitting

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
  • Feature extraction method of night light remote sensing image based on two-dimensional Gaussian surface fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] combine figure 1 Describe this embodiment, based on a two-dimensional Gaussian surface fitting method for extracting features from remote sensing images of night lights, the method is implemented by the following steps:

[0026] Step 1: Read the luminous image I.

[0027] Step 2: Smooth the data; specifically:

[0028] define filter window

[0029] Use the kernel to filter the image I to achieve the purpose of smoothing the image, and the smoothed image is defined as I'.

[0030] Step 3: Data scaling, which is implemented as follows:

[0031] According to the formula Scale the numerical range of image pixels to [0, 1], where I" represents the scaled image, max(I') represents the maximum pixel value of the image I', and min(I') represents the minimum pixel value of the image I'.

[0032] Step 4: Build a two-dimensional Gaussian function, the implementation method is as follows:

[0033] Define a 2D Gaussian function where A is the magnitude, x 1 , x 2 repres...

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

A feature extraction method for nighttime light remote sensing images based on two-dimensional Gaussian surface fitting belongs to the field of remote sensing image processing and analysis, and solves the problem that the prior art is relatively limited in the development and application of night light images. The image data is smoothed, and the light brightness value in the image is scaled; then a two-dimensional Gaussian function is designed, the parameters to be fitted are initialized, and the least squares method is used for fitting; finally, the parameters of the fitting function are extracted as the characteristics of the luminous image . The invention analyzes the night light image from the angle of night light distribution. The luminous image is projected into a three-dimensional coordinate system, the two-dimensional Gaussian function is used to fit the surface formed after mapping, and the geometric features of the two-dimensional Gaussian function are used to represent the data characteristics of the luminous image.

Description

technical field [0001] The invention relates to the field of remote sensing image processing and analysis, in particular to a method for extracting features of night light remote sensing images based on two-dimensional Gaussian surface fitting. Its main purpose is to map the luminous image to a three-dimensional coordinate system, fit the surface formed after projection to a two-dimensional Gaussian function, and extract the geometric features of the fitted surface to represent the characteristics of the luminous image. Background technique [0002] Night light remote sensing is to use earth observation sensors to obtain the visible light emitted by the surface under cloudless conditions at night. In the acquisition of remote sensing spatial information, night light remote sensing is an active branch in the field of remote sensing. Night light image data not only has the advantages of rapid and continuous acquisition of remote sensing data, but also can uniquely and directl...

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): G06V10/44G06V20/13G06T5/00
CPCG06T5/002G06T2207/10032G06V20/13G06V10/44Y02B20/40
Inventor 张贺峰特日根罗霄刘欣悦赵宇恒
Owner CHANGGUANG SATELLITE TECH CO LTD