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

Adaptive spatial filtering method based on neighborhood

A spatial filtering and self-adaptive technology, applied in image data processing, instrumentation, computing, etc., can solve the problems of blurred boundaries, reduce the reliability and accuracy of change detection results, improve the degree of automation, and improve the intra-class quality, noise reduction effect

Active Publication Date: 2021-05-25
XIAN UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a neighborhood-based adaptive spatial filtering method, which solves the problem that the filtering method in the prior art filters out salt and pepper noise while making different The mixture between ground objects and blurred boundaries greatly reduce the reliability and accuracy of change detection results

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
  • Adaptive spatial filtering method based on neighborhood
  • Adaptive spatial filtering method based on neighborhood
  • Adaptive spatial filtering method based on neighborhood

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] Detailed steps of the present invention are as follows:

[0027] Image data description: JN data is the original image data acquired by QuickBird satellite, and the spectral ranges included are blue band (0.45-0.52m), green band (0.52-0.59m), red band (0.63-0.69m), Near-infrared band (0.77-0.89m), and the original image contains multiple types of ground objects and scenes.

[0028] Step 1. Initialize each pixel of the input image, take each pixel as the center point of the window, and obtain the corresponding window pixel value with a window of size 3×3.

[0029] Step 2, count each pixel value obtained by the 3×3 window, and sort (from small to large), and obtain the upper quartile pixel point Up_quartile_pixel and the lower quartile pixel point Low_quartile_pixel.

[0030] Step 3, for each pixel as the seed pixel Pixel, the upper quartile pixel and the lower quartile pixel are used as constraints to perform adaptive neighborhood point expansion (Low_quartile_pixel≤Pix...

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 an adaptive spatial filtering method based on a neighborhood, and the method comprises the steps: 1, initializing each pixel point of an input image, and obtaining a corresponding window pixel value; 2, sorting from small to large, and obtaining upper quartile pixel points and lower quartile pixel points; 3, carrying out adaptive neighborhood expansion by taking the upper quartile pixel points and the lower quartile pixel points as constraint conditions, carrying out adaptive filtering by taking the obtained adaptive region as neighborhood information to obtain a filtered image, and calculating coordinates of all pixel points in the adaptive region and variances of seed pixel values of all the pixel points; 4, obtaining the variance of the filtered image and the seed pixel points, and judging whether the condition is true or not; and 5, repeating the steps 3-4, carrying out iterative calculation until all pixel points meet a judgment condition, and taking the obtained last filtering image as a final filtering image. Image edge detail information is kept, and the definition is high.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image change detection neighborhood, and relates to a neighborhood-based self-adaptive spatial filtering method. Background technique [0002] With the rapid development of remote sensing satellites and aerospace remote sensing technology, the spatial resolution and temporal resolution of high-resolution images have been greatly improved. Through the analysis and rapid processing of remote sensing image data, information on surface changes can be effectively obtained, which is very useful for exploring the surface. Provide data support for changes, and provide important scientific basis for urban changes, precision agriculture, geological disasters, etc. On the one hand, with the improvement of image resolution, the ability to obtain ground object information is enhanced, but on the other hand, it is found that new and old images in different periods have a lot of micro noise, and the spect...

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): G06T5/00
CPCG06T2207/10032G06T2207/20028G06T5/70
Inventor 吕志勇王锋军李广飞杨萱
Owner XIAN UNIV OF TECH