Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Automatic Selection of Scale Segmentation Parameters in Object-Oriented Remote Sensing Image Analysis

A technology for segmenting parameters and remote sensing images, applied in the field of remote sensing geoscience analysis, can solve problems such as single and difficult to understand the overall image, and achieve high theoretical credibility, wide practicability, and work efficiency.

Inactive Publication Date: 2016-08-17
CHINA UNIV OF GEOSCIENCES (BEIJING)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the surface system is a complex system composed of different levels of subsystems. Since the objects contained in the images are of different sizes, they need to be reflected at different processing scales. However, the current object-oriented remote sensing image analysis is often based on discrete or With a single scale, it is difficult to achieve a global understanding of the image

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
  • Automatic Selection of Scale Segmentation Parameters in Object-Oriented Remote Sensing Image Analysis
  • Automatic Selection of Scale Segmentation Parameters in Object-Oriented Remote Sensing Image Analysis
  • Automatic Selection of Scale Segmentation Parameters in Object-Oriented Remote Sensing Image Analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039]The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0040] Such as figure 1 As shown, it is a flow chart of the method for automatically selecting scale segmentation parameters in the object-oriented remote sensing image analysis of the embodiment of the present invention. This embodiment includes the following steps:

[0041] Step 10: Input the remote sensing image, which is a panchromatic image.

[0042] This embodiment takes panchromatic images as an example, but the method and idea proposed by the present invention are also applicable to the selection of scale segmentation parameters of multispectral remote sensing images.

[0043] Step 20: Automatic selection of spatial scale segmentation parameters.

[0044] The aut...

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 automatic selection method of scale segmentation parameters in object-oriented remote sensing image analysis: the optimal spatial scale segmentation parameters are determined by obtaining the average local variance curve variable range method; the optimal attribute scale segmentation parameters are determined by the local variance histogram The graph estimation method is determined; the optimal combined threshold parameters are determined by using anisotropic spatial correlation statistics to obtain horizontal and vertical ranges; the index evaluation method is used to evaluate the scale effect of the segmentation results and optimize the adjustment of scale segmentation parameters. The present invention takes into account geo-spatial statistics and pattern recognition theory and method, realizes the automatic selection of optimal scale segmentation parameters before segmentation, and the determined optimal scale segmentation parameters can be clearly explained based on statistical theory, and has higher theoretical credibility , improving the efficiency and accuracy of object-oriented remote sensing image information extraction and analysis.

Description

technical field [0001] The invention relates to the field of remote sensing geoscience analysis methods, in particular to an automatic selection method of scale segmentation parameters in object-oriented remote sensing image analysis. Background technique [0002] The research on Object-Oriented Remote Sensing Image Processing and Analysis (GEOBIA) is still in its infancy, and the academic community has not yet clearly defined the concept of object-oriented scale. According to the definition of image objects in mainstream object-oriented commercial software—an image object is a connected region composed of pixels with the same attributes, the superficial meaning of scale in object-oriented image processing and analysis is the size of image objects or object details in terms of spatial span; From the perspective of image object extraction algorithm, that is, image segmentation algorithm, the scale selection in object-oriented image processing and analysis mainly corresponds 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
Inventor 明冬萍
Owner CHINA UNIV OF GEOSCIENCES (BEIJING)
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
Eureka Blog
Learn More
PatSnap group products