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

Automatic selection method of scene matching area based on image information entropy

A technology of scene matching and image information, which is applied in the field of scene matching and navigation, can solve the problem that it is difficult to achieve a unified, systematic and comprehensive examination of the nature of the reference map, and achieve the effect of reducing the amount of selection calculation and effectively selecting

Inactive Publication Date: 2013-02-13
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the current scene matching area selection methods combine gray variance, number of independent pixels, edge density, correlation peak characteristics and other indicators to examine the suitability of the reference image matching. Since these indicators come from different theoretical perspectives, the reference image It is difficult to achieve a unified, systematic and comprehensive examination of properties. The quality of selection depends to a large extent on the effect of the combination of indicators and the selection strategy. The advantages still require manual participation

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 method of scene matching area based on image information entropy
  • Automatic selection method of scene matching area based on image information entropy
  • Automatic selection method of scene matching area based on image information entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] A method for automatically selecting a scene matching area based on image information entropy of the present invention is introduced below in conjunction with the accompanying drawings and embodiments:

[0045] Such as figure 1 As shown, a method for automatically selecting a scene matching area based on image information entropy includes the following steps:

[0046] The first step: selection of scene information;

[0047] Select a candidate scene matching area with a pixel repetition rate not lower than 70% from the candidate set to obtain candidate set 1. In this embodiment, the information entropy of the candidate set is calculated, and used as a reference index to check the scene information amount of the matching area. The candidate scene matching areas such as water surface, desert, field, flat open land and the like are eliminated from the candidate set to obtain the candidate set 1 . Specifically include the following steps:

[0048] (1) Using existing tech...

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 belongs to the technical field of scene matching and navigation, and specifically relates to a method for automatically selecting a scene matching area based on image information entropy, and aims to provide a selection method for realizing effective and automatic selection of a scene matching area for cruise missiles. It includes the following steps: the selection of scene information, the selection of feature stability and the selection of regional uniqueness. The present invention adopts the selection steps of scene information, feature stability and regional uniqueness, adopts the strategy of hierarchical selection and reverse elimination, reduces the calculation amount of scene matching area selection, and realizes the automatic, fast and effective scene matching area selection. The self-matching success probability of the selected scene matching area is >97%, the error variance is <10, and the selected matching area can meet the adaptability requirements.

Description

technical field [0001] The invention belongs to the technical field of scene matching and navigation, and in particular relates to a method for automatically selecting a scene matching area based on image information entropy. Background technique [0002] Scene matching has the advantages of high autonomy, accuracy independent of range, high guidance accuracy, wide strike range, repeatable target selection, etc. The cumulative error of the inertial navigation system is regularly corrected, which is an important means to improve the accuracy of weapon hits, auxiliary navigation and integrated navigation. [0003] The reference image information pre-stored in the recorded navigation computer becomes a reference image, which is usually a high-resolution satellite optical image or an aerial image. Usually, the number of matching areas to be selected on the scheduled flight track is huge, and it is difficult to directly use it as a reference map. It is necessary to select a scen...

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
Inventor 付梦印张晓晨王美玲邓志红周培德靳璐
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products