Multi-source scene feature extraction system and method based on index set constraint

A technology of scene features and index sets, which is applied to instruments, computing, character and pattern recognition, etc., can solve problems such as complex structures, achieve high confidence, high real-time performance, and solve heterogeneous preprocessing problems.

Pending Publication Date: 2022-07-29
中国人民解放军96901部队
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the application defect of the complex structure of the existing terminal guidance image landmark selection method, that is, the

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
  • Multi-source scene feature extraction system and method based on index set constraint
  • Multi-source scene feature extraction system and method based on index set constraint
  • Multi-source scene feature extraction system and method based on index set constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] A method for extracting multi-source scene features based on index set constraints of the present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0069] Aiming at the application defects of the existing terminal guidance image landmark selection algorithm, the present invention provides a multi-source scene feature extraction system and method based on index set constraints. The source feature extraction module realizes high-confidence heterologous feature extraction based on visible light image input, so as to complete the production of on-board matching heterologous template data, and provide support for high-precision matching and identification of precision guided weapons; it can be used to solve the preprocessing of benchmark images. The evaluation of the pros and cons of target adaptation structure to achieve comprehensive coverage of indicators.

[0070] A multi-source scene feature extraction system base...

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 relates to a multi-source scene feature extraction system and method based on index set constraint, and belongs to the technical field of image matching. According to the method, a visible light-binary image space mapping relation is formed through a binary generation mapping module; an optical adaptive landmark structure is selected from the visible light satellite picture data through a matching calculation module, and matching calculation is carried out by using a mapping model to obtain matching correlation surface information of the adaptive structure; statistical analysis is carried out on related surface information through an index evaluation module, and related surface matching characteristics are extracted; and through an intelligent evaluation module, preferably sorting the plurality of adaptive landmark structure matching index evaluation data to obtain an optimal evaluation adaptive structure combination. The method effectively solves the problem of heterogeneous preprocessing and the problem of reference map preprocessing target adaptation structure advantage and disadvantage evaluation, index coverage is comprehensive, adaptation structure index evaluation confidence is high, adaptation landmark area selection and manufacturing are simple, real-time performance is high, and actual combat requirements can be well met.

Description

technical field [0001] The invention belongs to the technical field of image recognition and image matching, and relates to a multi-source scene feature extraction system and method based on index set constraints. Background technique [0002] In the field of modern national defense and military, the intelligentization of precision guidance technology is the development trend of modern weapons and equipment systems. In the many high-tech local wars that broke out in recent years, precision guidance weapons are characterized by their high precision, high lethality, and strong anti-interference ability. Advantages such as low cost played a key role and had a crucial impact on the course and outcome of the war. [0003] Infrared imaging guidance is an important development direction of precision guidance. At present, the infrared imaging guidance technology at home and abroad is mainly based on image matching. The key to restricting its guidance application ability is the hard...

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): G06V10/44G06V10/75G06V10/776G06K9/62
CPCG06F18/217
Inventor 何浩东王才红许馨月高军强宫树香刘庆国钟华王兴隆蒋鸣赵云飞
Owner 中国人民解放军96901部队
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