Feature extraction and matching method based on multimodal image of airborne photoelectric system

A multi-modal image and feature extraction technology, applied to computer parts, character and pattern recognition, instruments, etc., can solve problems such as dimension difference, texture difference, viewing angle difference, etc., to achieve the effect of matching and improving capabilities

Pending Publication Date: 2022-07-12
西安应用光学研究所
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are large differences in the multi-modal image itself, including texture differences, dimension differences, cross-scale, viewing angle differences, etc.
There are still very big technical challenges

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 and matching method based on multimodal image of airborne photoelectric system
  • Feature extraction and matching method based on multimodal image of airborne photoelectric system
  • Feature extraction and matching method based on multimodal image of airborne photoelectric system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] In order to make the purpose, content and advantages of the present invention clearer, the specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0012] like figure 1 As shown, the multi-modal image feature extraction and matching method according to the embodiment of the present invention includes the following steps: first, feature extraction is performed based on two input video images; secondly, uniform feature points are generated based on Generate an adaptive matching template for one of the feature points; thirdly, based on the generated template, use the kernel correlation algorithm to match the feature map of the other channel; fourth, for the result of template matching, use vector field consistency to perform false matching cull.

[0013] Each step in the above process is described in detail below:

[0014] S1: Multimodal Image Feature Extraction

[0015] The in...

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 airborne photoelectric reconnaissance and situation awareness, and discloses a feature extraction and matching method based on a multi-modal image of an airborne photoelectric system, which comprises the following steps: S1, extracting features of the multi-modal image; s2, adaptively selecting a matching template; s3, performing kernel correlation matching based on a template; and S4, removing mismatching. According to the method, the feature map is generated after feature extraction is carried out on the multi-modal image of the airborne photoelectric system, matching of a large number of feature points is carried out based on the feature map, mismatching is eliminated, correct matching point pairs are obtained, finally correct matching of the multi-modal image is achieved, and the capacity under multiple task scenes can be improved.

Description

technical field [0001] The invention belongs to the technical field of airborne photoelectric reconnaissance and situational awareness, and relates to a feature extraction and matching method based on a multimodal image of an airborne photoelectric system. Background technique [0002] Airborne optoelectronic systems generally have multiple optoelectronic sensors, and some advanced optoelectronic systems also have powerful data storage and processing capabilities, including storage of massive terrain data, 3D reconstruction and real-time rendering processing, which can provide different modalities and even different dimensions. Object- and scene-related graphic images, as well as multispectral images. [0003] Different images provide different scene or target information and have strong complementary characteristics. The fusion of multi-modal images can extract their respective information and complement each other. It has strong requirements under multiple tasks, including...

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 Applications(China)
IPC IPC(8): G06V10/75G06V10/40G06K9/62
Inventor 李辉高强肖相国范浩硕郭羽刘建平王常世杨科康臻薛媛元赵俊成
Owner 西安应用光学研究所
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