Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion

A remote sensing image fusion and target recognition technology, applied in the field of digital image processing

Active Publication Date: 2012-09-12
BEIHANG UNIV
View PDF2 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing recognition methods fail to play the role of target composition and the spatial relationship between sub-targets in recognition

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
  • Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion
  • Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion
  • Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Such as figure 1 As shown, the implementation of the present invention is divided into four main steps, namely: feature hierarchy and relationship analysis, region segmentation and target potential region extraction, target region extraction and sub-target region division, sub-target identification and target verification. Taking the recognition of large and medium-sized targets such as airports and ports in multi-source remote sensing images (multispectral, SAR, panchromatic) as examples, the specific implementation steps of the present invention will be described in detail below.

[0022] (1) Feature hierarchy and relationship analysis: Divide target features into five levels, and analyze the selection effect of high-level features on middle and low-level features based on relevant experience knowledge of the target, and establish selection criteria for high-level features on middle and low-level features;

[0023] 1) Multi-layer representation of target features

[...

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 provides a method of identifying large and medium-sized objects based on multi-source remote sensing image fusion. The method comprises that multispectral and SAR images are segmented into image areas according to spectrum distribution between different objects and differences of electromagnetic radiation, and a potential area of an object is extracted according to experience and knowledge of object distribution, so that characteristic extraction and object identification are more targeted while identification efficiency and identification accuracy of the system are improved; that based on the above, object areas are determined by extracting object contour, spatial layout and the like, and sub-object areas are divided according to spatial layout relation of the object contour and sub-object spatial layout; and that sub-object characteristics are extracted, and with the guidance of object characteristic set and object prior knowledge, sub-object identification and object verification are finally realizedby execution of identification rules and matching of characteristics.

Description

technical field [0001] The invention relates to a method for automatic recognition of remote sensing image targets, in particular to a method for realizing automatic recognition of large and medium-sized targets based on multi-source remote sensing image feature extraction technology, which belongs to the technical field of digital image processing. Background technique [0002] The application fields of remote sensing technology cover many aspects such as environmental monitoring, resource investigation, land planning, disaster prevention, map surveying and mapping, and weather forecasting, and have made significant contributions to the development of the national economy. Among them, the identification of large and medium-sized ground targets such as airports, ports, bridges, oil depots, ships, and aircrafts is one of the research hotspots in the application of remote sensing technology. With the rapid development of aviation / space remote sensing technology, visible light,...

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): G06K9/46G06T7/00
Inventor 李波胡蕾丁浩季艳田越
Owner BEIHANG UNIV
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