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

Decision-level fusion based bridge recognition method

A recognition method and decision-making technology, applied in the field of information processing, can solve problems such as low recognition rate, and achieve the effects of improving the accuracy rate, increasing the speed, and reducing the false alarm rate.

Active Publication Date: 2013-04-03
NORTH CHINA UNIVERSITY OF TECHNOLOGY
View PDF2 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] The present invention provides a bridge recognition method based on decision-making layer fusion, adopts multi-sensor fusion technology, comprehensively utilizes the complementary features of multispectral, panchromatic and SAR images for bridge recognition, solves the problem of low target recognition rate of a single image source, and effectively Improved correct recognition rate of bridge targets

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
  • Decision-level fusion based bridge recognition method
  • Decision-level fusion based bridge recognition method
  • Decision-level fusion based bridge recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] Refer to the attached Figure 1~3 , the technical solution of the present invention is described in detail.

[0084] Step 1: Read in the multispectral image, panchromatic image and SAR image, convert the multispectral image from RGB space to HSV space, and obtain three components of H, S and V.

[0085] The space conversion formula from the RGB color model space to the HSV color model is:

[0086] S=(MAX-MIN) / MAX

[0087] H = 60 * ( G - B ) / ( MAX - MIN ) R = MAX ...

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 a decision-level fusion based bridge recognition method. The method includes following steps: reading in multispectral images, full-color images and SAR (synthetic aperture radar) images, and subjecting the multispectral images to HSV (hue, saturation and value) spatial conversion; respectively performing expansion and corrosion pretreatment to components H, S and V; respectively subjecting the H, S and V to threshold segmentation; using 8 neighborhood search to remove small-area interference area to obtain land-water segmentation result; using morphological dilation and morphological corrosion operator to put water body area in order to obtain a potential bridge area; extracting textural features of the potential bridge area from the full-color images, determining threshold, and recognizing bridge; and subjecting bridge recognition results in the full-color images and the SAR images to decision-level fusion. Bridge recognition is realized by comprehensively utilizing complementary features of the multispectral images, the full-color images and the SAR images, so that correct recognition rate of bridge targets is effectively improved.

Description

technical field [0001] The invention relates to an information processing technology, in particular to a bridge identification method based on decision-making layer fusion. Background technique [0002] In recent years, with the unprecedented development of remote sensing technology, there are more and more means of obtaining remote sensing data, and the remote sensing data is becoming more and more abundant. At the same time, the application field of remote sensing is constantly expanding and deepening. With the explosive growth of remote sensing images, the ability and efficiency of information extraction has become a bottleneck that limits the development of remote sensing applications. [0003] Target recognition technology is an important content in the field of information processing. How to accurately identify targets from images has great application value in various fields, such as the identification of sensitive targets in military, the identification of lesions i...

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): G06K9/00
CPCG06V20/176
Inventor 张永梅马健喆孙静臧淼胥玉龙
Owner NORTH CHINA UNIVERSITY OF TECHNOLOGY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com