SAR graph ship target detection method based on transform domain information fusion

A technology of target detection and ship detection, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as urgent demand for high-precision target detection algorithms and difficulty in identifying structural information

Active Publication Date: 2021-06-08
北京理工大学重庆创新中心 +1
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the identification of structural information in SAR images is a difficult problem
[0004] To sum up, the accuracy of target detection in SAR images has resulted, and with the increasing amount of SAR data acquired by a large number of orbiting radar satellites every day, the demand for high-precision target detection algorithms has become more and more urgent

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
  • SAR graph ship target detection method based on transform domain information fusion
  • SAR graph ship target detection method based on transform domain information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] This embodiment provides a method for detecting ship targets in SAR graphics based on transformation domain information fusion, the process of which is as follows figure 1 shown. Firstly, the SAR image is input into the ship target detection network, and the preliminary ship detection result is output; at the same time, the SAR image is input into the optical image conversion network, and the pseudo optical image corresponding to the SAR image is output; after that, the pseudo optical image is input into the segmentation In the network, the segmentation result is output; finally, the segmentation result and the preliminary ship detection result are input into the false alarm elimination algorithm, and the detection result after removing the false alarm is obtained, which is the final ship detection result.

[0047] It should be understood that the step "obtain preliminary ship detection results based on the SAR image" and the step "convert the SAR image into a pseudo-op...

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 an SAR graph ship target detection method based on transform domain information fusion. The method includes obtaining a preliminary ship detection result based on an SAR image; converting the SAR image into a pseudo optical image, and inputting the pseudo optical image into an image segmentation network to obtain a segmentation result; and performing false alarm elimination on the preliminary ship detection result according to the segmentation result to obtain a final ship detection result. Compared with a traditional SAR image ship detection algorithm, the invention has the advantages that false alarm elimination of a preliminary detection result is finally realized through SAR image conversion and segmentation, so that the ship detection and recognition precision is improved; meanwhile, the conversion network from the SAR image to the optical image can assist the interpretation of the SAR image.

Description

technical field [0001] The invention relates to the technical field of synthetic aperture radar target detection, in particular to a SAR graphics ship target detection method based on transformation domain information fusion. Background technique [0002] Synthetic Aperture Radar (SAR) and optical sensors constitute the two most important forms of spaceborne Earth observation. Compared with optical systems, SAR images have the advantage of all-weather, all-weather, high-resolution imaging. Using these characteristics, SAR images can avoid the influence of natural phenomena and obtain more transmission image information. [0003] Although SAR images are widely used in earth observation, SAR images themselves contain some disadvantages. First of all, due to the interference of coherent echoes scattered by the reflective surface in each resolution unit, a kind of multiplicative noise called speckle noise will be added to the image; secondly, the full polarization that is diff...

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): G06K9/00G06K9/34G06K9/62G06N3/08
CPCG06N3/084G06V20/13G06V10/267G06V2201/07G06F18/24
Inventor 张博程师皓
Owner 北京理工大学重庆创新中心
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