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

Attention pyramid network-based SAR image multi-scale ship detection method

An attention, multi-scale technology, applied in the field of radar remote sensing, which can solve the problems of reduced detection accuracy and selection.

Active Publication Date: 2019-08-02
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF7 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned problems or deficiencies, in order to overcome the existing SAR image ship detection method in the face of the extracted massive features, it is impossible to adaptively select significant target features from the rich global features, and the detection accuracy rate is also reduced. , so that the feature extraction link in the multi-scale ship detection of SAR images has the ability to adaptively select salient features and highlight the characteristics of ships of different scales

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
  • Attention pyramid network-based SAR image multi-scale ship detection method
  • Attention pyramid network-based SAR image multi-scale ship detection method
  • Attention pyramid network-based SAR image multi-scale ship detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The ship data set SSDD that utilizes Chinese People's Liberation Army Naval Aviation University to propose below carries out multi-scale ship detection, and the present invention is described further.

[0061] The dataset used in the experiment is the SAR Image Ship Detection Dataset (SSDD), which includes different types of SAR ship images. Table 1 shows the types of SAR images in SSDD.

[0062] Table 1 Types of SAR images in SSDD

[0063]

[0064] In the experiment, the training set, validation set and test set are constructed in a ratio of 7:2:1. The initial value of the learning rate is set to 0.001, and it decays every 2000 steps with a decay rate of 0.1; the weight decay rate is 0.0001; the momentum value is set to 0.9; the scale of the anchors is set to {16 2 ,twenty four 2 ,40 2 ,60 2 ,80 2}, seven ratios {1:1, 1:2, 1:3, 2:1, 2:3, 3:1, 3:2} are set for each scale to meet the needs of different scale ship detection. The experiment obtained a multi-scale...

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 radar remote sensing, and relates to an attention pyramid network-based SAR image multi-scale ship detection method. On the basis of an existing featurepyramid network, the invention provides a multi-scale feature extraction method with adaptive selection of significant features, namely the feature pyramid network based on a dense attention mechanism, and the method is applied to SAR image multi-scale ship target detection. Prominent features are highlighted from global and local ranges through the channel attention model and the spatial attention model respectively, and better detection performance is obtained; meanwhile, the attention mechanism is applied to the multi-scale fusion process of each layer, the characteristics can be enhancedlayer by layer, false alarm targets can be effectively eliminated, and the detection precision is improved.

Description

technical field [0001] The invention belongs to the technical field of radar remote sensing, and relates to a multi-scale ship detection method for SAR images based on an attention pyramid network. Background technique [0002] In recent years, the use of Synthetic Aperture Radar (SAR) images for ship target detection on the sea surface has become a research hotspot around the world. As a large maritime country, our country has a long coastline and vast sea area. Using SAR to monitor the ocean in real time and carrying out research on ship target detection based on SAR images is of great significance to safeguard national security and safeguard my country's maritime rights and interests. [0003] At present, there are many types of ship targets, and the sizes are also different. Due to the large difference between ships of different scales, large-scale ships occupy more pixels in SAR images, while small-scale ship targets occupy very few pixels in high-resolution SAR images...

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): G06K9/00G06K9/46G06N3/04
CPCG06V20/13G06V10/462G06N3/045
Inventor 崔宗勇李其曹宗杰
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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