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

Method for improving detection precision of ships approaching shore in SAR image

A ship detection and image technology, applied in the field of synthetic aperture radar image interpretation, can solve problems such as insufficient detection accuracy of docked ships

Pending Publication Date: 2021-01-29
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF15 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The invention belongs to the technical field of synthetic aperture radar (SAR) image interpretation, discloses a method for improving the detection accuracy of docked ships in SAR images, and is used to solve the problem of insufficient detection accuracy of docked ships in the prior art

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 for improving detection precision of ships approaching shore in SAR image
  • Method for improving detection precision of ships approaching shore in SAR image
  • Method for improving detection precision of ships approaching shore in SAR image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0152] Attached below figure 1 对本发明的作进一步详细描述。

[0153] 步骤1、初始化数据集

[0154] Such as figure 2 所示,采用随机的方法调整SSDD数据集中的SAR图像次序,得到新的SSDD数据集。

[0155] 步骤2、建立生成模块

[0156] Such as figure 1 所示,按照经典的卷积神经网络方法,定义生成模块的输入层,记为L1;

[0157] 以生成模块的输入层L1作为输入,采用传统的全连接层方法对生成模块的输入层L1层进行非线性加权求和,得到8192维的输出向量L2pre;

[0158] 以8192维的输出向量L2pre作为输入,采用定义4中的经典的reshape操作将L2pre进行矩阵重排,得到4×4×512维的向量,记为L2;

[0159] 以4×4×512维的向量L2作为输入,采用定义5的反卷积方法,初始化反卷积操作的卷积核尺寸参数为4×4×256,对4×4×512维的向量L2进行上采样,得到上采样后的结果,记为L3。

[0160] 以上采样后结果L3作为输入,采用定义5的反卷积方法,初始化反卷积操作的卷积核尺寸参数为4×4×128,对上采样后结果L3进行上采样,得到上采样后的结果,记为L4。

[0161] 以上采样后结果L4作为输入,采用定义5的反卷积方法,初始化反卷积操作的卷积核尺寸参数为4×4×64,对L4进行上采样,得到上采样后的结果,记为L5。

[0162] 以上采样后结果L5作为输入,采用定义5的反卷积方法,初始化反卷积操作的卷积核尺寸参数为4×4×32,对L4进行上采样,得到上采样后的结果,记为L6。

[0163] 以上采样后结果L6作为输入,采用定义5的反卷积方法,初始化反卷积操作的卷积核尺寸参数为4×4×16,对L4进行上采样,得到上采样后的结果,记为L7。

[0164] 以上采样后结果L7作为输入,采用定义5的反卷积方法,初始化反卷积操作的卷积核尺寸参数为4×4×3,对L4进行上采样,得到上采样后的结果,记为L8。

[0165] 定义由上采样后结果L1、L2、L3、L4、L5、L6、L7、L8所组成的网络为生成模块。

[0166] 步骤3、建立判别模块

...

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 method for improving the detection precision of ships approaching a shore in an SAR image. The method is based on a deep learning theory, and mainly comprises four parts: a generative adversarial network, K-means clustering, scene amplification, and a classic detection network (Faster R-CNN, Cascade R-CNN, SSD, and RetinaNet). The generative adversarial network realizes image feature extraction, the K-means clustering method realizes image dichotomy by using extracted features to obtain a classification result of each image, scene amplification is performed to obtaina more balanced data set, and the classical detection network performs training by using the processed data set and executes a detection task. While the detection precision of the offshore ship is slightly improved, the detection precision of the ship approaching the shore on the Faster R-CNN, the Cascade R-CNN, the SSD and the RetinaNet network is improved by 8.60%, 8.32%, 18.15% and 12.40% respectively, and the detection precision of the ship approaching the shore is improved.

Description

technical field [0001] The invention belongs to the technical field of synthetic aperture radar (Synthetic Aperture Radar, SAR) image interpretation, and relates to a method for improving the detection accuracy of docked ships in SAR images. Background technique [0002] Synthetic Aperture Radar (SAR) is an active remote sensing technology that can work all day and all day. Compared with optical sensors, SAR can penetrate clouds and fog, and can also complete observation tasks under severe weather conditions. With the continuous improvement of SAR imaging resolution, ship target detection technology in SAR images has become a research hotspot. In particular, in terms of civilian use, SAR image ship detection technology can detect and search dangerous ships and carry out search and rescue; in military use, SAR image ship detection technology can monitor the sea to maintain national security. For details, please refer to the literature "Wang Zhiyong, Dou Hao, Tian Jinwen. Re...

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): G01S13/90G01S13/937G06K9/62G06N3/04G06N3/08
CPCG01S13/90G01S13/9094G01S13/937G06N3/08G06N3/045G06F18/23213
Inventor 张晓玲张天文柯潇师君韦顺军
Owner UNIV OF ELECTRONICS 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